1<!DOCTYPE html> 2<html> 3 <head> 4 <meta charset="UTF-8"> 5 <title>ISCA Archive</title> 6 <meta name="viewport" content="width=device-width, initial-scale=1"> 7 8 9 <!-- JQuery helpers --> 10 <link rel="stylesheet" href="../resources/jquery.dataTables.min.css"> 11
11<script src="../resources/jquery-3.5.1.min.js"></script>
11 12
12<script src="../resources/jquery.dataTables.min.js"></script>
12 13
13<script src="../resources/accent-neutralise.js"></script>
13 14 15 <!-- Fonts --> 16 <link rel="stylesheet" href="../resources/fontawesome-free-subset/style.css"> 17 18 <!-- Overall theme --> 19 <link rel="stylesheet" href="../resources/w3.css"> 20 <link rel="stylesheet" href="../resources/w3-theme-blue.css"> 21
21<script src="../resources/w3.js"></script>
21 22 23 <!-- ISCA archive publication requirements --> 24 <base href="https://www.isca-archive.org/interspeech_2024/" /> 25 <link rel="stylesheet" href="../resources/is.css"> 26 </head> 27 <body> 28 29 <!-- Top menu bar, fixed on large/medium screens --> 30 <div class="w3-top w3-hide-small"> 31 <div class="w3-bar w3-grayscale-min w3-theme-d4 w3-center"> 32 <a href="../../index.html" class="w3-bar-item w3-button w3-theme-d2 w3-mobile"> 33 <i class="icon-home w3-margin-right"></i>ISCA 34 </a> 35 <a href="../index.html" class="w3-bar-item w3-button w3-mobile">Archive</a> 36 <a href="#" class="w3-bar-item w3-button w3-mobile">Interspeech 2024</a> 37 <a class="w3-bar-item w3-button w3-mobile" onclick="document.getElementById('sessionchooser').style.display='block'">Sessions 38 </a> 39 <a href="#bypaper" class="w3-bar-item w3-button w3-mobile"><i class="icon-search" style='margin-right:5px'></i>Search</a> 40 <a href="https://interspeech2024.org/" class="w3-bar-item w3-button w3-mobile w3-right">Website</a> 41 <a href="booklet.pdf" class="w3-bar-item w3-button w3-mobile w3-right">Booklet</a> 42 </div> 43 </div> 44 45 <!-- Top menu bar, scrollable on small screens --> 46 <div class="w3-hide-large w3-hide-medium"> 47 <div class="w3-bar w3-grayscale-min w3-theme-d4 w3-center"> 48 <span class="w3-bar-item w3-button w3-mobile w3-opacity-max"> </span> 49 <a href="../../index.html" class="w3-bar-item w3-button w3-mobile"> 50 <i class="icon-home w3-margin-right"></i>ISCA 51 </a> 52 <a href="../index.html" class="w3-bar-item w3-button w3-mobile">Archive</a> 53 <a href="#" class="w3-bar-item w3-button w3 w3-mobile" onclick="document.getElementById('sessionchooser').style.display='block'">Sessions 54 </a> 55 <a href="#bypaper" class="w3-bar-item w3-button w3-mobile"><i class="icon-search" style='margin-right:5px'></i>Search</a> 56 <a href="https://interspeech2024.org/" class="w3-bar-item w3-button w3-mobile w3-right">Website</a> 57 <a href="booklet.pdf" class="w3-bar-item w3-button w3-mobile w3-right">Booklet</a> 58 </div> 59 </div> 60 61 <!-- Papers help popup --> 62 <div id="help_papers" class="w3-modal"> 63 <div class="w3-modal-content w3-card-4 w3-greyscale w3-theme-d4 w3-padding w3-bordered"> 64 <div class="w3-container"> 65 <span onclick="document.getElementById('help_papers').style.display='none'" 66 class="w3-button w3-display-topright">×</span> 67 <div class="w3-container"> 68 <p class="w3-text">Click on column names to sort.</p> 69 <p class="w3-text">Searching uses the 'and' of terms e.g. <span class='w3-monospace'>Smith Interspeech</span> matches all papers by Smith in any Interspeech. The order of terms is not significant.</p> 70 <p class="w3-text">Use double quotes for exact phrasal matches e.g. <span class='w3-monospace'>"acoustic features"</span>.</p> 71 <p class="w3-text">Case is ignored.</p> 72 <p class="w3-text">Diacritics are optional e.g. <span class='w3-monospace'>lefevre</span> also matches <span class='w3-monospace'>lefèvre</span> (but not vice versa).</p> 73 <p class="w3-text">It can be useful to turn off spell-checking for the search box in your browser preferences.</p> 74 <p class="w3-text">If you prefer to scroll rather than page, increase the number in the show entries dropdown.</p> 75 </div> 76 </div> 77 </div> 78 </div> 79 80 81 <div class="w3-top w3-hide-medium w3-hide-large"> 82 <div class="w3-bar w3-grayscale-min w3-theme-d4 w3-opacity-max"> 83 <a href="#" class="w3-bar-item w3-button w3-theme-d2 w3-left">top</a> 84 </div> 85 </div> 86 87 <div class="w3-grayscale w3-theme-l5"> 88 89 <!-- Conference header --> 90 <div class="w3-container" id="about"> 91 <div class="w3-content" style="max-width:1100px;margin-top:50px; margin-bottom: 10px"> 92 <h2 class="w3-center w3-padding-16">
93 <span class="w3-text">Interspeech 2024</span> 94 </h2> 95 <h5 class="w3-text w3-center"> Kos, Greece<br>1-5 September 2024</h5> 96 <br> 97 <h5 class="w3-text w3-center">General Chairs: Itshak Lapidot, Sharon Gannot</h5> 98 <br> 99 <h5 class="w3-text w3-center">Technical Program Chairs: Jean-François Bonastre, Luciana Ferrer, Reinhold Haeb-Umbach</h5> 100 <pre class="w3-text w3-center">doi: 10.21437/Interspeech.2024</pre> 101 <pre class="w3-text w3-center">ISSN: 2958-1796</pre> 102 </div> 103 </div> 104 105 <!-- Sessions --> 106 <div class="w3-container"> 107 <div class="w3-content" style="max-width:1200px;margin-top: 10px"> 108 <div class="w3-content" style="height:10px" id="Keynote 1 ISCA Medallist"></div> 109 <div class="w3-card w3-round w3-white w3-padding"> 110 <div class="w3-container" style="margin-top:40px"> 111 <h4 class="w3-center">Keynote 1 ISCA Medallist</h4> 112 <hr> 113 <a class="w3-text" href="trancoso24_interspeech.html"> 114 <p> 115 Towards Responsible Speech Processing 116 <br> 117 <span class="w3-text w3-text-theme"> 118 Isabel Trancoso 119 </span> 120 </p> 121 </a> 122 </div> 123 </div> 124 <br> 125 <div class="w3-content" style="height:10px" id="L2 Speech, Bilingualism and Code-Switching"></div> 126 <div class="w3-card w3-round w3-white w3-padding"> 127 <div class="w3-container" style="margin-top:40px"> 128 <h4 class="w3-center">L2 Speech, Bilingualism and Code-Switching</h4> 129 <hr> 130 <a class="w3-text" href="wesolek24_interspeech.html"> 131 <p> 132 The influence of L2 accent strength and different error types on personality trait ratings 133 <br> 134 <span class="w3-text w3-text-theme"> 135 Sarah Wesolek, Piotr Gulgowski, Joanna Blaszczak, Marzena Zygis 136 </span> 137 </p> 138 </a> 139 <a class="w3-text" href="chi24_interspeech.html"> 140 <p> 141 Characterizing code-switching: Applying Linguistic Principles for Metric Assessment and Development 142 <br> 143 <span class="w3-text w3-text-theme"> 144 Jie Chi, Electra Wallington, Peter Bell 145 </span> 146 </p> 147 </a> 148 <a class="w3-text" href="xue24_interspeech.html"> 149 <p> 150 Towards a better understanding of receptive multilingualism: listening conditions and priming effects 151 <br> 152 <span class="w3-text w3-text-theme"> 153 Wei Xue, Ivan Yuen, Bernd Möbius 154 </span> 155 </p> 156 </a> 157 <a class="w3-text" href="mohapatra24b_interspeech.html"> 158 <p> 159 2.5D Vocal Tract Modeling: Bridging Low-Dimensional Efficiency with 3D Accuracy 160 <br>
161 <span class="w3-text w3-text-theme"> 162 Debasish Ray Mohapatra, Victor Zappi, Sidney Fels 163 </span> 164 </p> 165 </a> 166 </div> 167 </div> 168 <br> 169 <div class="w3-content" style="height:10px" id="Speaker Diarization 1"></div> 170 <div class="w3-card w3-round w3-white w3-padding"> 171 <div class="w3-container" style="margin-top:40px"> 172 <h4 class="w3-center">Speaker Diarization 1</h4> 173 <hr> 174 <a class="w3-text" href="chowdhury24_interspeech.html"> 175 <p> 176 Investigating Confidence Estimation Measures for Speaker Diarization 177 <br> 178 <span class="w3-text w3-text-theme">
179 Anurag Chowdhury, Abhinav Misra, Mark C. Fuhs, Monika Woszczyna 180 </span> 181 </p> 182 </a> 183 <a class="w3-text" href="li24x_interspeech.html"> 184 <p> 185 Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarization 186 <br> 187 <span class="w3-text w3-text-theme"> 188 Xiang Li, Vivek Govindan, Rohit Paturi, Sundararajan Srinivasan 189 </span> 190 </p> 191 </a> 192 <a class="w3-text" href="huang24d_interspeech.html"> 193 <p> 194 On the Success and Limitations of Auxiliary Network Based Word-Level End-to-End Neural Speaker Diarization 195 <br> 196 <span class="w3-text w3-text-theme"> 197 Yiling Huang, Weiran Wang, Guanlong Zhao, Hank Liao, Wei Xia, Quan Wang 198 </span> 199 </p> 200 </a> 201 <a class="w3-text" href="harkonen24_interspeech.html"> 202 <p> 203 EEND-M2F: Masked-attention mask transformers for speaker diarization 204 <br> 205 <span class="w3-text w3-text-theme"> 206 Marc Härkönen, Samuel J. Broughton, Lahiru Samarakoon 207 </span> 208 </p> 209 </a> 210 <a class="w3-text" href="yin24_interspeech.html"> 211 <p> 212 AFL-Net: Integrating Audio, Facial, and Lip Modalities with a Two-step Cross-attention for Robust Speaker Diarization in the Wild 213 <br> 214 <span class="w3-text w3-text-theme"> 215 YongKang Yin, Xu Li, Ying Shan, YueXian Zou 216 </span> 217 </p> 218 </a> 219 <a class="w3-text" href="arya24_interspeech.html"> 220 <p> 221 Exploiting Wavelet Scattering Transform for an Unsupervised Speaker Diarization in Deep Neural Network Framework 222 <br> 223 <span class="w3-text w3-text-theme"> 224 Arunav Arya, Murtiza Ali, Karan Nathwani 225 </span> 226 </p> 227 </a> 228 </div> 229 </div> 230 <br> 231 <div class="w3-content" style="height:10px" id="Speech and Audio Analysis and Representations"></div> 232 <div class="w3-card w3-round w3-white w3-padding"> 233 <div class="w3-container" style="margin-top:40px"> 234 <h4 class="w3-center">Speech and Audio Analysis and Representations</h4> 235 <hr> 236 <a class="w3-text" href="zhao24h_interspeech.html"> 237 <p> 238 MINT: Boosting Audio-Language Model via Multi-Target Pre-Training and Instruction Tuning 239 <br> 240 <span class="w3-text w3-text-theme"> 241 Hang Zhao, Yifei Xin, Zhesong Yu, Bilei Zhu, Lu Lu, Zejun Ma 242 </span> 243 </p> 244 </a> 245 <a class="w3-text" href="niizumi24_interspeech.html"> 246 <p> 247 M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation 248 <br>
249 <span class="w3-text w3-text-theme"> 250 Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Masahiro Yasuda, Shunsuke Tsubaki, Keisuke Imoto 251 </span> 252 </p> 253 </a> 254 <a class="w3-text" href="fujita24_interspeech.html"> 255 <p> 256 Audio Fingerprinting with Holographic Reduced Representations 257 <br> 258 <span class="w3-text w3-text-theme"> 259 Yusuke Fujita, Tatsuya Komatsu 260 </span> 261 </p> 262 </a> 263 <a class="w3-text" href="meyer24b_interspeech.html"> 264 <p> 265 RAST: A Reference-Audio Synchronization Tool for Dubbed Content 266 <br> 267 <span class="w3-text w3-text-theme"> 268 David Meyer, Eitan Abecassis, Clara Fernandez-Labrador, Christopher Schroers 269 </span> 270 </p> 271 </a> 272 <a class="w3-text" href="li24ja_interspeech.html"> 273 <p> 274 YOLOPitch: A Time-Frequency Dual-Branch YOLO Model for Pitch Estimation 275 <br> 276 <span class="w3-text w3-text-theme"> 277 Xuefei Li, Hao Huang, Ying Hu, Liang He, Jiabao Zhang, Yuyi Wang 278 </span> 279 </p> 280 </a> 281 <a class="w3-text" href="ullah24_interspeech.html"> 282 <p> 283 Reduce, Reuse, Recycle: Is Perturbed Data Better than Other Language Augmentation for Low Resource Self-Supervised Speech Models 284 <br> 285 <span class="w3-text w3-text-theme"> 286 Asad Ullah, Alessandro Ragano, Andrew Hines 287 </span> 288 </p> 289 </a> 290 <a class="w3-text" href="pieper24_interspeech.html"> 291 <p> 292 AlignNet: Learning dataset score alignment functions to enable better training of speech quality estimators 293 <br> 294 <span class="w3-text w3-text-theme"> 295 Jaden Pieper, Stephen Voran 296 </span> 297 </p> 298 </a> 299 </div> 300 </div> 301 <br> 302 <div class="w3-content" style="height:10px" id="Acoustic Event Detection and Classification 2"></div> 303 <div class="w3-card w3-round w3-white w3-padding"> 304 <div class="w3-container" style="margin-top:40px"> 305 <h4 class="w3-center">Acoustic Event Detection and Classification 2</h4> 306 <hr> 307 <a class="w3-text" href="liang24_interspeech.html"> 308 <p> 309 Improving Audio Classification with Low-Sampled Microphone Input: An Empirical Study Using Model Self-Distillation 310 <br> 311 <span class="w3-text w3-text-theme"> 312 Dawei Liang, Alice Zhang, David Harwath, Edison Thomaz 313 </span> 314 </p> 315 </a> 316 <a class="w3-text" href="mu24_interspeech.html"> 317 <p> 318 MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial
318-Temporal Domains for Sound Event Localization and Detection 319 <br> 320 <span class="w3-text w3-text-theme"> 321 Da Mu, Zhicheng Zhang, Haobo Yue 322 </span> 323 </p> 324 </a> 325 <a class="w3-text" href="nam24_interspeech.html"> 326 <p> 327 Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection 328 <br> 329 <span class="w3-text w3-text-theme"> 330 Hyeonuk Nam, Seong-Hu Kim, Deokki Min, Junhyeok Lee, Yong-Hwa Park 331 </span> 332 </p> 333 </a> 334 <a class="w3-text" href="ho24_interspeech.html"> 335 <p> 336 Stream-based Active Learning for Anomalous Sound Detection in Machine Condition Monitoring 337 <br> 338 <span class="w3-text w3-text-theme"> 339 Tuan Vu Ho, Kota Dohi, Yohei Kawaguchi 340 </span> 341 </p> 342 </a> 343 <a class="w3-text" href="jiang24c_interspeech.html"> 344 <p> 345 AnoPatch: Towards Better Consistency in Machine Anomalous Sound Detection 346 <br> 347 <span class="w3-text w3-text-theme"> 348 Anbai Jiang, Bing Han, Zhiqiang Lv, Yufeng Deng, Wei-Qiang Zhang, Xie Chen, Yanmin Qian, Jia Liu, Pingyi Fan 349 </span> 350 </p> 351 </a> 352 <a class="w3-text" href="xie24d_interspeech.html"> 353 <p> 354 FakeSound: Deepfake General Audio Detection 355 <br> 356 <span class="w3-text w3-text-theme"> 357 Zeyu Xie, Baihan Li, Xuenan Xu, Zheng Liang, Kai Yu, Mengyue Wu 358 </span> 359 </p> 360 </a> 361 <a class="w3-text" href="ghaffarzadegan24_interspeech.html"> 362 <p> 363 Sound of Traffic: A Dataset for Acoustic Traffic Identification and Counting 364 <br> 365 <span class="w3-text w3-text-theme"> 366 Shabnam Ghaffarzadegan, Luca Bondi, Wei-Chang Lin, Abinaya Kumar, Ho-Hsiang Wu, Hans-Georg Horst, Samarjit Das 367 </span> 368 </p> 369 </a> 370 </div> 371 </div> 372 <br> 373 <div class="w3-content" style="height:10px" id="Detection and Classification of Bioacoustic Signals"></div> 374 <div class="w3-card w3-round w3-white w3-padding"> 375 <div class="w3-container" style="margin-top:40px"> 376 <h4 class="w3-center">Detection and Classification of Bioacoustic Signals</h4> 377 <hr> 378 <a class="w3-text" href="kumar24_interspeech.html"> 379 <p> 380 Vision Transformer Segmentation for Visual Bird Sound Denoising 381 <br> 382 <span class="w3-text w3-text-theme"> 383 Sahil Kumar, Jialu Li, Youshan Zhang 384 </span> 385 </p> 386 </a> 387 <a class="w3-text" href="jing24_interspeech.html"> 388 <p> 389 DB3V: A Dialect Dominated Dataset of Bird Vocalisation for Cross-corpus Bird Species Recognition 390 <br>
391 <span class="w3-text w3-text-theme"> 392 Xin Jing, Luyang Zhang, Jiangjian Xie, Alexander Gebhard, Alice Baird, Björn Schuller 393 </span> 394 </p> 395 </a> 396 <a class="w3-text" href="cauzinille24_interspeech.html"> 397 <p> 398 Investigating self-supervised speech models' ability to classify animal vocalizations: The case of gibbon's vocal signatures 399 <br> 400 <span class="w3-text w3-text-theme"> 401 Jules Cauzinille, Benoît Favre, Ricard Marxer, Dena Clink, Abdul Hamid Ahmad, Arnaud Rey 402 </span> 403 </p> 404 </a> 405 <a class="w3-text" href="qiu24_interspeech.html"> 406 <p> 407 Study Selectively: An Adaptive Knowledge Distillation based on a Voting Network for Heart Sound Classification 408 <br> 409 <span class="w3-text w3-text-theme"> 410 Xihang Qiu, Lixian Zhu, Zikai Song, Zeyu Chen, Haojie Zhang, Kun Qian, Ye Zhang, Bin Hu, Yoshiharu Yamamoto, Björn W. Schuller 411 </span> 412 </p> 413 </a> 414 <a class="w3-text" href="lin24_interspeech.html"> 415 <p> 416 SimuSOE: A Simulated Snoring Dataset for Obstructive Sleep Apnea-Hypopnea Syndrome Evaluation during Wakefulness 417 <br> 418 <span class="w3-text w3-text-theme"> 419 Jie Lin, Xiuping Yang, Li Xiao, Xinhong Li, Weiyan Yi, Yuhong Yang, Weiping Tu, Xiong Chen 420 </span> 421 </p> 422 </a> 423 </div> 424 </div> 425 <br> 426 <div class="w3-content" style="height:10px" id="Acoustic Echo Cancellation"></div> 427 <div class="w3-card w3-round w3-white w3-padding"> 428 <div class="w3-container" style="margin-top:40px"> 429 <h4 class="w3-center">Acoustic Echo Cancellation</h4> 430 <hr> 431 <a class="w3-text" href="nayak24_interspeech.html"> 432 <p> 433 Multi-mic Echo Cancellation Coalesced with Beamforming for Real World Adverse Acoustic Conditions 434 <br> 435 <span class="w3-text w3-text-theme"> 436 Premanand Nayak, Kamini Sabu, M. Ali Basha Shaik 437 </span> 438 </p> 439 </a> 440 <a class="w3-text" href="khanagha24_interspeech.html"> 441 <p> 442 Interference Aware Training Target for DNN based joint Acoustic Echo Cancellation and Noise Suppression 443 <br> 444 <span class="w3-text w3-text-theme"> 445 Vahid Khanagha, Dimitris Koutsaidis, Kaustubh Kalgaonkar, Sriram Srinivasan 446 </span> 447 </p> 448 </a> 449 <a class="w3-text" href="gao24b_interspeech.html"> 450 <p> 451 Low Complexity Echo Delay Estimator Based on Binarized Feature Matching 452 <br>
453 <span class="w3-text w3-text-theme"> 454 Yi Gao, Xiang Su 455 </span> 456 </p> 457 </a> 458 <a class="w3-text" href="ni24_interspeech.html"> 459 <p> 460 MSA-DPCRN: A Multi-Scale Asymmetric Dual-Path Convolution Recurrent Network with Attentional Feature Fusion for Acoustic Echo Cancellation 461 <br> 462 <span class="w3-text w3-text-theme"> 463 Ye Ni, Cong Pang, Chengwei Huang, Cairong Zou 464 </span> 465 </p> 466 </a> 467 <a class="w3-text" href="schwartz24_interspeech.html"> 468 <p> 469 Efficient Joint Bemforming and Acoustic Echo Cancellation Structure for Conference Call Scenarios 470 <br> 471 <span class="w3-text w3-text-theme"> 472 Ofer Schwartz, Sharon Gannot 473 </span> 474 </p> 475 </a> 476 <a class="w3-text" href="zhao24b_interspeech.html"> 477 <p> 478 SDAEC: Signal Decoupling for Advancing Acoustic Echo Cancellation 479 <br> 480 <span class="w3-text w3-text-theme"> 481 Fei Zhao, Jinjiang Liu, Xueliang Zhang 482 </span> 483 </p> 484 </a> 485 </div> 486 </div> 487 <br> 488 <div class="w3-content" style="height:10px" id="Speech Synthesis: Voice Conversion 1"></div> 489 <div class="w3-card w3-round w3-white w3-padding"> 490 <div class="w3-container" style="margin-top:40px"> 491 <h4 class="w3-center">Speech Synthesis: Voice Conversion 1</h4> 492 <hr> 493 <a class="w3-text" href="seki24_interspeech.html"> 494 <p> 495 Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals 496 <br> 497 <span class="w3-text w3-text-theme"> 498 Kentaro Seki, Shinnosuke Takamichi, Norihiro Takamune, Yuki Saito, Kanami Imamura, Hiroshi Saruwatari 499 </span> 500 </p> 501 </a> 502 <a class="w3-text" href="baade24_interspeech.html"> 503 <p> 504 Neural Codec Language Models for Disentangled and Textless Voice Conversion 505 <br> 506 <span class="w3-text w3-text-theme"> 507 Alan Baade, Puyuan Peng, David Harwath 508 </span> 509 </p> 510 </a> 511 <a class="w3-text" href="morrison24_interspeech.html"> 512 <p> 513 Fine-Grained and Interpretable Neural Speech Editing 514 <br> 515 <span class="w3-text w3-text-theme"> 516 Max Morrison, Cameron Churchwell, Nathan Pruyne, Bryan Pardo 517 </span> 518 </p> 519 </a> 520 <a class="w3-text" href="kaneko24_interspeech.html"> 521 <p> 522 FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation 523 <br>
524 <span class="w3-text w3-text-theme"> 525 Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo 526 </span> 527 </p> 528 </a> 529 <a class="w3-text" href="ning24_interspeech.html"> 530 <p> 531 DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion 532 <br> 533 <span class="w3-text w3-text-theme"> 534 Ziqian Ning, Shuai Wang, Pengcheng Zhu, Zhichao Wang, Jixun Yao, Lei Xie, Mengxiao Bi 535 </span> 536 </p> 537 </a> 538 <a class="w3-text" href="qi24_interspeech.html"> 539 <p> 540 Towards Realistic Emotional Voice Conversion using Controllable Emotional Intensity 541 <br> 542 <span class="w3-text w3-text-theme"> 543 Tianhua Qi, Shiyan Wang, Cheng Lu, Yan Zhao, Yuan Zong, Wenming Zheng 544 </span> 545 </p> 546 </a> 547 </div> 548 </div> 549 <br> 550 <div class="w3-content" style="height:10px" id="Neural Network Architectures for ASR 2"></div> 551 <div class="w3-card w3-round w3-white w3-padding"> 552 <div class="w3-container" style="margin-top:40px"> 553 <h4 class="w3-center">Neural Network Architectures for ASR 2</h4> 554 <hr> 555 <a class="w3-text" href="nakagome24_interspeech.html"> 556 <p> 557 InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictions 558 <br> 559 <span class="w3-text w3-text-theme"> 560 Yu Nakagome, Michael Hentschel 561 </span> 562 </p> 563 </a> 564 <a class="w3-text" href="meng24_interspeech.html"> 565 <p> 566 SEQ-former: A context-enhanced and efficient automatic speech recognition framework 567 <br> 568 <span class="w3-text w3-text-theme"> 569 Qinglin Meng, Min Liu, Kaixun Huang, Kun Wei, Lei Xie, Zongfeng Quan, Weihong Deng, Quan Lu, Ning Jiang, Guoqing Zhao 570 </span> 571 </p> 572 </a> 573 <a class="w3-text" href="flynn24b_interspeech.html"> 574 <p> 575 How Much Context Does My Attention-Based ASR System Need? 576 <br> 577 <span class="w3-text w3-text-theme"> 578 Robert Flynn, Anton Ragni 579 </span> 580 </p> 581 </a> 582 <a class="w3-text" href="vitale24_interspeech.html"> 583 <p> 584 Rich speech signal: exploring and exploiting end-to-end automatic speech recognizersâ ability to model hesitation phenomena 585 <br> 586 <span class="w3-text w3-text-theme"> 587 Vincenzo Norman Vitale, Loredana Schettino, Francesco Cutugno 588 </span> 589 </p> 590 </a> 591 <a class="w3-text" href="zhang24q_interspeech.html"> 592 <p> 593 Transmitted and Aggregated Self-Attention for Automatic Speech Recognition 594 <br>
595 <span class="w3-text w3-text-theme"> 596 Tian-Hao Zhang, Xinyuan Qian, Feng Chen, Xu-Cheng Yin 597 </span> 598 </p> 599 </a> 600 <a class="w3-text" href="prabhu24_interspeech.html"> 601 <p> 602 MULTI-CONVFORMER: Extending Conformer with Multiple Convolution Kernels 603 <br> 604 <span class="w3-text w3-text-theme"> 605 Darshan Prabhu, Yifan Peng, Preethi Jyothi, Shinji Watanabe 606 </span> 607 </p> 608 </a> 609 <a class="w3-text" href="miyazaki24_interspeech.html"> 610 <p> 611 Exploring the Capability of Mamba in Speech Applications 612 <br> 613 <span class="w3-text w3-text-theme"> 614 Koichi Miyazaki, Yoshiki Masuyama, Masato Murata 615 </span> 616 </p> 617 </a> 618 <a class="w3-text" href="wan24_interspeech.html"> 619 <p> 620 Lightweight Transducer Based on Frame-Level Criterion 621 <br> 622 <span class="w3-text w3-text-theme"> 623 Genshun Wan, Mengzhi Wang, Tingzhi Mao, Hang Chen, Zhongfu Ye 624 </span> 625 </p> 626 </a> 627 <a class="w3-text" href="gupta24_interspeech.html"> 628 <p> 629 Exploring the limits of decoder-only models trained on public speech recognition corpora 630 <br> 631 <span class="w3-text w3-text-theme"> 632 Ankit Gupta, George Saon, Brian Kingsbury 633 </span> 634 </p> 635 </a> 636 <a class="w3-text" href="gong24b_interspeech.html"> 637 <p> 638 Contextual Biasing Speech Recognition in Speech-enhanced Large Language Model 639 <br> 640 <span class="w3-text w3-text-theme"> 641 Xun Gong, Anqi Lv, Zhiming Wang, Yanmin Qian 642 </span> 643 </p> 644 </a> 645 </div> 646 </div> 647 <br> 648 <div class="w3-content" style="height:10px" id="Decoding Algorithms"></div> 649 <div class="w3-card w3-round w3-white w3-padding"> 650 <div class="w3-container" style="margin-top:40px"> 651 <h4 class="w3-center">Decoding Algorithms</h4> 652 <hr> 653 <a class="w3-text" href="wang24k_interspeech.html"> 654 <p> 655 Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask 656 <br> 657 <span class="w3-text w3-text-theme"> 658 Tianzi Wang, Xurong Xie, Zhaoqing Li, Shoukang Hu, Zengrui Jin, Jiajun Deng, Mingyu Cui, Shujie Hu, Mengzhe Geng, Guinan Li, Helen Meng, Xunying Liu 659 </span> 660 </p> 661 </a> 662 <a class="w3-text" href="zou24_interspeech.html"> 663 <p> 664 E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition 665 <br>
666 <span class="w3-text w3-text-theme"> 667 Kun Zou, Fengyun Tan, Ziyang Zhuang, Chenfeng Miao, Tao Wei, Shaodan Zhai, Zijian Li, Wei Hu, Shaojun Wang, Jing Xiao 668 </span> 669 </p> 670 </a> 671 <a class="w3-text" href="ciaperoni24_interspeech.html"> 672 <p> 673 Beam-search SIEVE for low-memory speech recognition 674 <br> 675 <span class="w3-text w3-text-theme"> 676 Martino Ciaperoni, Athanasios Katsamanis, Aristides Gionis, Panagiotis Karras 677 </span> 678 </p> 679 </a> 680 <a class="w3-text" href="galvez24_interspeech.html"> 681 <p> 682 Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU 683 <br> 684 <span class="w3-text w3-text-theme"> 685 Daniel Galvez, Vladimir Bataev, Hainan Xu, Tim Kaldewey 686 </span> 687 </p> 688 </a> 689 <a class="w3-text" href="wang24w_interspeech.html"> 690 <p> 691 Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm 692 <br> 693 <span class="w3-text w3-text-theme"> 694 Weiran Wang, Zelin Wu, Diamantino Caseiro, Tsendsuren Munkhdalai, Khe Chai Sim, Pat Rondon, Golan Pundak, Gan Song, Rohit Prabhavalkar, Zhong Meng, Ding Zhao, Tara Sainath, Yanzhang He, Pedro Moreno Mengibar 695 </span> 696 </p> 697 </a> 698 <a class="w3-text" href="takagi24_interspeech.html"> 699 <p> 700 Text-only Domain Adaptation for CTC-based Speech Recognition through Substitution of Implicit Linguistic Information in the Search Space 701 <br> 702 <span class="w3-text w3-text-theme"> 703 Tatsunari Takagi, Yukoh Wakabayashi, Atsunori Ogawa, Norihide Kitaoka 704 </span> 705 </p> 706 </a> 707 </div> 708 </div> 709 <br> 710 <div class="w3-content" style="height:10px" id="Pronunciation Assessment"></div> 711 <div class="w3-card w3-round w3-white w3-padding"> 712 <div class="w3-container" style="margin-top:40px"> 713 <h4 class="w3-center">Pronunciation Assessment</h4> 714 <hr> 715 <a class="w3-text" href="wang24la_interspeech.html"> 716 <p> 717 Pitch-Aware RNN-T for Mandarin Chinese Mispronunciation Detection and Diagnosis 718 <br> 719 <span class="w3-text w3-text-theme"> 720 Xintong Wang, Mingqian Shi, Ye Wang 721 </span> 722 </p> 723 </a> 724 <a class="w3-text" href="chen24c_interspeech.html"> 725 <p> 726 MultiPA: A Multi-task Speech Pronunciation Assessment Model for Open Response Scenarios 727 <br> 728 <span class="w3-text w3-text-theme"> 729 Yu-Wen Chen, Zhou Yu, Julia Hirschberg 730 </span> 731 </p> 732 </a> 733 <a class="w3-text" href="cao24b_interspeech.html"> 734 <p> 735 A Framework for Phoneme-Level Pronunciation Assessment Using CTC 736 <br>
737 <span class="w3-text w3-text-theme"> 738 Xinwei Cao, Zijian Fan, Torbjørn Svendsen, Giampiero Salvi 739 </span> 740 </p> 741 </a> 742 <a class="w3-text" href="shahin24_interspeech.html"> 743 <p> 744 Phonological-Level Mispronunciation Detection and Diagnosis 745 <br> 746 <span class="w3-text w3-text-theme"> 747 Mostafa Shahin, Beena Ahmed 748 </span> 749 </p> 750 </a> 751 <a class="w3-text" href="do24_interspeech.html"> 752 <p> 753 Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment 754 <br> 755 <span class="w3-text w3-text-theme"> 756 Heejin Do, Wonjun Lee, Gary Geunbae Lee 757 </span> 758 </p> 759 </a> 760 <a class="w3-text" href="phan24_interspeech.html"> 761 <p> 762 Automated content assessment and feedback for Finnish L2 learners in a picture description speaking task 763 <br> 764 <span class="w3-text w3-text-theme"> 765 Nhan Phan, Anna von Zansen, Maria Kautonen, Ekaterina Voskoboinik, Tamas Grosz, Raili Hilden, Mikko Kurimo 766 </span> 767 </p> 768 </a> 769 </div> 770 </div> 771 <br> 772 <div class="w3-content" style="height:10px" id="Spoken Language Processing"></div> 773 <div class="w3-card w3-round w3-white w3-padding"> 774 <div class="w3-container" style="margin-top:40px"> 775 <h4 class="w3-center">Spoken Language Processing</h4> 776 <hr> 777 <a class="w3-text" href="wang24c_interspeech.html"> 778 <p> 779 Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning 780 <br> 781 <span class="w3-text w3-text-theme"> 782 Zhenyu Wang, Shuyu Kong, Li Wan, Biqiao Zhang, Yiteng Huang, Mumin Jin, Ming Sun, Xin Lei, Zhaojun Yang 783 </span> 784 </p> 785 </a> 786 <a class="w3-text" href="jung24_interspeech.html"> 787 <p> 788 Relational Proxy Loss for Audio-Text based Keyword Spotting 789 <br> 790 <span class="w3-text w3-text-theme"> 791 Youngmoon Jung, Seungjin Lee, Joon-Young Yang, Jaeyoung Roh, Chang Woo Han, Hoon-Young Cho 792 </span> 793 </p> 794 </a> 795 <a class="w3-text" href="jin24d_interspeech.html"> 796 <p> 797 CTC-aligned Audio-Text Embedding for Streaming Open-vocabulary Keyword Spotting 798 <br> 799 <span class="w3-text w3-text-theme"> 800 Sichen Jin, Youngmoon Jung, Seungjin Lee, Jaeyoung Roh, Changwoo Han, Hoonyoung Cho 801 </span> 802 </p> 803 </a> 804 <a class="w3-text" href="li24r_interspeech.html"> 805 <p> 806 Text-aware Speech Separation for Multi-talker Keyword Spotting 807 <br>
808 <span class="w3-text w3-text-theme"> 809 Haoyu Li, Baochen Yang, Yu Xi, Linfeng Yu, Tian Tan, Hao Li, Kai Yu 810 </span> 811 </p> 812 </a> 813 <a class="w3-text" href="yen24_interspeech.html"> 814 <p> 815 Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition 816 <br> 817 <span class="w3-text w3-text-theme"> 818 Hao Yen, Pin-Jui Ku, Sabato Marco Siniscalchi, Chin-Hui Lee 819 </span> 820 </p> 821 </a> 822 <a class="w3-text" href="monteiro24_interspeech.html"> 823 <p> 824 Adding User Feedback To Enhance CB-Whisper 825 <br> 826 <span class="w3-text w3-text-theme"> 827 Raul Monteiro 828 </span> 829 </p> 830 </a> 831 <a class="w3-text" href="peng24b_interspeech.html"> 832 <p> 833 OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer 834 <br> 835 <span class="w3-text w3-text-theme"> 836 Yifan Peng, Jinchuan Tian, William Chen, Siddhant Arora, Brian Yan, Yui Sudo, Muhammad Shakeel, Kwanghee Choi, Jiatong Shi, Xuankai Chang, Jee-weon Jung, Shinji Watanabe 837 </span> 838 </p> 839 </a> 840 </div> 841 </div> 842 <br> 843 <div class="w3-content" style="height:10px" id="Spoken Machine Translation 2"></div> 844 <div class="w3-card w3-round w3-white w3-padding"> 845 <div class="w3-container" style="margin-top:40px"> 846 <h4 class="w3-center">Spoken Machine Translation 2</h4> 847 <hr> 848 <a class="w3-text" href="chen24m_interspeech.html"> 849 <p> 850 Parameter-Efficient Adapter Based on Pre-trained Models for Speech Translation 851 <br> 852 <span class="w3-text w3-text-theme"> 853 Nan Chen, Yonghe Wang, Feilong Bao 854 </span> 855 </p> 856 </a> 857 <a class="w3-text" href="abdullah24_interspeech.html"> 858 <p> 859 Wave to Interlingua: Analyzing Representations of Multilingual Speech Transformers for Spoken Language Translation 860 <br> 861 <span class="w3-text w3-text-theme"> 862 Badr M. Abdullah, Mohammed Maqsood Shaik, Dietrich Klakow 863 </span> 864 </p> 865 </a> 866 <a class="w3-text" href="chen24w_interspeech.html"> 867 <p> 868 Knowledge-Preserving Pluggable Modules for Multilingual Speech Translation Tasks 869 <br> 870 <span class="w3-text w3-text-theme"> 871 Nan Chen, Yonghe Wang, Feilong Bao 872 </span> 873 </p> 874 </a> 875 <a class="w3-text" href="rabatin24_interspeech.html"> 876 <p> 877 Navigating the Minefield of MT Beam Search in Cascaded Streaming Speech Translation 878 <br>
879 <span class="w3-text w3-text-theme"> 880 Rastislav Rabatin, Frank Seide, Ernie Chang 881 </span> 882 </p> 883 </a> 884 <a class="w3-text" href="wang24aa_interspeech.html"> 885 <p> 886 Soft Language Identification for Language-Agnostic Many-to-One End-to-End Speech Translation 887 <br> 888 <span class="w3-text w3-text-theme"> 889 Peidong Wang, Jian Xue, Jinyu Li, Junkun Chen, Aswin Shanmugam Subramanian 890 </span> 891 </p> 892 </a> 893 <a class="w3-text" href="oneata24_interspeech.html"> 894 <p> 895 Translating speech with just images 896 <br> 897 <span class="w3-text w3-text-theme"> 898 Dan Oneata, Herman Kamper 899 </span> 900 </p> 901 </a> 902 <a class="w3-text" href="khurana24_interspeech.html"> 903 <p> 904 ZeroST: Zero-Shot Speech Translation 905 <br> 906 <span class="w3-text w3-text-theme"> 907 Sameer Khurana, Chiori Hori, Antoine Laurent, Gordon Wichern, Jonathan Le Roux 908 </span> 909 </p> 910 </a> 911 </div> 912 </div> 913 <br> 914 <div class="w3-content" style="height:10px" id="Biosignal-enabled Spoken Communication"></div> 915 <div class="w3-card w3-round w3-white w3-padding"> 916 <div class="w3-container" style="margin-top:40px"> 917 <h4 class="w3-center">Biosignal-enabled Spoken Communication</h4> 918 <hr> 919 <a class="w3-text" href="li24ca_interspeech.html"> 920 <p> 921 A multimodal approach to study the nature of coordinative patterns underlying speech rhythm 922 <br> 923 <span class="w3-text w3-text-theme"> 924 Jinyu Li, Leonardo Lancia 925 </span> 926 </p> 927 </a> 928 <a class="w3-text" href="wu24k_interspeech.html"> 929 <p> 930 Towards EMG-to-Speech with Necklace Form Factor 931 <br> 932 <span class="w3-text w3-text-theme"> 933 Peter Wu, Ryan Kaveh, Raghav Nautiyal, Christine Zhang, Albert Guo, Anvitha Kachinthaya, Tavish Mishra, Bohan Yu, Alan W Black, Rikky Muller, Gopala Krishna Anumanchipalli 934 </span> 935 </p> 936 </a> 937 <a class="w3-text" href="bras24_interspeech.html"> 938 <p> 939 Using articulated speech EEG signals for imagined speech decoding 940 <br> 941 <span class="w3-text w3-text-theme"> 942 Chris Bras, Tanvina Patel, Odette Scharenborg 943 </span> 944 </p> 945 </a> 946 <a class="w3-text" href="kwon24_interspeech.html"> 947 <p> 948 Direct Speech Synthesis from Non-Invasive, Neuromagnetic Signals 949 <br>
950 <span class="w3-text w3-text-theme"> 951 Jinuk Kwon, David Harwath, Debadatta Dash, Paul Ferrari, Jun Wang 952 </span> 953 </p> 954 </a> 955 <a class="w3-text" href="yang24o_interspeech.html"> 956 <p> 957 Optical Flow Guided Tongue Trajectory Generation for Diffusion-based Acoustic to Articulatory Inversion 958 <br> 959 <span class="w3-text w3-text-theme"> 960 Yudong Yang, Rongfeng Su, Rukiye Ruzi, Manwa Ng, Shaofeng Zhao, Nan Yan, Lan Wang 961 </span> 962 </p> 963 </a> 964 <a class="w3-text" href="jain24_interspeech.html"> 965 <p> 966 Multimodal Segmentation for Vocal Tract Modeling 967 <br> 968 <span class="w3-text w3-text-theme"> 969 Rishi Jain, Bohan Yu, Peter Wu, Tejas Prabhune, Gopala Anumanchipalli 970 </span> 971 </p> 972 </a> 973 <a class="w3-text" href="bandekar24_interspeech.html"> 974 <p> 975 Articulatory synthesis using representations learnt through phonetic label-aware contrastive loss 976 <br> 977 <span class="w3-text w3-text-theme"> 978 Jesuraj Bandekar, Sathvik Udupa, Prasanta Kumar Ghosh 979 </span> 980 </p> 981 </a> 982 <a class="w3-text" href="yan24b_interspeech.html"> 983 <p> 984 Auditory Attention Decoding in Four-Talker Environment with EEG 985 <br> 986 <span class="w3-text w3-text-theme"> 987 Yujie Yan, Xiran Xu, Haolin Zhu, Pei Tian, Zhongshu Ge, Xihong Wu, Jing Chen 988 </span> 989 </p> 990 </a> 991 <a class="w3-text" href="lin24f_interspeech.html"> 992 <p> 993 ASA: An Auditory Spatial Attention Dataset with Multiple Speaking Locations 994 <br> 995 <span class="w3-text w3-text-theme"> 996 Zijie Lin, Tianyu He, Siqi Cai, Haizhou Li 997 </span> 998 </p> 999 </a> 1000 <a class="w3-text" href="pahuja24_interspeech.html"> 1001 <p> 1002 Leveraging Graphic and Convolutional Neural Networks for Auditory Attention Detection with EEG 1003 <br> 1004 <span class="w3-text w3-text-theme"> 1005 Saurav Pahuja, Gabriel Ivucic, Pascal Himmelmann, Siqi Cai, Tanja Schultz, Haizhou Li 1006 </span> 1007 </p> 1008 </a> 1009 </div> 1010 </div> 1011 <br> 1012 <div class="w3-content" style="height:10px" id="Individual and Social Factors in Phonetics"></div> 1013 <div class="w3-card w3-round w3-white w3-padding"> 1014 <div class="w3-container" style="margin-top:40px"> 1015 <h4 class="w3-center">Individual and Social Factors in Phonetics</h4> 1016 <hr> 1017 <a class="w3-text" href="pistor24_interspeech.html"> 1018 <p> 1019 Echoes of Implicit Bias Exploring Aesthetics and Social Meanings of Swiss German Dialect Features 1020 <br>
1021 <span class="w3-text w3-text-theme"> 1022 Tillmann Pistor, Adrian Leemann 1023 </span> 1024 </p> 1025 </a> 1026 <a class="w3-text" href="li24ra_interspeech.html"> 1027 <p> 1028 In search of structure and correspondence in intra-speaker trial-to-trial variability 1029 <br> 1030 <span class="w3-text w3-text-theme"> 1031 Vivian G. Li 1032 </span> 1033 </p> 1034 </a> 1035 <a class="w3-text" href="smith24_interspeech.html"> 1036 <p> 1037 Modelled Multivariate Overlap: A method for measuring vowel merger 1038 <br> 1039 <span class="w3-text w3-text-theme"> 1040 Irene Smith, Morgan Sonderegger, The Spade Consortium 1041 </span> 1042 </p> 1043 </a> 1044 <a class="w3-text" href="ochi24_interspeech.html"> 1045 <p> 1046 Entrainment Analysis and Prosody Prediction of Subsequent Interlocutorâs Backchannels in Dialogue 1047 <br> 1048 <span class="w3-text w3-text-theme"> 1049 Keiko Ochi, Koji Inoue, Divesh Lala, Tatsuya Kawahara 1050 </span> 1051 </p> 1052 </a> 1053 <a class="w3-text" href="tanner24_interspeech.html"> 1054 <p> 1055 Exploring the anatomy of articulation rate in spontaneous English speech: relationships between utterance length effects and social factors 1056 <br> 1057 <span class="w3-text w3-text-theme"> 1058 James Tanner, Morgan Sonderegger, Jane Stuart-Smith, Tyler Kendall, Jeff Mielke, Robin Dodsworth, Erik Thomas 1059 </span> 1060 </p> 1061 </a> 1062 <a class="w3-text" href="taylor24_interspeech.html"> 1063 <p> 1064 Familiar and Unfamiliar Speaker Identification in Speech and Singing 1065 <br> 1066 <span class="w3-text w3-text-theme"> 1067 Katelyn Taylor, Amelia Gully, Helena Daffern 1068 </span> 1069 </p> 1070 </a> 1071 </div> 1072 </div> 1073 <br> 1074 <div class="w3-content" style="height:10px" id="Paralinguistics"></div> 1075 <div class="w3-card w3-round w3-white w3-padding"> 1076 <div class="w3-container" style="margin-top:40px"> 1077 <h4 class="w3-center">Paralinguistics</h4> 1078 <hr> 1079 <a class="w3-text" href="parragallego24_interspeech.html"> 1080 <p> 1081 Cross-transfer Knowledge between Speech and Text Encoders to Evaluate Customer Satisfaction 1082 <br> 1083 <span class="w3-text w3-text-theme"> 1084 Luis Felipe Parra-Gallego, Tilak Purohit, Bogdan Vlasenko, Juan Rafael Orozco-Arroyave, Mathew Magimai.-Doss 1085 </span> 1086 </p> 1087 </a> 1088 <a class="w3-text" href="kodali24_interspeech.html"> 1089 <p> 1090 Fine-tuning of Pre-trained Models for Classification of Vocal Intensity Category from Speech Signals 1091 <br>
1092 <span class="w3-text w3-text-theme"> 1093 Manila Kodali, Sudarsana Reddy Kadiri, Paavo Alku 1094 </span> 1095 </p> 1096 </a> 1097 <a class="w3-text" href="kathan24_interspeech.html"> 1098 <p> 1099 Real-world PTSD Recognition: A Cross-corpus and Cross-linguistic Evaluation 1100 <br> 1101 <span class="w3-text w3-text-theme"> 1102 Alexander Kathan, Martin Bürger, Andreas Triantafyllopoulos, Sabrina Milkus, Jonas Hohmann, Pauline Muderlak, Jürgen Schottdorf, Richard Musil, Björn Schuller, Shahin Amiriparian 1103 </span> 1104 </p> 1105 </a> 1106 <a class="w3-text" href="bhattacharya24_interspeech.html"> 1107 <p> 1108 Switching Tongues, Sharing Hearts: Identifying the Relationship between Empathy and Code-switching in Speech 1109 <br> 1110 <span class="w3-text w3-text-theme"> 1111 Debasmita Bhattacharya, Eleanor Lin, Run Chen, Julia Hirschberg 1112 </span> 1113 </p> 1114 </a> 1115 </div> 1116 </div> 1117 <br> 1118 <div class="w3-content" style="height:10px" id="Speaker Recognition: Adversarial and Spoofing Attacks"></div> 1119 <div class="w3-card w3-round w3-white w3-padding"> 1120 <div class="w3-container" style="margin-top:40px"> 1121 <h4 class="w3-center">Speaker Recognition: Adversarial and Spoofing Attacks</h4> 1122 <hr> 1123 <a class="w3-text" href="rosello24_interspeech.html"> 1124 <p> 1125 Anti-spoofing Ensembling Model: Dynamic Weight Allocation in Ensemble Models for Improved Voice Biometrics Security 1126 <br> 1127 <span class="w3-text w3-text-theme"> 1128 Eros Rosello, Angel M. Gomez, Iván López-Espejo, Antonio M. Peinado, Juan M. MartÃn-Doñas 1129 </span> 1130 </p> 1131 </a> 1132 <a class="w3-text" href="zhang24j_interspeech.html"> 1133 <p> 1134 Spoof Diarization: "What Spoofed When" in Partially Spoofed Audio 1135 <br> 1136 <span class="w3-text w3-text-theme"> 1137 Lin Zhang, Xin Wang, Erica Cooper, Mireia Diez, Federico Landini, Nicholas Evans, Junichi Yamagishi 1138 </span> 1139 </p> 1140 </a> 1141 <a class="w3-text" href="wu24b_interspeech.html"> 1142 <p> 1143 Spoofing Speech Detection by Modeling Local Spectro-Temporal and Long-term Dependency 1144 <br> 1145 <span class="w3-text w3-text-theme"> 1146 Haochen Wu, Wu Guo, Zhentao Zhang, Wenting Zhao, Shengyu Peng, Jie Zhang 1147 </span> 1148 </p> 1149 </a> 1150 <a class="w3-text" href="lu24b_interspeech.html"> 1151 <p> 1152 Improving Copy-Synthesis Anti-Spoofing Training Method with Rhythm and Speaker Perturbation 1153 <br>
1154 <span class="w3-text w3-text-theme"> 1155 Jingze Lu, Yuxiang Zhang, Zhuo Li, Zengqiang Shang, Wenchao Wang, Pengyuan Zhang 1156 </span> 1157 </p> 1158 </a> 1159 <a class="w3-text" href="kan24_interspeech.html"> 1160 <p> 1161 VoiceDefense: Protecting Automatic Speaker Verification Models Against Black-box Adversarial Attacks 1162 <br> 1163 <span class="w3-text w3-text-theme"> 1164 Yip Keng Kan, Ke Xu, Hao Li, Jie Shi 1165 </span> 1166 </p> 1167 </a> 1168 <a class="w3-text" href="chen24p_interspeech.html"> 1169 <p> 1170 Neural Codec-based Adversarial Sample Detection for Speaker Verification 1171 <br> 1172 <span class="w3-text w3-text-theme"> 1173 Xuanjun Chen, Jiawei Du, Haibin Wu, Jyh-Shing Roger Jang, Hung-yi Lee 1174 </span> 1175 </p> 1176 </a> 1177 <a class="w3-text" href="chen24_interspeech.html"> 1178 <p> 1179 Textual-Driven Adversarial Purification for Speaker Verification 1180 <br> 1181 <span class="w3-text w3-text-theme"> 1182 Sizhou Chen, Yibo Bai, Jiadi Yao, Xiao-Lei Zhang, Xuelong Li 1183 </span> 1184 </p> 1185 </a> 1186 <a class="w3-text" href="li24g_interspeech.html"> 1187 <p> 1188 Boosting the Transferability of Adversarial Examples with Gradient-Aligned Ensemble Attack for Speaker Recognition 1189 <br> 1190 <span class="w3-text w3-text-theme"> 1191 Zhuhai Li, Jie Zhang, Wu Guo, Haochen Wu 1192 </span> 1193 </p> 1194 </a> 1195 <a class="w3-text" href="truong24b_interspeech.html"> 1196 <p> 1197 Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection 1198 <br> 1199 <span class="w3-text w3-text-theme"> 1200 Duc-Tuan Truong, Ruijie Tao, Tuan Nguyen, Hieu-Thi Luong, Kong Aik Lee, Eng Siong Chng 1201 </span> 1202 </p> 1203 </a> 1204 </div> 1205 </div> 1206 <br> 1207 <div class="w3-content" style="height:10px" id="Audio Event Detection and Classification 1"></div> 1208 <div class="w3-card w3-round w3-white w3-padding"> 1209 <div class="w3-container" style="margin-top:40px"> 1210 <h4 class="w3-center">Audio Event Detection and Classification 1</h4> 1211 <hr> 1212 <a class="w3-text" href="feng24b_interspeech.html"> 1213 <p> 1214 Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling? 1215 <br> 1216 <span class="w3-text w3-text-theme"> 1217 Tiantian Feng, Dimitrios Dimitriadis, Shrikanth S. Narayanan 1218 </span> 1219 </p> 1220 </a> 1221 <a class="w3-text" href="dinkel24b_interspeech.html"> 1222 <p> 1223 Scaling up masked audio encoder learning for general audio classification 1224 <br>
1225 <span class="w3-text w3-text-theme"> 1226 Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang, Bin Wang 1227 </span> 1228 </p> 1229 </a> 1230 <a class="w3-text" href="yadav24_interspeech.html"> 1231 <p> 1232 Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations 1233 <br> 1234 <span class="w3-text w3-text-theme"> 1235 Sarthak Yadav, Zheng-Hua Tan 1236 </span> 1237 </p> 1238 </a> 1239 <a class="w3-text" href="cai24_interspeech.html"> 1240 <p> 1241 MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection 1242 <br> 1243 <span class="w3-text w3-text-theme"> 1244 Pengfei Cai, Yan Song, Kang Li, Haoyu Song, Ian McLoughlin 1245 </span> 1246 </p> 1247 </a> 1248 <a class="w3-text" href="ebbers24_interspeech.html"> 1249 <p> 1250 Sound Event Bounding Boxes 1251 <br> 1252 <span class="w3-text w3-text-theme"> 1253 Janek Ebbers, François G. Germain, Gordon Wichern, Jonathan Le Roux 1254 </span> 1255 </p> 1256 </a> 1257 <a class="w3-text" href="li24k_interspeech.html"> 1258 <p> 1259 Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Network 1260 <br> 1261 <span class="w3-text w3-text-theme"> 1262 Yanxiong Li, Jiaxin Tan, Guoqing Chen, Jialong Li, Yongjie Si, Qianhua He 1263 </span> 1264 </p> 1265 </a> 1266 </div> 1267 </div> 1268 <br> 1269 <div class="w3-content" style="height:10px" id="Source Separation 2"></div> 1270 <div class="w3-card w3-round w3-white w3-padding"> 1271 <div class="w3-container" style="margin-top:40px"> 1272 <h4 class="w3-center">Source Separation 2</h4> 1273 <hr> 1274 <a class="w3-text" href="taherian24_interspeech.html"> 1275 <p> 1276 Towards Explainable Monaural Speaker Separation with Auditory-based Training 1277 <br> 1278 <span class="w3-text w3-text-theme"> 1279 Hassan Taherian, Vahid Ahmadi Kalkhorani, Ashutosh Pandey, Daniel Wong, Buye Xu, DeLiang Wang 1280 </span> 1281 </p> 1282 </a> 1283 <a class="w3-text" href="ewert24_interspeech.html"> 1284 <p> 1285 Does the Lombard Effect Matter in Speech Separation? Introducing the Lombard-GRID-2mix Dataset 1286 <br> 1287 <span class="w3-text w3-text-theme"> 1288 Iva Ewert, Marvin Borsdorf, Haizhou Li, Tanja Schultz 1289 </span> 1290 </p> 1291 </a> 1292 <a class="w3-text" href="pan24_interspeech.html"> 1293 <p> 1294 PARIS: Pseudo-AutoRegressIve Siamese Training for Online Speech Separation 1295 <br>
1296 <span class="w3-text w3-text-theme"> 1297 Zexu Pan, Gordon Wichern, François G. Germain, Kohei Saijo, Jonathan Le Roux 1298 </span> 1299 </p> 1300 </a> 1301 <a class="w3-text" href="zhang24p_interspeech.html"> 1302 <p> 1303 OR-TSE: An Overlap-Robust Speaker Encoder for Target Speech Extraction 1304 <br> 1305 <span class="w3-text w3-text-theme"> 1306 Yiru Zhang, Linyu Yao, Qun Yang 1307 </span> 1308 </p> 1309 </a> 1310 <a class="w3-text" href="hsieh24b_interspeech.html"> 1311 <p> 1312 Multimodal Representation Loss Between Timed Text and Audio for Regularized Speech Separation 1313 <br> 1314 <span class="w3-text w3-text-theme"> 1315 Tsun-An Hsieh, Heeyoul Choi, Minje Kim 1316 </span> 1317 </p> 1318 </a> 1319 <a class="w3-text" href="lin24g_interspeech.html"> 1320 <p> 1321 SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech 1322 <br> 1323 <span class="w3-text w3-text-theme"> 1324 Jingru Lin, Meng Ge, Junyi Ao, Liqun Deng, Haizhou Li 1325 </span> 1326 </p> 1327 </a> 1328 <a class="w3-text" href="wang24g_interspeech.html"> 1329 <p> 1330 TSE-PI: Target Sound Extraction under Reverberant Environments with Pitch Information 1331 <br> 1332 <span class="w3-text w3-text-theme"> 1333 Yiwen Wang, Xihong Wu 1334 </span> 1335 </p> 1336 </a> 1337 <a class="w3-text" href="saijo24_interspeech.html"> 1338 <p> 1339 Enhanced Reverberation as Supervision for Unsupervised Speech Separation 1340 <br> 1341 <span class="w3-text w3-text-theme"> 1342 Kohei Saijo, Gordon Wichern, François G. Germain, Zexu Pan, Jonathan Le Roux 1343 </span> 1344 </p> 1345 </a> 1346 </div> 1347 </div> 1348 <br> 1349 <div class="w3-content" style="height:10px" id="Noise Reduction, Dereverberation, and Echo Cancellation"></div> 1350 <div class="w3-card w3-round w3-white w3-padding"> 1351 <div class="w3-container" style="margin-top:40px"> 1352 <h4 class="w3-center">Noise Reduction, Dereverberation, and Echo Cancellation</h4> 1353 <hr> 1354 <a class="w3-text" href="zhao24_interspeech.html"> 1355 <p> 1356 Deep Echo Path Modeling for Acoustic Echo Cancellation 1357 <br> 1358 <span class="w3-text w3-text-theme"> 1359 Fei Zhao, Chenggang Zhang, Shulin He, Jinjiang Liu, Xueliang Zhang 1360 </span> 1361 </p> 1362 </a> 1363 <a class="w3-text" href="guo24_interspeech.html"> 1364 <p> 1365 Graph Attention Based Multi-Channel U-Net for Speech Dereverberation With Ad-Hoc Microphone Arrays 1366 <br>
1367 <span class="w3-text w3-text-theme"> 1368 Hongmei Guo, Yijiang Chen, Xiao-Lei Zhang, Xuelong Li 1369 </span> 1370 </p> 1371 </a> 1372 <a class="w3-text" href="bahrman24_interspeech.html"> 1373 <p> 1374 Speech dereverberation constrained on room impulse response characteristics 1375 <br> 1376 <span class="w3-text w3-text-theme"> 1377 Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard 1378 </span> 1379 </p> 1380 </a> 1381 <a class="w3-text" href="yuan24_interspeech.html"> 1382 <p> 1383 DeWinder: Single-Channel Wind Noise Reduction using Ultrasound Sensing 1384 <br> 1385 <span class="w3-text w3-text-theme"> 1386 Kuang Yuan, Shuo Han, Swarun Kumar, Bhiksha Raj 1387 </span> 1388 </p> 1389 </a> 1390 <a class="w3-text" href="barnhill24_interspeech.html"> 1391 <p> 1392 ANIMAL-CLEAN â A Deep Denoising Toolkit for Animal-Independent Signal Enhancement 1393 <br> 1394 <span class="w3-text w3-text-theme"> 1395 Alexander Barnhill, Elmar Noeth, Andreas Maier, Christian Bergler 1396 </span> 1397 </p> 1398 </a> 1399 <a class="w3-text" href="nayak24b_interspeech.html"> 1400 <p> 1401 Elucidating Clock-drift Using Real-world Audios In Wireless Mode For Time-offset Insensitive End-to-End Asynchronous Acoustic Echo Cancellation 1402 <br> 1403 <span class="w3-text w3-text-theme"> 1404 Premanand Nayak, M. Ali Basha Shaik 1405 </span> 1406 </p> 1407 </a> 1408 <a class="w3-text" href="wang24o_interspeech.html"> 1409 <p> 1410 QMixCAT: Unsupervised Speech Enhancement Using Quality-guided Signal Mixing and Competitive Alternating Model Training 1411 <br> 1412 <span class="w3-text w3-text-theme"> 1413 Shilin Wang, Haixin Guan, Yanhua Long 1414 </span> 1415 </p> 1416 </a> 1417 </div> 1418 </div> 1419 <br> 1420 <div class="w3-content" style="height:10px" id="Computationally-Efficient Speech Enhancement"></div> 1421 <div class="w3-card w3-round w3-white w3-padding"> 1422 <div class="w3-container" style="margin-top:40px"> 1423 <h4 class="w3-center">Computationally-Efficient Speech Enhancement</h4> 1424 <hr> 1425 <a class="w3-text" href="bae24_interspeech.html"> 1426 <p> 1427 Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds 1428 <br> 1429 <span class="w3-text w3-text-theme"> 1430 Hanbin Bae, Pavel Andreev, Azat Saginbaev, Nicholas Babaev, WonJun Lee, Hosang Sung, Hoon-Young Cho 1431 </span> 1432 </p> 1433 </a> 1434 <a class="w3-text" href="gholami24_interspeech.html"> 1435 <p> 1436 Knowledge Distillation for Tiny Speech Enhancement with Latent Feature Augmentation 1437 <br>
1438 <span class="w3-text w3-text-theme"> 1439 Behnam Gholami, Mostafa El-Khamy, KeeBong Song 1440 </span> 1441 </p> 1442 </a> 1443 <a class="w3-text" href="zhang24o_interspeech.html"> 1444 <p> 1445 Sub-PNWR: Speech Enhancement Based on Signal Sub-Band Splitting and Pseudo Noisy Waveform Reconstruction Loss 1446 <br> 1447 <span class="w3-text w3-text-theme"> 1448 Yuewei Zhang, Huanbin Zou, Jie Zhu 1449 </span> 1450 </p> 1451 </a> 1452 <a class="w3-text" href="zhao24c_interspeech.html"> 1453 <p> 1454 Streamlining Speech Enhancement DNNs: an Automated Pruning Method Based on Dependency Graph with Advanced Regularized Loss Strategies 1455 <br> 1456 <span class="w3-text w3-text-theme"> 1457 Zugang Zhao, Jinghong Zhang, Yonghui Liu, Jianbing Liu, Kai Niu, Zhiqiang He 1458 </span> 1459 </p> 1460 </a> 1461 <a class="w3-text" href="zhang24k_interspeech.html"> 1462 <p> 1463 Lightweight Dynamic Sparse Transformer for Monaural Speech Enhancement 1464 <br> 1465 <span class="w3-text w3-text-theme"> 1466 Zehua Zhang, Xuyi Zhuang, Yukun Qian, Mingjiang Wang 1467 </span> 1468 </p> 1469 </a> 1470 <a class="w3-text" href="lin24h_interspeech.html"> 1471 <p> 1472 MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enhancement 1473 <br> 1474 <span class="w3-text w3-text-theme"> 1475 Zizhen Lin, Xiaoting Chen, Junyu Wang 1476 </span> 1477 </p> 1478 </a> 1479 <a class="w3-text" href="cheng24_interspeech.html"> 1480 <p> 1481 Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement 1482 <br> 1483 <span class="w3-text w3-text-theme"> 1484 Longbiao Cheng, Ashutosh Pandey, Buye Xu, Tobi Delbruck, Shih-Chii Liu 1485 </span> 1486 </p> 1487 </a> 1488 </div> 1489 </div> 1490 <br> 1491 <div class="w3-content" style="height:10px" id="Zero-shot TTS"></div> 1492 <div class="w3-card w3-round w3-white w3-padding"> 1493 <div class="w3-container" style="margin-top:40px"> 1494 <h4 class="w3-center">Zero-shot TTS</h4> 1495 <hr> 1496 <a class="w3-text" href="xue24c_interspeech.html"> 1497 <p> 1498 Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model 1499 <br> 1500 <span class="w3-text w3-text-theme"> 1501 Jinlong Xue, Yayue Deng, Yicheng Han, Yingming Gao, Ya Li 1502 </span> 1503 </p> 1504 </a> 1505 <a class="w3-text" href="wang24v_interspeech.html"> 1506 <p> 1507 An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS 1508 <br>
1509 <span class="w3-text w3-text-theme"> 1510 Xiaofei Wang, Sefik Emre Eskimez, Manthan Thakker, Hemin Yang, Zirun Zhu, Min Tang, Yufei Xia, Jinzhu Li, Sheng Zhao, Jinyu Li, Naoyuki Kanda 1511 </span> 1512 </p> 1513 </a> 1514 <a class="w3-text" href="fujita24b_interspeech.html"> 1515 <p> 1516 Lightweight Zero-shot Text-to-Speech with Mixture of Adapters 1517 <br> 1518 <span class="w3-text w3-text-theme"> 1519 Kenichi Fujita, Takanori Ashihara, Marc Delcroix, Yusuke Ijima 1520 </span> 1521 </p> 1522 </a> 1523 <a class="w3-text" href="pankov24_interspeech.html"> 1524 <p> 1525 DINO-VITS: Data-Efficient Zero-Shot TTS with Self-Supervised Speaker Verification Loss for Noise Robustness 1526 <br> 1527 <span class="w3-text w3-text-theme"> 1528 Vikentii Pankov, Valeria Pronina, Alexander Kuzmin, Maksim Borisov, Nikita Usoltsev, Xingshan Zeng, Alexander Golubkov, Nikolai Ermolenko, Aleksandra Shirshova, Yulia Matveeva 1529 </span> 1530 </p> 1531 </a> 1532 </div> 1533 </div> 1534 <br> 1535 <div class="w3-content" style="height:10px" id="Noise Robustness, Far-Field, and Multi-Talker ASR"></div> 1536 <div class="w3-card w3-round w3-white w3-padding"> 1537 <div class="w3-container" style="margin-top:40px"> 1538 <h4 class="w3-center">Noise Robustness, Far-Field, and Multi-Talker ASR</h4> 1539 <hr> 1540 <a class="w3-text" href="jin24_interspeech.html"> 1541 <p> 1542 LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization 1543 <br> 1544 <span class="w3-text w3-text-theme"> 1545 Zengrui Jin, Yifan Yang, Mohan Shi, Wei Kang, Xiaoyu Yang, Zengwei Yao, Fangjun Kuang, Liyong Guo, Lingwei Meng, Long Lin, Yong Xu, Shi-Xiong Zhang, Daniel Povey 1546 </span> 1547 </p> 1548 </a> 1549 <a class="w3-text" href="xing24_interspeech.html"> 1550 <p> 1551 A Joint Noise Disentanglement and Adversarial Training Framework for Robust Speaker Verification 1552 <br> 1553 <span class="w3-text w3-text-theme"> 1554 Xujiang Xing, Mingxing Xu, Thomas Fang Zheng 1555 </span> 1556 </p> 1557 </a> 1558 <a class="w3-text" href="shi24e_interspeech.html"> 1559 <p> 1560 Serialized Output Training by Learned Dominance 1561 <br> 1562 <span class="w3-text w3-text-theme"> 1563 Ying Shi, Lantian Li, Shi Yin, Dong Wang, Jiqing Han 1564 </span> 1565 </p> 1566 </a> 1567 <a class="w3-text" href="zheng24d_interspeech.html"> 1568 <p> 1569 SOT Triggered Neural Clustering for Speaker Attributed ASR 1570 <br>
1571 <span class="w3-text w3-text-theme"> 1572 Xianrui Zheng, Guangzhi Sun, Chao Zhang, Philip C. Woodland 1573 </span> 1574 </p> 1575 </a> 1576 <a class="w3-text" href="bando24_interspeech.html"> 1577 <p> 1578 Neural Blind Source Separation and Diarization for Distant Speech Recognition 1579 <br> 1580 <span class="w3-text w3-text-theme"> 1581 Yoshiaki Bando, Tomohiko Nakamura, Shinji Watanabe 1582 </span> 1583 </p> 1584 </a> 1585 <a class="w3-text" href="masumura24_interspeech.html"> 1586 <p> 1587 Unified Multi-Talker ASR with and without Target-speaker Enrollment 1588 <br> 1589 <span class="w3-text w3-text-theme"> 1590 Ryo Masumura, Naoki Makishima, Tomohiro Tanaka, Mana Ihori, Naotaka Kawata, Shota Orihashi, Kazutoshi Shinoda, Taiga Yamane, Saki Mizuno, Keita Suzuki, Satoshi Suzuki, Nobukatsu Hojo, Takafumi Moriya, Atsushi Ando 1591 </span> 1592 </p> 1593 </a> 1594 </div> 1595 </div> 1596 <br> 1597 <div class="w3-content" style="height:10px" id="Contextual Biasing and Adaptation"></div> 1598 <div class="w3-card w3-round w3-white w3-padding"> 1599 <div class="w3-container" style="margin-top:40px"> 1600 <h4 class="w3-center">Contextual Biasing and Adaptation</h4> 1601 <hr> 1602 <a class="w3-text" href="shamsian24_interspeech.html"> 1603 <p> 1604 Keyword-Guided Adaptation of Automatic Speech Recognition 1605 <br> 1606 <span class="w3-text w3-text-theme"> 1607 Aviv Shamsian, Aviv Navon, Neta Glazer, Gill Hetz, Joseph Keshet 1608 </span> 1609 </p> 1610 </a> 1611 <a class="w3-text" href="manhtienanh24_interspeech.html"> 1612 <p> 1613 Improving Speech Recognition with Prompt-based Contextualized ASR and LLM-based Re-predictor 1614 <br> 1615 <span class="w3-text w3-text-theme"> 1616 Nguyen Manh Tien Anh, Thach Ho Sy 1617 </span> 1618 </p> 1619 </a> 1620 <a class="w3-text" href="wang24q_interspeech.html"> 1621 <p> 1622 Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer 1623 <br> 1624 <span class="w3-text w3-text-theme"> 1625 Peng Wang, Yifan Yang, Zheng Liang, Tian Tan, Shiliang Zhang, Xie Chen 1626 </span> 1627 </p> 1628 </a> 1629 <a class="w3-text" href="yang24j_interspeech.html"> 1630 <p> 1631 Contextual Biasing with Confidence-based Homophone Detector for Mandarin End-to-End Speech Recognition 1632 <br> 1633 <span class="w3-text w3-text-theme"> 1634 Chengxu Yang, Lin Zheng, Sanli Tian, Gaofeng Cheng, Sujie Xiao, Ta Li 1635 </span> 1636 </p> 1637 </a> 1638 <a class="w3-text" href="huang24f_interspeech.html"> 1639 <p> 1640 Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation 1641 <br>
1642 <span class="w3-text w3-text-theme"> 1643 Ruizhe Huang, Mahsa Yarmohammadi, Sanjeev Khudanpur, Daniel Povey 1644 </span> 1645 </p> 1646 </a> 1647 <a class="w3-text" href="andrusenko24_interspeech.html"> 1648 <p> 1649 Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter 1650 <br> 1651 <span class="w3-text w3-text-theme"> 1652 Andrei Andrusenko, Aleksandr Laptev, Vladimir Bataev, Vitaly Lavrukhin, Boris Ginsburg 1653 </span> 1654 </p> 1655 </a> 1656 <a class="w3-text" href="wei24_interspeech.html"> 1657 <p> 1658 Prompt Tuning for Speech Recognition on Unknown Spoken Name Entities 1659 <br> 1660 <span class="w3-text w3-text-theme"> 1661 Xizi Wei, Stephen McGregor 1662 </span> 1663 </p> 1664 </a> 1665 <a class="w3-text" href="liu24e_interspeech.html"> 1666 <p> 1667 Improved Factorized Neural Transducer Model For Text-only Domain Adaptation 1668 <br> 1669 <span class="w3-text w3-text-theme"> 1670 Junzhe Liu, Jianwei Yu, Xie Chen 1671 </span> 1672 </p> 1673 </a> 1674 <a class="w3-text" href="liu24d_interspeech.html"> 1675 <p> 1676 Modality Translation Learning for Joint Speech-Text Model 1677 <br> 1678 <span class="w3-text w3-text-theme"> 1679 Pin-Yen Liu, Jen-Tzung Chien 1680 </span> 1681 </p> 1682 </a> 1683 <a class="w3-text" href="zhao24d_interspeech.html"> 1684 <p> 1685 SAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASR 1686 <br> 1687 <span class="w3-text w3-text-theme"> 1688 Qiuming Zhao, Guangzhi Sun, Chao Zhang, Mingxing Xu, Thomas Fang Zheng 1689 </span> 1690 </p> 1691 </a> 1692 <a class="w3-text" href="ando24_interspeech.html"> 1693 <p> 1694 Factor-Conditioned Speaking-Style Captioning 1695 <br> 1696 <span class="w3-text w3-text-theme"> 1697 Atsushi Ando, Takafumi Moriya, Shota Horiguchi, Ryo Masumura 1698 </span> 1699 </p> 1700 </a> 1701 <a class="w3-text" href="khassanov24_interspeech.html"> 1702 <p> 1703 Dual-Pipeline with Low-Rank Adaptation for New Language Integration in Multilingual ASR 1704 <br> 1705 <span class="w3-text w3-text-theme"> 1706 Yerbolat Khassanov, Zhipeng Chen, Tianfeng Chen, Tze Yuang Chong, Wei Li, Jun Zhang, Lu Lu, Yuxuan Wang 1707 </span> 1708 </p> 1709 </a> 1710 <a class="w3-text" href="yusuf24_interspeech.html"> 1711 <p> 1712 Speculative Speech Recognition by Audio-Prefixed Low-Rank Adaptation of Language Models 1713 <br>
1714 <span class="w3-text w3-text-theme"> 1715 Bolaji Yusuf, Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran 1716 </span> 1717 </p> 1718 </a> 1719 <a class="w3-text" href="kim24u_interspeech.html"> 1720 <p> 1721 Domain-Aware Data Selection for Speech Classification via Meta-Reweighting 1722 <br> 1723 <span class="w3-text w3-text-theme"> 1724 Junghun Kim, Ka Hyun Park, Hoyoung Yoon, U Kang 1725 </span> 1726 </p> 1727 </a> 1728 </div> 1729 </div> 1730 <br> 1731 <div class="w3-content" style="height:10px" id="Spoken Language Understanding"></div> 1732 <div class="w3-card w3-round w3-white w3-padding"> 1733 <div class="w3-container" style="margin-top:40px"> 1734 <h4 class="w3-center">Spoken Language Understanding</h4> 1735 <hr> 1736 <a class="w3-text" href="futami24_interspeech.html"> 1737 <p> 1738 Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model 1739 <br> 1740 <span class="w3-text w3-text-theme"> 1741 Hayato Futami, Siddhant Arora, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe 1742 </span> 1743 </p> 1744 </a> 1745 <a class="w3-text" href="porjazovski24_interspeech.html"> 1746 <p> 1747 Out-of-distribution generalisation in spoken language understanding 1748 <br> 1749 <span class="w3-text w3-text-theme"> 1750 Dejan Porjazovski, Anssi Moisio, Mikko Kurimo 1751 </span> 1752 </p> 1753 </a> 1754 <a class="w3-text" href="laperriere24_interspeech.html"> 1755 <p> 1756 A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding 1757 <br> 1758 <span class="w3-text w3-text-theme"> 1759 Gaëlle Laperrière, Sahar Ghannay, Bassam Jabaian, Yannick Estève 1760 </span> 1761 </p> 1762 </a> 1763 <a class="w3-text" href="lee24i_interspeech.html"> 1764 <p> 1765 Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond 1766 <br> 1767 <span class="w3-text w3-text-theme"> 1768 Beomseok Lee, Ioan Calapodescu, Marco Gaido, Matteo Negri, Laurent Besacier 1769 </span> 1770 </p> 1771 </a> 1772 <a class="w3-text" href="li24b_interspeech.html"> 1773 <p> 1774 Using Large Language Model for End-to-End Chinese ASR and NER 1775 <br> 1776 <span class="w3-text w3-text-theme"> 1777 Yuang Li, Jiawei Yu, Min Zhang, Mengxin Ren, Yanqing Zhao, Xiaofeng Zhao, Shimin Tao, Jinsong Su, Hao Yang 1778 </span> 1779 </p> 1780 </a> 1781 <a class="w3-text" href="koudounas24b_interspeech.html"> 1782 <p> 1783 A Contrastive Learning Approach to Mitigate Bias in Speech Models 1784 <br>
1785 <span class="w3-text w3-text-theme"> 1786 Alkis Koudounas, Flavio Giobergia, Eliana Pastor, Elena Baralis 1787 </span> 1788 </p> 1789 </a> 1790 </div> 1791 </div> 1792 <br> 1793 <div class="w3-content" style="height:10px" id="Spoken Machine Translation 1"></div> 1794 <div class="w3-card w3-round w3-white w3-padding"> 1795 <div class="w3-container" style="margin-top:40px"> 1796 <h4 class="w3-center">Spoken Machine Translation 1</h4> 1797 <hr> 1798 <a class="w3-text" href="huang24h_interspeech.html"> 1799 <p> 1800 Investigating Decoder-only Large Language Models for Speech-to-text Translation 1801 <br> 1802 <span class="w3-text w3-text-theme"> 1803 Chao-Wei Huang, Hui Lu, Hongyu Gong, Hirofumi Inaguma, Ilia Kulikov, Ruslan Mavlyutov, Sravya Popuri 1804 </span> 1805 </p> 1806 </a> 1807 <a class="w3-text" href="hirschkind24_interspeech.html"> 1808 <p> 1809 Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation 1810 <br> 1811 <span class="w3-text w3-text-theme"> 1812 Nameer Hirschkind, Xiao Yu, Mahesh Kumar Nandwana, Joseph Liu, Eloi DuBois, Dao Le, Nicolas Thiebaut, Colin Sinclair, Kyle Spence, Charles Shang, Zoe Abrams, Morgan McGuire 1813 </span> 1814 </p> 1815 </a> 1816 <a class="w3-text" href="chen24v_interspeech.html"> 1817 <p> 1818 Sign Value Constraint Decomposition for Efficient 1-Bit Quantization of Speech Translation Tasks 1819 <br> 1820 <span class="w3-text w3-text-theme"> 1821 Nan Chen, Yonghe Wang, Feilong Bao 1822 </span> 1823 </p> 1824 </a> 1825 <a class="w3-text" href="lee24h_interspeech.html"> 1826 <p> 1827 Lightweight Audio Segmentation for Long-form Speech Translation 1828 <br> 1829 <span class="w3-text w3-text-theme"> 1830 Jaesong Lee, Soyoon Kim, Hanbyul Kim, Joon Son Chung 1831 </span> 1832 </p> 1833 </a> 1834 <a class="w3-text" href="tan24b_interspeech.html"> 1835 <p> 1836 Contrastive Feedback Mechanism for Simultaneous Speech Translation 1837 <br> 1838 <span class="w3-text w3-text-theme"> 1839 Haotian Tan, Sakriani Sakti 1840 </span> 1841 </p> 1842 </a> 1843 <a class="w3-text" href="macaire24_interspeech.html"> 1844 <p> 1845 Towards Speech-to-Pictograms Translation 1846 <br> 1847 <span class="w3-text w3-text-theme"> 1848 Cécile Macaire, Chloé Dion, Didier Schwab, Benjamin Lecouteux, Emmanuelle Esperança-Rodier 1849 </span> 1850 </p> 1851 </a> 1852 </div> 1853 </div> 1854 <br> 1855 <div class="w3-content" style="height:10px" id="Hearing Disorders"></div> 1856 <div class="w3-card w3-round w3-white w3-padding"> 1857 <div class="w3-container" style="margin-top:40px"> 1858 <h4 class="w3-center">Hearing Disorders</h4> 1859 <hr> 1860 <a class="w3-text" href="lee24e_interspeech.html"> 1861 <p> 1862 Automatic Assessment of Speech Production Skills for Children with Cochlear Implants Using Wav2Vec2.0 Acoustic Embeddings 1863 <br>
1864 <span class="w3-text w3-text-theme"> 1865 Seonwoo Lee, Sunhee Kim, Minhwa Chung 1866 </span> 1867 </p> 1868 </a> 1869 <a class="w3-text" href="ahn24_interspeech.html"> 1870 <p> 1871 SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization 1872 <br> 1873 <span class="w3-text w3-text-theme"> 1874 Young Jin Ahn, Jungwoo Park, Sangha Park, Jonghyun Choi, Kee-Eung Kim 1875 </span> 1876 </p> 1877 </a> 1878 <a class="w3-text" href="huckvale24_interspeech.html"> 1879 <p> 1880 Evaluating a 3-factor listener model for prediction of speech intelligibility to hearing-impaired listeners 1881 <br> 1882 <span class="w3-text w3-text-theme"> 1883 Mark Huckvale, Gaston Hilkhuysen 1884 </span> 1885 </p> 1886 </a> 1887 <a class="w3-text" href="fagniart24_interspeech.html"> 1888 <p> 1889 Production of fricative consonants in French-speaking children with cochlear implants and typical hearing: acoustic and phonological analyses. 1890 <br> 1891 <span class="w3-text w3-text-theme"> 1892 Sophie Fagniart, Brigitte Charlier, Véronique Delvaux, Bernard Harmegnies, Anne Huberlant, Myriam Piccaluga, Kathy Huet 1893 </span> 1894 </p> 1895 </a> 1896 <a class="w3-text" href="irino24_interspeech.html"> 1897 <p> 1898 Signal processing algorithm effective for sound quality of hearing loss simulators 1899 <br> 1900 <span class="w3-text w3-text-theme"> 1901 Toshio Irino, Shintaro Doan, Minami Ishikawa 1902 </span> 1903 </p> 1904 </a> 1905 <a class="w3-text" href="niu24c_interspeech.html"> 1906 <p> 1907 Auditory Spatial Attention Detection Based on Feature Disentanglement and Brain Connectivity-Informed Graph Neural Networks 1908 <br> 1909 <span class="w3-text w3-text-theme"> 1910 Yixiang Niu, Ning Chen, Hongqing Zhu, Zhiying Zhu, Guangqiang Li, Yibo Chen 1911 </span> 1912 </p> 1913 </a> 1914 <a class="w3-text" href="monaghan24_interspeech.html"> 1915 <p> 1916 Automatic Detection of Hearing Loss from Children's Speech using wav2vec 2.0 Features 1917 <br> 1918 <span class="w3-text w3-text-theme"> 1919 Jessica Monaghan, Arun Sebastian, Nicky Chong-White, Vicky Zhang, Vijayalakshmi Easwar, Padraig Kitterick 1920 </span> 1921 </p> 1922 </a> 1923 </div> 1924 </div> 1925 <br> 1926 <div class="w3-content" style="height:10px" id="Speech Disorders 2"></div> 1927 <div class="w3-card w3-round w3-white w3-padding"> 1928 <div class="w3-container" style="margin-top:40px"> 1929 <h4 class="w3-center">Speech Disorders 2</h4> 1930 <hr> 1931 <a class="w3-text" href="changawala24_interspeech.html"> 1932 <p> 1933 Whister: Using Whisperâs representations for Stuttering detection 1934 <br>
1935 <span class="w3-text w3-text-theme"> 1936 Vrushank Changawala, Frank Rudzicz 1937 </span> 1938 </p> 1939 </a> 1940 <a class="w3-text" href="xiong24_interspeech.html"> 1941 <p> 1942 Improving Speech-Based Dysarthria Detection using Multi-task Learning with Gradient Projection 1943 <br> 1944 <span class="w3-text w3-text-theme"> 1945 Yan Xiong, Visar Berisha, Julie Liss, Chaitali Chakrabarti 1946 </span> 1947 </p> 1948 </a> 1949 <a class="w3-text" href="chen24i_interspeech.html"> 1950 <p> 1951 Cascaded Transfer Learning Strategy for Cross-Domain Alzheimer's Disease Recognition through Spontaneous Speech 1952 <br> 1953 <span class="w3-text w3-text-theme"> 1954 Guanlin Chen, Yun Jin 1955 </span> 1956 </p> 1957 </a> 1958 <a class="w3-text" href="ilias24_interspeech.html"> 1959 <p> 1960 A Cross-Attention Layer coupled with Multimodal Fusion Methods for Recognizing Depression from Spontaneous Speech 1961 <br> 1962 <span class="w3-text w3-text-theme"> 1963 Loukas Ilias, Dimitris Askounis 1964 </span> 1965 </p> 1966 </a> 1967 <a class="w3-text" href="ng24_interspeech.html"> 1968 <p> 1969 Segmental and Suprasegmental Speech Foundation Models for Classifying Cognitive Risk Factors: Evaluating Out-of-the-Box Performance 1970 <br> 1971 <span class="w3-text w3-text-theme"> 1972 Si-Ioi Ng, Lingfeng Xu, Kimberly D. Mueller, Julie Liss, Visar Berisha 1973 </span> 1974 </p> 1975 </a> 1976 <a class="w3-text" href="papadimitriou24_interspeech.html"> 1977 <p> 1978 Multimodal Continuous Fingerspelling Recognition via Visual Alignment Learning 1979 <br> 1980 <span class="w3-text w3-text-theme"> 1981 Katerina Papadimitriou, Gerasimos Potamianos 1982 </span> 1983 </p> 1984 </a> 1985 <a class="w3-text" href="ariasvergara24_interspeech.html"> 1986 <p> 1987 Contrastive Learning Approach for Assessment of Phonological Precision in Patients with Tongue Cancer Using MRI Data 1988 <br> 1989 <span class="w3-text w3-text-theme"> 1990 Tomas Arias-Vergara, Paula Andrea Pérez-Toro, Xiaofeng Liu, Fangxu Xing, Maureen Stone, Jiachen Zhuo, Jerry L. Prince, Maria Schuster, Elmar Noeth, Jonghye Woo, Andreas Maier 1991 </span> 1992 </p> 1993 </a> 1994 <a class="w3-text" href="zhang24l_interspeech.html"> 1995 <p> 1996 DysArinVox: DYSphonia & DYSarthria mandARIN speech corpus 1997 <br>
1998 <span class="w3-text w3-text-theme"> 1999 Haojie Zhang, Tao Zhang, Ganjun Liu, Dehui Fu, Xiaohui Hou, Ying Lv 2000 </span> 2001 </p> 2002 </a> 2003 <a class="w3-text" href="zhou24e_interspeech.html"> 2004 <p> 2005 YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection 2006 <br> 2007 <span class="w3-text w3-text-theme"> 2008 Xuanru Zhou, Anshul Kashyap, Steve Li, Ayati Sharma, Brittany Morin, David Baquirin, Jet Vonk, Zoe Ezzes, Zachary Miller, Maria Tempini, Jiachen Lian, Gopala Anumanchipalli 2009 </span> 2010 </p> 2011 </a> 2012 <a class="w3-text" href="gosztolya24c_interspeech.html"> 2013 <p> 2014 Automatic Longitudinal Investigation of Multiple Sclerosis Subjects 2015 <br> 2016 <span class="w3-text w3-text-theme"> 2017 Gábor Gosztolya, Veronika Svindt, Judit Bóna, Ildikó Hoffmann 2018 </span> 2019 </p> 2020 </a> 2021 </div> 2022 </div> 2023 <br> 2024 <div class="w3-content" style="height:10px" id="TAUKADIAL Challenge: Speech-Based Cognitive Assessment in Chinese and English (Special Session)"></div> 2025 <div class="w3-card w3-round w3-white w3-padding"> 2026 <div class="w3-container" style="margin-top:40px"> 2027 <h4 class="w3-center">TAUKADIAL Challenge: Speech-Based Cognitive Assessment in Chinese and English (Special Session)</h4> 2028 <hr> 2029 <a class="w3-text" href="luz24_interspeech.html"> 2030 <p> 2031 Connected Speech-Based Cognitive Assessment in Chinese and English 2032 <br> 2033 <span class="w3-text w3-text-theme"> 2034 Saturnino Luz, Sofia De La Fuente Garcia, Fasih Haider, Davida Fromm, Brian MacWhinney, Alyssa Lanzi, Ya-Ning Chang, Chia-Ju Chou, Yi-Chien Liu 2035 </span> 2036 </p> 2037 </a> 2038 <a class="w3-text" href="ortizperez24_interspeech.html"> 2039 <p> 2040 Cognitive Insights Across Languages: Enhancing Multimodal Interview Analysis 2041 <br> 2042 <span class="w3-text w3-text-theme"> 2043 David Ortiz-Perez, Jose Garcia-Rodriguez, David Tomás 2044 </span> 2045 </p> 2046 </a> 2047 <a class="w3-text" href="gosztolya24_interspeech.html"> 2048 <p> 2049 Combining Acoustic Feature Sets for Detecting Mild Cognitive Impairment in the Interspeech'24 TAUKADIAL Challenge 2050 <br> 2051 <span class="w3-text w3-text-theme"> 2052 Gábor Gosztolya, László Tóth 2053 </span> 2054 </p> 2055 </a> 2056 <a class="w3-text" href="duan24_interspeech.html"> 2057 <p> 2058 Pre-trained Feature Fusion and Matching for Mild Cognitive Impairment Detection 2059 <br>
2060 <span class="w3-text w3-text-theme"> 2061 Junwen Duan, Fangyuan Wei, Hong-Dong Li, Jin Liu 2062 </span> 2063 </p> 2064 </a> 2065 <a class="w3-text" href="barreraaltuna24_interspeech.html"> 2066 <p> 2067 The Interspeech 2024 TAUKADIAL Challenge: Multilingual Mild Cognitive Impairment Detection with Multimodal Approach 2068 <br> 2069 <span class="w3-text w3-text-theme"> 2070 Benjamin Barrera-Altuna, Daeun Lee, Zaima Zarnaz, Jinyoung Han, Seungbae Kim 2071 </span> 2072 </p> 2073 </a> 2074 <a class="w3-text" href="favaro24_interspeech.html"> 2075 <p> 2076 Leveraging Universal Speech Representations for Detecting and Assessing the Severity of Mild Cognitive Impairment Across Languages 2077 <br> 2078 <span class="w3-text w3-text-theme"> 2079 Anna Favaro, Tianyu Cao, Najim Dehak, Laureano Moro-Velazquez 2080 </span> 2081 </p> 2082 </a> 2083 <a class="w3-text" href="hoang24_interspeech.html"> 2084 <p> 2085 Translingual Language Markers for Cognitive Assessment from Spontaneous Speech 2086 <br> 2087 <span class="w3-text w3-text-theme"> 2088 Bao Hoang, Yijiang Pang, Hiroko Dodge, Jiayu Zhou 2089 </span> 2090 </p> 2091 </a> 2092 <a class="w3-text" href="pereztoro24_interspeech.html"> 2093 <p> 2094 Multilingual Speech and Language Analysis for the Assessment of Mild Cognitive Impairment: Outcomes from the Taukadial Challenge 2095 <br> 2096 <span class="w3-text w3-text-theme"> 2097 Paula Andrea Pérez-Toro, Tomas Arias-Vergara, Philipp Klumpp, Tobias Weise, Maria Schuster, Elmar Noeth, Juan Rafael Orozco-Arroyave, Andreas Maier 2098 </span> 2099 </p> 2100 </a> 2101 </div> 2102 </div> 2103 <br> 2104 <div class="w3-content" style="height:10px" id="Show and Tell 1"></div> 2105 <div class="w3-card w3-round w3-white w3-padding"> 2106 <div class="w3-container" style="margin-top:40px"> 2107 <h4 class="w3-center">Show and Tell 1</h4> 2108 <hr> 2109 <a class="w3-text" href="arai24_interspeech.html"> 2110 <p> 2111 Production of phrases by mechanical models of the human vocal tract 2112 <br> 2113 <span class="w3-text w3-text-theme"> 2114 Takayuki Arai, Ryohei Suzuki, Chandler Earp, Shinya Tsuji, Keiko Ochi 2115 </span> 2116 </p> 2117 </a> 2118 <a class="w3-text" href="gourav24_interspeech.html"> 2119 <p> 2120 Faster Vocoder: a multi threading approach to achieve low latency during TTS Inference 2121 <br> 2122 <span class="w3-text w3-text-theme"> 2123 Vishal Gourav, Ankit Tyagi, Phanindra Mankale 2124 </span> 2125 </p> 2126 </a> 2127 <a class="w3-text" href="mohan24_interspeech.html"> 2128 <p> 2129 A powerful and modern AAC composition tool for impaired speakers 2130 <br>
2131 <span class="w3-text w3-text-theme"> 2132 Aanchan Mohan, Monideep Chakraborti, Katelyn Eng, Nailia Kushaeva, Mirjana Prpa, Jordan Lewis, Tianyi Zhang, Vince Geisler, Carol Geisler 2133 </span> 2134 </p> 2135 </a> 2136 <a class="w3-text" href="mika24_interspeech.html"> 2137 <p> 2138 VoxFlow AI: wearable voice converter for atypical speech 2139 <br> 2140 <span class="w3-text w3-text-theme"> 2141 Grzegorz P. Mika, Konrad Zieli´nski, PaweÅ Cyrta, Marek Grzelec 2142 </span> 2143 </p> 2144 </a> 2145 <a class="w3-text" href="akarsh24_interspeech.html"> 2146 <p> 2147 Stress transfer in speech-to-speech machine translation 2148 <br> 2149 <span class="w3-text w3-text-theme"> 2150 Sai Akarsh, Vamshiraghusimha Narasinga, Anil Kumar Vuppala 2151 </span> 2152 </p> 2153 </a> 2154 <a class="w3-text" href="okamoto24b_interspeech.html"> 2155 <p> 2156 Mobile PresenTra: NICT fast neural text-to-speech system on smartphones with incremental inference of MS-FC-HiFi-GAN for law-latency synthesis 2157 <br> 2158 <span class="w3-text w3-text-theme"> 2159 Takuma Okamoto, Yamato Ohtani, Hisashi Kawai 2160 </span> 2161 </p> 2162 </a> 2163 <a class="w3-text" href="peirolilja24_interspeech.html"> 2164 <p> 2165 Multi-speaker and multi-dialectal Catalan TTS models for video gaming 2166 <br> 2167 <span class="w3-text w3-text-theme"> 2168 Alex Peiró-Lilja, José Giraldo, Martà Llopart-Font, Carme Armentano-Oller, Baybars Külebi, Mireia Farrús 2169 </span> 2170 </p> 2171 </a> 2172 <a class="w3-text" href="francis24_interspeech.html"> 2173 <p> 2174 ConnecTone: a modular AAC system prototype with contextual generative text prediction and style-adaptive conversational TTS 2175 <br> 2176 <span class="w3-text w3-text-theme"> 2177 Juliana Francis, Ãva Székely, Joakim Gustafson 2178 </span> 2179 </p> 2180 </a> 2181 <a class="w3-text" href="rohmatillah24_interspeech.html"> 2182 <p> 2183 Reliable dialogue system for facilitating student-counselor communication 2184 <br> 2185 <span class="w3-text w3-text-theme"> 2186 Mahdin Rohmatillah, Bryan Gautama Ngo, Willianto Sulaiman, Po-Chuan Chen, Jen-Tzung Chien 2187 </span> 2188 </p> 2189 </a> 2190 <a class="w3-text" href="lameris24_interspeech.html"> 2191 <p> 2192 CreakVC: a voice conversion tool for modulating creaky voice 2193 <br>
2194 <span class="w3-text w3-text-theme"> 2195 Harm Lameris, Joakim Gustafson, Ãva Székely 2196 </span> 2197 </p> 2198 </a> 2199 <a class="w3-text" href="tsao24_interspeech.html"> 2200 <p> 2201 EZTalking: English assessment platform for teachers and students 2202 <br> 2203 <span class="w3-text w3-text-theme"> 2204 Yu-Sheng Tsao, Yung-Chang Hsu, Jiun-Ting Li, Siang-Hong Weng, Tien-Hong Lo, Berlin Chen 2205 </span> 2206 </p> 2207 </a> 2208 </div> 2209 </div> 2210 <br> 2211 <div class="w3-content" style="height:10px" id="Keynote 2"></div> 2212 <div class="w3-card w3-round w3-white w3-padding"> 2213 <div class="w3-container" style="margin-top:40px"> 2214 <h4 class="w3-center">Keynote 2</h4> 2215 <hr> 2216 <a class="w3-text" href="araki24_interspeech.html"> 2217 <p> 2218 Frontier of Frontend for Conversational Speech Processing 2219 <br> 2220 <span class="w3-text w3-text-theme"> 2221 Shoko Araki 2222 </span> 2223 </p> 2224 </a> 2225 </div> 2226 </div> 2227 <br> 2228 <div class="w3-content" style="height:10px" id="Phonetics and Phonology of Second Language Acquisition"></div> 2229 <div class="w3-card w3-round w3-white w3-padding"> 2230 <div class="w3-container" style="margin-top:40px"> 2231 <h4 class="w3-center">Phonetics and Phonology of Second Language Acquisition</h4> 2232 <hr> 2233 <a class="w3-text" href="tuttosi24_interspeech.html"> 2234 <p> 2235 Mmm whatcha say? Uncovering distal and proximal context effects in first and second-language word perception using psychophysical reverse correlation 2236 <br> 2237 <span class="w3-text w3-text-theme"> 2238 Paige TuttösÃ, H. Henny Yeung, Yue Wang, Fenqi Wang, Guillaume Denis, Jean-Julien Aucouturier, Angelica Lim 2239 </span> 2240 </p> 2241 </a> 2242 <a class="w3-text" href="popescu24_interspeech.html"> 2243 <p> 2244 Automatic Speech Recognition with parallel L1 and L2 acoustic phone models to evaluate /l/ allophony in L2 English speech production 2245 <br> 2246 <span class="w3-text w3-text-theme"> 2247 Anisia Popescu, Lori Lamel, Ioana Vasilescu, Laurence Devillers 2248 </span> 2249 </p> 2250 </a> 2251 <a class="w3-text" href="huang24i_interspeech.html"> 2252 <p> 2253 Analysis of articulatory setting for L1 and L2 English speakers using MRI data 2254 <br> 2255 <span class="w3-text w3-text-theme"> 2256 Kevin Huang, Jack Goldberg, Louis Goldstein, Shrikanth Narayanan 2257 </span> 2258 </p> 2259 </a> 2260 <a class="w3-text" href="colgiu24_interspeech.html"> 2261 <p> 2262 Bilingual Rhotic Production Patterns: A Generational Comparison of Spanish-English Bilingual Speakers in Canada 2263 <br>
2264 <span class="w3-text w3-text-theme"> 2265 Ioana Colgiu, Laura Spinu, Rajiv Rao, Yasaman Rafat 2266 </span> 2267 </p> 2268 </a> 2269 <a class="w3-text" href="coulange24_interspeech.html"> 2270 <p> 2271 Exploring Impact of Pausing and Lexical Stress Patterns on L2 English Comprehensibility in Real Time 2272 <br> 2273 <span class="w3-text w3-text-theme"> 2274 Sylvain Coulange, Tsuneo Kato, Solange Rossato, Monica Masperi 2275 </span> 2276 </p> 2277 </a> 2278 <a class="w3-text" href="wu24m_interspeech.html"> 2279 <p> 2280 Mandarin T3 Production by Chinese and Japanese Native Speakers 2281 <br> 2282 <span class="w3-text w3-text-theme"> 2283 Qi Wu 2284 </span> 2285 </p> 2286 </a> 2287 </div> 2288 </div> 2289 <br> 2290 <div class="w3-content" style="height:10px" id="Corpora-based Approaches in Automatic Emotion Recognition"></div> 2291 <div class="w3-card w3-round w3-white w3-padding"> 2292 <div class="w3-container" style="margin-top:40px"> 2293 <h4 class="w3-center">Corpora-based Approaches in Automatic Emotion Recognition</h4> 2294 <hr> 2295 <a class="w3-text" href="ranjan24_interspeech.html"> 2296 <p> 2297 Reinforcement Learning based Data Augmentation for Noise Robust Speech Emotion Recognition 2298 <br> 2299 <span class="w3-text w3-text-theme"> 2300 Sumit Ranjan, Rupayan Chakraborty, Sunil Kumar Kopparapu 2301 </span> 2302 </p> 2303 </a> 2304 <a class="w3-text" href="mote24_interspeech.html"> 2305 <p> 2306 Unsupervised Domain Adaptation for Speech Emotion Recognition using K-Nearest Neighbors Voice Conversion 2307 <br> 2308 <span class="w3-text w3-text-theme"> 2309 Pravin Mote, Berrak Sisman, Carlos Busso 2310 </span> 2311 </p> 2312 </a> 2313 <a class="w3-text" href="wang24ja_interspeech.html"> 2314 <p> 2315 Confidence-aware Hypothesis Transfer Networks for Source-Free Cross-Corpus Speech Emotion Recognition 2316 <br> 2317 <span class="w3-text w3-text-theme"> 2318 Jincen Wang, Yan Zhao, Cheng Lu, Hailun Lian, Hongli Chang, Yuan Zong, Wenming Zheng 2319 </span> 2320 </p> 2321 </a> 2322 <a class="w3-text" href="xi24_interspeech.html"> 2323 <p> 2324 An Effective Local Prototypical Mapping Network for Speech Emotion Recognition 2325 <br> 2326 <span class="w3-text w3-text-theme"> 2327 Yuxuan Xi, Yan Song, Lirong Dai, Haoyu Song, Ian McLoughlin 2328 </span> 2329 </p> 2330 </a> 2331 <a class="w3-text" href="gao24f_interspeech.html"> 2332 <p> 2333 Speech Emotion Recognition with Multi-level Acoustic and
2333Semantic Information Extraction and Interaction 2334 <br> 2335 <span class="w3-text w3-text-theme"> 2336 Yuan Gao, Hao Shi, Chenhui Chu, Tatsuya Kawahara 2337 </span> 2338 </p> 2339 </a> 2340 </div> 2341 </div> 2342 <br> 2343 <div class="w3-content" style="height:10px" id="Analysis of Speakers States and Traits"></div> 2344 <div class="w3-card w3-round w3-white w3-padding"> 2345 <div class="w3-container" style="margin-top:40px"> 2346 <h4 class="w3-center">Analysis of Speakers States and Traits</h4> 2347 <hr> 2348 <a class="w3-text" href="niebuhr24_interspeech.html"> 2349 <p> 2350 How rhythm metrics are linked to produced and perceived speaker charisma 2351 <br> 2352 <span class="w3-text w3-text-theme"> 2353 Oliver Niebuhr, Nafiseh Taghva 2354 </span> 2355 </p> 2356 </a> 2357 <a class="w3-text" href="li24ma_interspeech.html"> 2358 <p> 2359 A Functional Trade-off between Prosodic and Semantic Cues in Conveying Sarcasm 2360 <br> 2361 <span class="w3-text w3-text-theme"> 2362 Zhu Li, Xiyuan Gao, Yuqing Zhang, Shekhar Nayak, Matt Coler 2363 </span> 2364 </p> 2365 </a> 2366 <a class="w3-text" href="murzaku24_interspeech.html"> 2367 <p> 2368 Multimodal Belief Prediction 2369 <br> 2370 <span class="w3-text w3-text-theme"> 2371 John Murzaku, Adil Soubki, Owen Rambow 2372 </span> 2373 </p> 2374 </a> 2375 <a class="w3-text" href="chen24f_interspeech.html"> 2376 <p> 2377 Detecting Empathy in Speech 2378 <br> 2379 <span class="w3-text w3-text-theme"> 2380 Run Chen, Haozhe Chen, Anushka Kulkarni, Eleanor Lin, Linda Pang, Divya Tadimeti, Jun Shin, Julia Hirschberg 2381 </span> 2382 </p> 2383 </a> 2384 <a class="w3-text" href="tao24b_interspeech.html"> 2385 <p> 2386 Learning Representation of Therapist Empathy in Counseling Conversation Using Siamese Hierarchical Attention Network 2387 <br> 2388 <span class="w3-text w3-text-theme"> 2389 Dehua Tao, Tan Lee, Harold Chui, Sarah Luk 2390 </span> 2391 </p> 2392 </a> 2393 <a class="w3-text" href="kunmei24_interspeech.html"> 2394 <p> 2395 Modelling Lexical Characteristics of the Healthy Aging Population: A Corpus-Based Study 2396 <br> 2397 <span class="w3-text w3-text-theme"> 2398 Han Kunmei 2399 </span> 2400 </p> 2401 </a> 2402 <a class="w3-text" href="gerczuk24_interspeech.html"> 2403 <p> 2404 Exploring Gender-Specific Speech Patterns in Automatic Suicide Risk Assessment 2405 <br>
2406 <span class="w3-text w3-text-theme"> 2407 Maurice Gerczuk, Shahin Amiriparian, Justina Lutz, Wolfgang Strube, Irina Papazova, Alkomiet Hasan, Björn W. Schuller 2408 </span> 2409 </p> 2410 </a> 2411 </div> 2412 </div> 2413 <br> 2414 <div class="w3-content" style="height:10px" id="Spoofing and Deepfake Detection"></div> 2415 <div class="w3-card w3-round w3-white w3-padding"> 2416 <div class="w3-container" style="margin-top:40px"> 2417 <h4 class="w3-center">Spoofing and Deepfake Detection</h4> 2418 <hr> 2419 <a class="w3-text" href="klein24_interspeech.html"> 2420 <p> 2421 Source Tracing of Audio Deepfake Systems 2422 <br> 2423 <span class="w3-text w3-text-theme"> 2424 Nicholas Klein, Tianxiang Chen, Hemlata Tak, Ricardo Casal, Elie Khoury 2425 </span> 2426 </p> 2427 </a> 2428 <a class="w3-text" href="liu24m_interspeech.html"> 2429 <p> 2430 How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio? 2431 <br> 2432 <span class="w3-text w3-text-theme"> 2433 Tianchi Liu, Lin Zhang, Rohan Kumar Das, Yi Ma, Ruijie Tao, Haizhou Li 2434 </span> 2435 </p> 2436 </a> 2437 <a class="w3-text" href="wang24l_interspeech.html"> 2438 <p> 2439 Revisiting and Improving Scoring Fusion for Spoofing-aware Speaker Verification Using Compositional Data Analysis 2440 <br> 2441 <span class="w3-text w3-text-theme"> 2442 Xin Wang, Tomi Kinnunen, Kong Aik Lee, Paul-Gauthier Noé, Junichi Yamagishi 2443 </span> 2444 </p> 2445 </a> 2446 <a class="w3-text" href="baser24_interspeech.html"> 2447 <p> 2448 SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures 2449 <br> 2450 <span class="w3-text w3-text-theme"> 2451 Oguzhan Baser, Kaan Kale, Sandeep P. Chinchali 2452 </span> 2453 </p> 2454 </a> 2455 <a class="w3-text" href="li24oa_interspeech.html"> 2456 <p> 2457 Interpretable Temporal Class Activation Representation for Audio Spoofing Detection 2458 <br> 2459 <span class="w3-text w3-text-theme"> 2460 Menglu Li, Xiao-Ping Zhang 2461 </span> 2462 </p> 2463 </a> 2464 <a class="w3-text" href="ge24_interspeech.html"> 2465 <p> 2466 DGPN: A Dual Graph Prototypical Network for Few-Shot Speech Spoofing Algorithm Recognition 2467 <br> 2468 <span class="w3-text w3-text-theme"> 2469 Zirui Ge, Xinzhou Xu, Haiyan Guo, Tingting Wang, Zhen Yang, Björn W. Schuller 2470 </span> 2471 </p> 2472 </a> 2473 </div> 2474 </div> 2475 <br> 2476 <div class="w3-content" style="height:10px" id="Audio Captioning, Tagging, and Audio-Text Retrieval"></div> 2477 <div class="w3-card w3-round w3-white w3-padding"> 2478 <div class="w3-container" style="margin-top:40px"> 2479 <h4 class="w3-center">Audio Captioning, Tagging, and Audio-Text Retrieval</h4> 2480 <hr> 2481 <a class="w3-text" href="sun24c_interspeech.html"> 2482 <p> 2483 PFCA-Net: Pyramid Feature Fusion and Cross Content Attention Network for Automated Audio Captioning 2484 <br>
2485 <span class="w3-text w3-text-theme"> 2486 Jianyuan Sun, Wenwu Wang, Mark D. Plumbley 2487 </span> 2488 </p> 2489 </a> 2490 <a class="w3-text" href="liu24_interspeech.html"> 2491 <p> 2492 Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding 2493 <br> 2494 <span class="w3-text w3-text-theme"> 2495 Jizhong Liu, Gang Li, Junbo Zhang, Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Yujun Wang, Bin Wang 2496 </span> 2497 </p> 2498 </a> 2499 <a class="w3-text" href="xin24b_interspeech.html"> 2500 <p> 2501 Audio-text Retrieval with Transformer-based Hierarchical Alignment and Disentangled Cross-modal Representation 2502 <br> 2503 <span class="w3-text w3-text-theme"> 2504 Yifei Xin, Zhihong Zhu, Xuxin Cheng, Xusheng Yang, Yuexian Zou 2505 </span> 2506 </p> 2507 </a> 2508 <a class="w3-text" href="dinkel24_interspeech.html"> 2509 <p> 2510 Streaming Audio Transformers for Online Audio Tagging 2511 <br> 2512 <span class="w3-text w3-text-theme"> 2513 Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang, Bin Wang 2514 </span> 2515 </p> 2516 </a> 2517 <a class="w3-text" href="chaudhary24_interspeech.html"> 2518 <p> 2519 Efficient CNNs with Quaternion Transformations and Pruning for Audio Tagging 2520 <br> 2521 <span class="w3-text w3-text-theme"> 2522 Aryan Chaudhary, Arshdeep Singh, Vinayak Abrol, Mark D. Plumbley 2523 </span> 2524 </p> 2525 </a> 2526 <a class="w3-text" href="jing24b_interspeech.html"> 2527 <p> 2528 ParaCLAP â Towards a general language-audio model for computational paralinguistic tasks 2529 <br> 2530 <span class="w3-text w3-text-theme"> 2531 Xin Jing, Andreas Triantafyllopoulos, Björn Schuller 2532 </span> 2533 </p> 2534 </a> 2535 <a class="w3-text" href="xu24e_interspeech.html"> 2536 <p> 2537 Efficient Audio Captioning with Encoder-Level Knowledge Distillation 2538 <br> 2539 <span class="w3-text w3-text-theme"> 2540 Xuenan Xu, Haohe Liu, Mengyue Wu, Wenwu Wang, Mark D. Plumbley 2541 </span> 2542 </p> 2543 </a> 2544 </div> 2545 </div> 2546 <br> 2547 <div class="w3-content" style="height:10px" id="Generative Speech Enhancement"></div> 2548 <div class="w3-card w3-round w3-white w3-padding"> 2549 <div class="w3-container" style="margin-top:40px"> 2550 <h4 class="w3-center">Generative Speech Enhancement</h4> 2551 <hr> 2552 <a class="w3-text" href="scheibler24_interspeech.html"> 2553 <p> 2554 Universal Score-based Speech Enhancement with High Content Preservation 2555 <br>
2556 <span class="w3-text w3-text-theme"> 2557 Robin Scheibler, Yusuke Fujita, Yuma Shirahata, Tatsuya Komatsu 2558 </span> 2559 </p> 2560 </a> 2561 <a class="w3-text" href="yang24h_interspeech.html"> 2562 <p> 2563 Genhancer: High-Fidelity Speech Enhancement via Generative Modeling on Discrete Codec Tokens 2564 <br> 2565 <span class="w3-text w3-text-theme"> 2566 Haici Yang, Jiaqi Su, Minje Kim, Zeyu Jin 2567 </span> 2568 </p> 2569 </a> 2570 <a class="w3-text" href="jukic24_interspeech.html"> 2571 <p> 2572 Schrödinger Bridge for Generative Speech Enhancement 2573 <br> 2574 <span class="w3-text w3-text-theme"> 2575 Ante JukiÄ, Roman Korostik, Jagadeesh Balam, Boris Ginsburg 2576 </span> 2577 </p> 2578 </a> 2579 <a class="w3-text" href="trachu24_interspeech.html"> 2580 <p> 2581 Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridge 2582 <br> 2583 <span class="w3-text w3-text-theme"> 2584 Thanapat Trachu, Chawan Piansaddhayanon, Ekapol Chuangsuwanich 2585 </span> 2586 </p> 2587 </a> 2588 <a class="w3-text" href="yang24k_interspeech.html"> 2589 <p> 2590 Pre-training Feature Guided Diffusion Model for Speech Enhancement 2591 <br> 2592 <span class="w3-text w3-text-theme"> 2593 Yiyuan Yang, Niki Trigoni, Andrew Markham 2594 </span> 2595 </p> 2596 </a> 2597 <a class="w3-text" href="kim24o_interspeech.html"> 2598 <p> 2599 Guided conditioning with predictive network on score-based diffusion model for speech enhancement 2600 <br> 2601 <span class="w3-text w3-text-theme"> 2602 Dail Kim, Da-Hee Yang, Donghyun Kim, Joon-Hyuk Chang, Jeonghwan Choi, Moa Lee, Jaemo Yang, Han-gil Moon 2603 </span> 2604 </p> 2605 </a> 2606 </div> 2607 </div> 2608 <br> 2609 <div class="w3-content" style="height:10px" id="Speech Synthesis: Evaluation"></div> 2610 <div class="w3-card w3-round w3-white w3-padding"> 2611 <div class="w3-container" style="margin-top:40px"> 2612 <h4 class="w3-center">Speech Synthesis: Evaluation</h4> 2613 <hr> 2614 <a class="w3-text" href="yin24b_interspeech.html"> 2615 <p> 2616 SVSNet+: Enhancing Speaker Voice Similarity Assessment Models with Representations from Speech Foundation Models 2617 <br> 2618 <span class="w3-text w3-text-theme"> 2619 Chun Yin, Tai-Shih Chi, Yu Tsao, Hsin-Min Wang 2620 </span> 2621 </p> 2622 </a> 2623 <a class="w3-text" href="anand24_interspeech.html"> 2624 <p> 2625 Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies 2626 <br>
2627 <span class="w3-text w3-text-theme"> 2628 Srija Anand, Praveen Srinivasa Varadhan, Ashwin Sankar, Giri Raju, Mitesh M. Khapra 2629 </span> 2630 </p> 2631 </a> 2632 <a class="w3-text" href="edlund24_interspeech.html"> 2633 <p> 2634 Assessing the impact of contextual framing on subjective TTS quality 2635 <br> 2636 <span class="w3-text w3-text-theme"> 2637 Jens Edlund, Christina TÃ¥nnander, Sébastien Le Maguer, Petra Wagner 2638 </span> 2639 </p> 2640 </a> 2641 <a class="w3-text" href="adigwe24_interspeech.html"> 2642 <p> 2643 What do people hear? Listenersâ Perception of Conversational Speech 2644 <br> 2645 <span class="w3-text w3-text-theme"> 2646 Adaeze Adigwe, Sarenne Wallbridge, Simon King 2647 </span> 2648 </p> 2649 </a> 2650 <a class="w3-text" href="wang24s_interspeech.html"> 2651 <p> 2652 Uncertainty-Aware Mean Opinion Score Prediction 2653 <br> 2654 <span class="w3-text w3-text-theme"> 2655 Hui Wang, Shiwan Zhao, Jiaming Zhou, Xiguang Zheng, Haoqin Sun, Xuechen Wang, Yong Qin 2656 </span> 2657 </p> 2658 </a> 2659 <a class="w3-text" href="saget24_interspeech.html"> 2660 <p> 2661 Lifelong Learning MOS Prediction for Synthetic Speech Quality Evaluation 2662 <br> 2663 <span class="w3-text w3-text-theme"> 2664 Félix Saget, Meysam Shamsi, Marie Tahon 2665 </span> 2666 </p> 2667 </a> 2668 </div> 2669 </div> 2670 <br> 2671 <div class="w3-content" style="height:10px" id="Multilingual ASR"></div> 2672 <div class="w3-card w3-round w3-white w3-padding"> 2673 <div class="w3-container" style="margin-top:40px"> 2674 <h4 class="w3-center">Multilingual ASR</h4> 2675 <hr> 2676 <a class="w3-text" href="kwok24_interspeech.html"> 2677 <p> 2678 Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems 2679 <br> 2680 <span class="w3-text w3-text-theme"> 2681 Chin Yuen Kwok, Jia Qi Yip, Eng Siong Chng 2682 </span> 2683 </p> 2684 </a> 2685 <a class="w3-text" href="shi24g_interspeech.html"> 2686 <p> 2687 ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets 2688 <br> 2689 <span class="w3-text w3-text-theme"> 2690 Jiatong Shi, Shih-Heng Wang, William Chen, Martijn Bartelds, Vanya Bannihatti Kumar, Jinchuan Tian, Xuankai Chang, Dan Jurafsky, Karen Livescu, Hung-yi Lee, Shinji Watanabe 2691 </span> 2692 </p> 2693 </a> 2694 <a class="w3-text" href="pineiromartin24_interspeech.html"> 2695 <p> 2696 Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition 2697 <br>
2698 <span class="w3-text w3-text-theme"> 2699 Andrés Piñeiro-MartÃn, Carmen GarcÃa-Mateo, Laura Docio-Fernandez, MarÃa del Carmen López-Pérez, Georg Rehm 2700 </span> 2701 </p> 2702 </a> 2703 <a class="w3-text" href="saif24_interspeech.html"> 2704 <p> 2705 M2ASR: Multilingual Multi-task Automatic Speech Recognition via Multi-objective Optimization 2706 <br> 2707 <span class="w3-text w3-text-theme"> 2708 A F M Saif, Lisha Chen, Xiaodong Cui, Songtao Lu, Brian Kingsbury, Tianyi Chen 2709 </span> 2710 </p> 2711 </a> 2712 <a class="w3-text" href="li24s_interspeech.html"> 2713 <p> 2714 MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research 2715 <br> 2716 <span class="w3-text w3-text-theme"> 2717 Song Li, Yongbin You, Xuezhi Wang, Zhengkun Tian, Ke Ding, Guanglu Wan 2718 </span> 2719 </p> 2720 </a> 2721 <a class="w3-text" href="houston24_interspeech.html"> 2722 <p> 2723 Improving Multilingual ASR Robustness to Errors in Language Input 2724 <br> 2725 <span class="w3-text w3-text-theme"> 2726 Brady Houston, Omid Sadjadi, Zejiang Hou, Srikanth Vishnubhotla, Kyu J. Han 2727 </span> 2728 </p> 2729 </a> 2730 </div> 2731 </div> 2732 <br> 2733 <div class="w3-content" style="height:10px" id="General Topics in ASR"></div> 2734 <div class="w3-card w3-round w3-white w3-padding"> 2735 <div class="w3-container" style="margin-top:40px"> 2736 <h4 class="w3-center">General Topics in ASR</h4> 2737 <hr> 2738 <a class="w3-text" href="suh24_interspeech.html"> 2739 <p> 2740 Improving Domain-Specific ASR with LLM-Generated Contextual Descriptions 2741 <br> 2742 <span class="w3-text w3-text-theme"> 2743 Jiwon Suh, Injae Na, Woohwan Jung 2744 </span> 2745 </p> 2746 </a> 2747 <a class="w3-text" href="li24c_interspeech.html"> 2748 <p> 2749 A Multitask Training Approach to Enhance Whisper with Open-Vocabulary Keyword Spotting 2750 <br> 2751 <span class="w3-text w3-text-theme"> 2752 Yuang Li, Min Zhang, Chang Su, Yinglu Li, Xiaosong Qiao, Mengxin Ren, Miaomiao Ma, Daimeng Wei, Shimin Tao, Hao Yang 2753 </span> 2754 </p> 2755 </a> 2756 <a class="w3-text" href="zusag24_interspeech.html"> 2757 <p> 2758 CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions 2759 <br> 2760 <span class="w3-text w3-text-theme"> 2761 Mario Zusag, Laurin Wagner, Bernhad Thallinger 2762 </span> 2763 </p> 2764 </a> 2765 <a class="w3-text" href="mihajlik24_interspeech.html"> 2766 <p> 2767 On Disfluency and Non-lexical Sound Labeling for End-to-end Automatic Speech Recognition 2768 <br>
2769 <span class="w3-text w3-text-theme"> 2770 Peter Mihajlik, Yan Meng, Mate S Kadar, Julian Linke, Barbara Schuppler, Katalin Mády 2771 </span> 2772 </p> 2773 </a> 2774 <a class="w3-text" href="mujtaba24_interspeech.html"> 2775 <p> 2776 Inclusive ASR for Disfluent Speech: Cascaded Large-Scale Self-Supervised Learning with Targeted Fine-Tuning and Data Augmentation 2777 <br> 2778 <span class="w3-text w3-text-theme"> 2779 Dena Mujtaba, Nihar R. Mahapatra, Megan Arney, J. Scott Yaruss, Caryn Herring, Jia Bin 2780 </span> 2781 </p> 2782 </a> 2783 <a class="w3-text" href="tan24_interspeech.html"> 2784 <p> 2785 DualPure: An Efficient Adversarial Purification Method for Speech Command Recognition 2786 <br> 2787 <span class="w3-text w3-text-theme"> 2788 Hao Tan, Xiaochen Liu, Huan Zhang, Junjian Zhang, Yaguan Qian, Zhaoquan Gu 2789 </span> 2790 </p> 2791 </a> 2792 <a class="w3-text" href="lehecka24_interspeech.html"> 2793 <p> 2794 A Comparative Analysis of Bilingual and Trilingual Wav2Vec Models for Automatic Speech Recognition in Multilingual Oral History Archives 2795 <br> 2796 <span class="w3-text w3-text-theme"> 2797 Jan LeheÄka, Josef V. Psutka, Lubos Smidl, Pavel Ircing, Josef Psutka 2798 </span> 2799 </p> 2800 </a> 2801 <a class="w3-text" href="delafuente24_interspeech.html"> 2802 <p> 2803 A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models 2804 <br> 2805 <span class="w3-text w3-text-theme"> 2806 Anton de la Fuente, Dan Jurafsky 2807 </span> 2808 </p> 2809 </a> 2810 <a class="w3-text" href="leivaditi24_interspeech.html"> 2811 <p> 2812 Fine-Tuning Strategies for Dutch Dysarthric Speech Recognition: Evaluating the Impact of Healthy, Disease-Specific, and Speaker-Specific Data 2813 <br> 2814 <span class="w3-text w3-text-theme"> 2815 Spyretta Leivaditi, Tatsunari Matsushima, Matt Coler, Shekhar Nayak, Vass Verkhodanova 2816 </span> 2817 </p> 2818 </a> 2819 <a class="w3-text" href="hsieh24_interspeech.html"> 2820 <p> 2821 Dysarthric Speech Recognition Using Curriculum Learning and Articulatory Feature Embedding 2822 <br> 2823 <span class="w3-text w3-text-theme"> 2824 I-Ting Hsieh, Chung-Hsien Wu 2825 </span> 2826 </p> 2827 </a> 2828 <a class="w3-text" href="wang24x_interspeech.html"> 2829 <p> 2830 Enhancing Dysarthric Speech Recognition for Unseen Speakers via Prototype-Based Adaptation 2831 <br>
2832 <span class="w3-text w3-text-theme"> 2833 Shiyao Wang, Shiwan Zhao, Jiaming Zhou, Aobo Kong, Yong Qin 2834 </span> 2835 </p> 2836 </a> 2837 <a class="w3-text" href="zheng24_interspeech.html"> 2838 <p> 2839 An efficient text augmentation approach for contextualized Mandarin speech recognition 2840 <br> 2841 <span class="w3-text w3-text-theme"> 2842 Naijun Zheng, Xucheng Wan, Kai Liu, Ziqing Du, Zhou Huan 2843 </span> 2844 </p> 2845 </a> 2846 <a class="w3-text" href="li24h_interspeech.html"> 2847 <p> 2848 Investigating ASR Error Correction with Large Language Model and Multilingual 1-best Hypotheses 2849 <br> 2850 <span class="w3-text w3-text-theme"> 2851 Sheng Li, Chen Chen, Chin Yuen Kwok, Chenhui Chu, Eng Siong Chng, Hisashi Kawai 2852 </span> 2853 </p> 2854 </a> 2855 <a class="w3-text" href="wang24n_interspeech.html"> 2856 <p> 2857 Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping 2858 <br> 2859 <span class="w3-text w3-text-theme"> 2860 Lun Wang, Om Thakkar, Zhong Meng, Nicole Rafidi, Rohit Prabhavalkar, Arun Narayanan 2861 </span> 2862 </p> 2863 </a> 2864 </div> 2865 </div> 2866 <br> 2867 <div class="w3-content" style="height:10px" id="Spoken Language Understanding"></div> 2868 <div class="w3-card w3-round w3-white w3-padding"> 2869 <div class="w3-container" style="margin-top:40px"> 2870 <h4 class="w3-center">Spoken Language Understanding</h4> 2871 <hr> 2872 <a class="w3-text" href="phung24_interspeech.html"> 2873 <p> 2874 AR-NLU: A Framework for Enhancing Natural Language Understanding Model Robustness against ASR Errors 2875 <br> 2876 <span class="w3-text w3-text-theme"> 2877 Emmy Phung, Harsh Deshpande, Ahmad Emami, Kanishk Singh 2878 </span> 2879 </p> 2880 </a> 2881 <a class="w3-text" href="li24_interspeech.html"> 2882 <p> 2883 Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language Understanding 2884 <br> 2885 <span class="w3-text w3-text-theme"> 2886 Mohan Li, Simon Keizer, Rama Doddipatla 2887 </span> 2888 </p> 2889 </a> 2890 <a class="w3-text" href="tran24b_interspeech.html"> 2891 <p> 2892 VN-SLU: A Vietnamese Spoken Language Understanding Dataset 2893 <br> 2894 <span class="w3-text w3-text-theme"> 2895 Tuyen Tran, Khanh Le, Ngoc Dang Nguyen, Minh Vu, Huyen Ngo, Woomyoung Park, Thi Thu Trang Nguyen 2896 </span> 2897 </p> 2898 </a> 2899 <a class="w3-text" href="kando24_interspeech.html"> 2900 <p>
2901 Textless Dependency Parsing by Labeled Sequence Prediction 2902 <br> 2903 <span class="w3-text w3-text-theme"> 2904 Shunsuke Kando, Yusuke Miyao, Jason Naradowsky, Shinnosuke Takamichi 2905 </span> 2906 </p> 2907 </a> 2908 <a class="w3-text" href="yue24_interspeech.html"> 2909 <p> 2910 Towards Speech Classification from Acoustic and Vocal Tract data in Real-time MRI 2911 <br> 2912 <span class="w3-text w3-text-theme"> 2913 Yaoyao Yue, Michael Proctor, Luping Zhou, Rijul Gupta, Tharinda Piyadasa, Amelia Gully, Kirrie Ballard, Craig Jin 2914 </span> 2915 </p> 2916 </a> 2917 <a class="w3-text" href="johnson24_interspeech.html"> 2918 <p> 2919 Efficient SQA from Long Audio Contexts: A Policy-driven Approach 2920 <br> 2921 <span class="w3-text w3-text-theme"> 2922 Alexander Johnson, Peter Plantinga, Pheobe Sun, Swaroop Gadiyaram, Abenezer Girma, Ahmad Emami 2923 </span> 2924 </p> 2925 </a> 2926 </div> 2927 </div> 2928 <br> 2929 <div class="w3-content" style="height:10px" id="Speech and Multimodal Resources"></div> 2930 <div class="w3-card w3-round w3-white w3-padding"> 2931 <div class="w3-container" style="margin-top:40px"> 2932 <h4 class="w3-center">Speech and Multimodal Resources</h4> 2933 <hr> 2934 <a class="w3-text" href="pesan24_interspeech.html"> 2935 <p> 2936 BESST Dataset: A Multimodal Resource for Speech-based Stress Detection and Analysis 2937 <br> 2938 <span class="w3-text w3-text-theme"> 2939 Jan Pešán, VojtÄch JuÅÃk, Martin Karafiát, Jan Äernocký 2940 </span> 2941 </p> 2942 </a> 2943 <a class="w3-text" href="turetzky24_interspeech.html"> 2944 <p> 2945 HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing 2946 <br> 2947 <span class="w3-text w3-text-theme"> 2948 Arnon Turetzky, Or Tal, Yael Segal, Yehoshua Dissen, Ella Zeldes, Amit Roth, Eyal Cohen, Yosi Shrem, Bronya R. Chernyak, Olga Seleznova, Joseph Keshet, Yossi Adi 2949 </span> 2950 </p> 2951 </a> 2952 <a class="w3-text" href="wang24b_interspeech.html"> 2953 <p> 2954 GLOBE: A High-quality English Corpus with Global Accents for Zero-shot Speaker Adaptive Text-to-Speech 2955 <br> 2956 <span class="w3-text w3-text-theme"> 2957 Wenbin Wang, Yang Song, Sanjay Jha 2958 </span> 2959 </p> 2960 </a> 2961 <a class="w3-text" href="kong24_interspeech.html"> 2962 <p> 2963 STraDa: A Singer Traits Dataset 2964 <br>
2965 <span class="w3-text w3-text-theme"> 2966 Yuexuan Kong, Viet-Anh Tran, Romain Hennequin 2967 </span> 2968 </p> 2969 </a> 2970 <a class="w3-text" href="anderer24_interspeech.html"> 2971 <p> 2972 MaViLS, a Benchmark Dataset for Video-to-Slide Alignment, Assessing Baseline Accuracy with a Multimodal Alignment Algorithm Leveraging Speech, OCR, and Visual Features 2973 <br> 2974 <span class="w3-text w3-text-theme"> 2975 Katharina Anderer, Andreas Reich, Matthias Wölfel 2976 </span> 2977 </p> 2978 </a> 2979 <a class="w3-text" href="sungbin24_interspeech.html"> 2980 <p> 2981 MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset 2982 <br> 2983 <span class="w3-text w3-text-theme"> 2984 Kim Sung-Bin, Lee Chae-Yeon, Gihun Son, Oh Hyun-Bin, Janghoon Ju, Suekyeong Nam, Tae-Hyun Oh 2985 </span> 2986 </p> 2987 </a> 2988 <a class="w3-text" href="veliche24_interspeech.html"> 2989 <p> 2990 Towards measuring fairness in speech recognition: Fair-Speech dataset 2991 <br> 2992 <span class="w3-text w3-text-theme"> 2993 Irina-Elena Veliche, Zhuangqun Huang, Vineeth Ayyat Kochaniyan, Fuchun Peng, Ozlem Kalinli, Michael L. Seltzer 2994 </span> 2995 </p> 2996 </a> 2997 <a class="w3-text" href="lu24f_interspeech.html"> 2998 <p> 2999 Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio 3000 <br> 3001 <span class="w3-text w3-text-theme"> 3002 Yi Lu, Yuankun Xie, Ruibo Fu, Zhengqi Wen, Jianhua Tao, Zhiyong Wang, Xin Qi, Xuefei Liu, Yongwei Li, Yukun Liu, Xiaopeng Wang, Shuchen Shi 3003 </span> 3004 </p> 3005 </a> 3006 <a class="w3-text" href="osman24_interspeech.html"> 3007 <p> 3008 SER Evals: In-domain and Out-of-domain benchmarking for speech emotion recognition 3009 <br> 3010 <span class="w3-text w3-text-theme"> 3011 Mohamed Osman, Daniel Z. Kaplan, Tamer Nadeem 3012 </span> 3013 </p> 3014 </a> 3015 </div> 3016 </div> 3017 <br> 3018 <div class="w3-content" style="height:10px" id="Pathological Speech Analysis 1"></div> 3019 <div class="w3-card w3-round w3-white w3-padding"> 3020 <div class="w3-container" style="margin-top:40px"> 3021 <h4 class="w3-center">Pathological Speech Analysis 1</h4> 3022 <hr> 3023 <a class="w3-text" href="gudmundsson24_interspeech.html"> 3024 <p> 3025 The MARRYS helmet: A new device for researching and training âjaw dancingâ 3026 <br> 3027 <span class="w3-text w3-text-theme"> 3028 Vidar Freyr Gudmundsson, Keve Márton Gönczi, Malin Svensson Lundmark, Donna Erickson, Oliver Niebuhr 3029 </span> 3030 </p> 3031 </a> 3032 <a class="w3-text" href="laquatra24_interspeech.html"> 3033 <p> 3034 Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions 3035 <br>
3036 <span class="w3-text w3-text-theme"> 3037 Moreno La Quatra, Maria Francesca Turco, Torbjørn Svendsen, Giampiero Salvi, Juan Rafael Orozco-Arroyave, Sabato Marco Siniscalchi 3038 </span> 3039 </p> 3040 </a> 3041 <a class="w3-text" href="triantafyllopoulos24_interspeech.html"> 3042 <p> 3043 Sustained Vowels for Pre- vs Post-Treatment COPD Classification 3044 <br> 3045 <span class="w3-text w3-text-theme"> 3046 Andreas Triantafyllopoulos, Anton Batliner, Wolfgang Mayr, Markus Fendler, Florian Pokorny, Maurice Gerczuk, Shahin Amiriparian, Thomas Berghaus, Björn Schuller 3047 </span> 3048 </p> 3049 </a> 3050 <a class="w3-text" href="amiri24_interspeech.html"> 3051 <p> 3052 Adversarial Robustness Analysis in Automatic Pathological Speech Detection Approaches 3053 <br> 3054 <span class="w3-text w3-text-theme"> 3055 Mahdi Amiri, Ina Kodrasi 3056 </span> 3057 </p> 3058 </a> 3059 <a class="w3-text" href="kim24q_interspeech.html"> 3060 <p> 3061 Automatic Children Speech Sound Disorder Detection with Age and Speaker Bias Mitigation 3062 <br> 3063 <span class="w3-text w3-text-theme"> 3064 Gahye Kim, Yunjung Eom, Selina S. Sung, Seunghee Ha, Tae-Jin Yoon, Jungmin So 3065 </span> 3066 </p> 3067 </a> 3068 </div> 3069 </div> 3070 <br> 3071 <div class="w3-content" style="height:10px" id="Speech and Language in Health: from Remote Monitoring to Medical Conversations - 1 (Special Session)"></div> 3072 <div class="w3-card w3-round w3-white w3-padding"> 3073 <div class="w3-container" style="margin-top:40px"> 3074 <h4 class="w3-center">Speech and Language in Health: from Remote Monitoring to Medical Conversations - 1 (Special Session)</h4> 3075 <hr> 3076 <a class="w3-text" href="kadkhodaieelyaderani24_interspeech.html"> 3077 <p> 3078 Reference-Free Estimation of the Quality of Clinical Notes Generated from Doctor-Patient Conversations 3079 <br> 3080 <span class="w3-text w3-text-theme"> 3081 Mojtaba Kadkhodaie Elyaderani, John Glover, Thomas Schaaf 3082 </span> 3083 </p> 3084 </a> 3085 <a class="w3-text" href="mun24_interspeech.html"> 3086 <p> 3087 Developing an End-to-End Framework for Predicting the Social Communication Severity Scores of Children with Autism Spectrum Disorder 3088 <br> 3089 <span class="w3-text w3-text-theme"> 3090 Jihyun Mun, Sunhee Kim, Minhwa Chung 3091 </span> 3092 </p> 3093 </a> 3094 <a class="w3-text" href="despotovic24_interspeech.html"> 3095 <p> 3096 Multimodal Fusion for Vocal Biomarkers Using Vector Cross-Attention 3097 <br>
3098 <span class="w3-text w3-text-theme"> 3099 Vladimir Despotovic, Abir Elbéji, Petr V. Nazarov, Guy Fagherazzi 3100 </span> 3101 </p> 3102 </a> 3103 <a class="w3-text" href="goria24_interspeech.html"> 3104 <p> 3105 Revealing Confounding Biases: A Novel Benchmarking Approach for Aggregate-Level Performance Metrics in Health Assessments 3106 <br> 3107 <span class="w3-text w3-text-theme"> 3108 Stefano Goria, Roseline Polle, Salvatore Fara, Nicholas Cummins 3109 </span> 3110 </p> 3111 </a> 3112 <a class="w3-text" href="rameau24_interspeech.html"> 3113 <p> 3114 Developing Multi-Disorder Voice Protocols: A team science approach involving clinical expertise, bioethics, standards, and DEI. 3115 <br> 3116 <span class="w3-text w3-text-theme"> 3117 Anaïs Rameau, Satrajit Ghosh, Alexandros Sigaras, Olivier Elemento, Jean-Christophe Belisle-Pipon, Vardit Ravitsky, Maria Powell, Alistair Johnson, David Dorr, Philip Payne, Micah Boyer, Stephanie Watts, Ruth Bahr, Frank Rudzicz, Jordan Lerner-Ellis, Shaheen Awan, Don Bolser, Yael Bensoussan 3118 </span> 3119 </p> 3120 </a> 3121 <a class="w3-text" href="dumpala24b_interspeech.html"> 3122 <p> 3123 Self-Supervised Embeddings for Detecting Individual Symptoms of Depression 3124 <br> 3125 <span class="w3-text w3-text-theme"> 3126 Sri Harsha Dumpala, Katerina Dikaios, Abraham Nunes, Frank Rudzicz, Rudolf Uher, Sageev Oore 3127 </span> 3128 </p> 3129 </a> 3130 <a class="w3-text" href="mehta24_interspeech.html"> 3131 <p> 3132 Comparing ambulatory voice measures during daily life with brief laboratory assessments in speakers with and without vocal hyperfunction 3133 <br> 3134 <span class="w3-text w3-text-theme"> 3135 Daryush D. Mehta, Jarrad H. Van Stan, Hamzeh Ghasemzadeh, Robert E. Hillman 3136 </span> 3137 </p> 3138 </a> 3139 <a class="w3-text" href="williams24_interspeech.html"> 3140 <p> 3141 Predicting Acute Pain Levels Implicitly from Vocal Features 3142 <br> 3143 <span class="w3-text w3-text-theme"> 3144 Jennifer Williams, Eike Schneiders, Henry Card, Tina Seabrooke, Beatrice Pakenham-Walsh, Tayyaba Azim, Lucy Valls-Reed, Ganesh Vigneswaran, John Robert Bautista, Rohan Chandra, Arya Farahi 3145 </span> 3146 </p> 3147 </a> 3148 <a class="w3-text" href="demir24_interspeech.html"> 3149 <p> 3150 Towards Intelligent Speech Assistants in Operating Rooms: A Multimodal Model for Surgical Workflow Analysis 3151 <br> 3152 <span class="w3-text w3-text-theme"> 3153 Kubilay Can Demir, Belén Lojo RodrÃguez, Tobias Weise, Andreas Maier, Seung Hee Yang 3154 </span> 3155 </p> 3156 </a> 3157 <a class="w3-text" href="premananth24_interspeech.html"> 3158 <p> 3159 A Multimodal Framework for the Assessment of the Schizophrenia Spectrum 3160 <br>
3161 <span class="w3-text w3-text-theme"> 3162 Gowtham Premananth, Yashish M. Siriwardena, Philip Resnik, Sonia Bansal, Deanna L.Kelly, Carol Espy-Wilson 3163 </span> 3164 </p> 3165 </a> 3166 </div> 3167 </div> 3168 <br> 3169 <div class="w3-content" style="height:10px" id="Speech and Brain"></div> 3170 <div class="w3-card w3-round w3-white w3-padding"> 3171 <div class="w3-container" style="margin-top:40px"> 3172 <h4 class="w3-center">Speech and Brain</h4> 3173 <hr> 3174 <a class="w3-text" href="wang24ka_interspeech.html"> 3175 <p> 3176 Exploring the Complementary Nature of Speech and Eye Movements for Profiling Neurological Disorders 3177 <br> 3178 <span class="w3-text w3-text-theme"> 3179 Yuzhe Wang, Anna Favaro, Thomas Thebaud, Jesus Villalba, Najim Dehak, Laureano Moro-Velazquez 3180 </span> 3181 </p> 3182 </a> 3183 <a class="w3-text" href="li24l_interspeech.html"> 3184 <p> 3185 Refining Self-supervised Learnt Speech Representation using Brain Activations 3186 <br> 3187 <span class="w3-text w3-text-theme"> 3188 HengYu Li, Kangdi Mei, Zhaoci Liu, Yang Ai, Liping Chen, Jie Zhang, Zhenhua Ling 3189 </span> 3190 </p> 3191 </a> 3192 <a class="w3-text" href="wang24ba_interspeech.html"> 3193 <p> 3194 Large Language Model-based FMRI Encoding of Language Functions for Subjects with Neurocognitive Disorder 3195 <br> 3196 <span class="w3-text w3-text-theme"> 3197 Yuejiao Wang, Xianmin Gong, Lingwei Meng, Xixin Wu, Helen Meng 3198 </span> 3199 </p> 3200 </a> 3201 <a class="w3-text" href="neelabh24_interspeech.html"> 3202 <p> 3203 From Sound to Meaning in the Auditory Cortex: A Neuronal Representation and Classification Analysis 3204 <br> 3205 <span class="w3-text w3-text-theme"> 3206 Kumar Neelabh, Vishnu Sreekumar 3207 </span> 3208 </p> 3209 </a> 3210 <a class="w3-text" href="feng24_interspeech.html"> 3211 <p> 3212 Towards an End-to-End Framework for Invasive Brain Signal Decoding with Large Language Models 3213 <br> 3214 <span class="w3-text w3-text-theme"> 3215 Sheng Feng, Heyang Liu, Yu Wang, Yanfeng Wang 3216 </span> 3217 </p> 3218 </a> 3219 <a class="w3-text" href="lee24c_interspeech.html"> 3220 <p> 3221 Toward Fully-End-to-End Listened Speech Decoding from EEG Signals 3222 <br> 3223 <span class="w3-text w3-text-theme"> 3224 Jihwan Lee, Aditya Kommineni, Tiantian Feng, Kleanthis Avramidis, Xuan Shi, Sudarsana Reddy Kadiri, Shrikanth Narayanan 3225 </span> 3226 </p> 3227 </a> 3228 </div> 3229 </div> 3230 <br> 3231 <div class="w3-content" style="height:10px" id="Innovative Methods in Phonetics and Phonology"></div> 3232 <div class="w3-card w3-round w3-white w3-padding"> 3233 <div class="w3-container" style="margin-top:40px"> 3234 <h4 class="w3-center">Innovative Methods in Phonetics and Phonology</h4> 3235 <hr> 3236 <a class="w3-text" href="ahn24d_interspeech.html"> 3237 <p> 3238 The Use of Phone Categories and Cross-Language Modeling for Phone Alignment of Panãra 3239 <br>
3240 <span class="w3-text w3-text-theme"> 3241 Emily P. Ahn, Eleanor Chodroff, Myriam Lapierre, Gina-Anne Levow 3242 </span> 3243 </p> 3244 </a> 3245 <a class="w3-text" href="raybarman24_interspeech.html"> 3246 <p> 3247 Deciphering Assamese Vowel Harmony with Featural InfoWaveGAN 3248 <br> 3249 <span class="w3-text w3-text-theme"> 3250 Sneha Ray Barman, Shakuntala Mahanta, Neeraj Kumar Sharma 3251 </span> 3252 </p> 3253 </a> 3254 <a class="w3-text" href="tadavarthy24_interspeech.html"> 3255 <p> 3256 Phonological Feature Detection for US English using the Phonet Library 3257 <br> 3258 <span class="w3-text w3-text-theme"> 3259 Harsha Veena Tadavarthy, Austin Jones, Margaret E. L. Renwick 3260 </span> 3261 </p> 3262 </a> 3263 <a class="w3-text" href="kaland24_interspeech.html"> 3264 <p> 3265 K-means and hierarchical clustering of f0 contours 3266 <br> 3267 <span class="w3-text w3-text-theme"> 3268 Constantijn Kaland, Jeremy Steffman, Jennifer Cole 3269 </span> 3270 </p> 3271 </a> 3272 <a class="w3-text" href="rousso24_interspeech.html"> 3273 <p> 3274 Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment 3275 <br> 3276 <span class="w3-text w3-text-theme"> 3277 Rotem Rousso, Eyal Cohen, Joseph Keshet, Eleanor Chodroff 3278 </span> 3279 </p> 3280 </a> 3281 <a class="w3-text" href="kim24l_interspeech.html"> 3282 <p> 3283 Using wav2vec 2.0 for phonetic classification tasks: methodological aspects 3284 <br> 3285 <span class="w3-text w3-text-theme"> 3286 Lila Kim, Cédric Gendrot 3287 </span> 3288 </p> 3289 </a> 3290 <a class="w3-text" href="lambropoulos24_interspeech.html"> 3291 <p> 3292 The sub-band cepstrum as a tool for locating local spectral regions of phonetic sensitivity: A first attempt with multi-speaker vowel data 3293 <br> 3294 <span class="w3-text w3-text-theme"> 3295 Michael Lambropoulos, Frantz Clermont, Shunichi Ishihara 3296 </span> 3297 </p> 3298 </a> 3299 <a class="w3-text" href="chung24_interspeech.html"> 3300 <p> 3301 Speaker-Independent Acoustic-to-Articulatory Inversion through Multi-Channel Attention Discriminator 3302 <br> 3303 <span class="w3-text w3-text-theme"> 3304 Woo-Jin Chung, Hong-Goo Kang 3305 </span> 3306 </p> 3307 </a> 3308 <a class="w3-text" href="weise24_interspeech.html"> 3309 <p> 3310 Speaker- and Text-Independent Estimation of Articulatory Movements and Phoneme Alignments from Speech 3311 <br>
3312 <span class="w3-text w3-text-theme"> 3313 Tobias Weise, Philipp Klumpp, Kubilay Can Demir, Paula Andrea Pérez-Toro, Maria Schuster, Elmar Noeth, Bjoern Heismann, Andreas Maier, Seung Hee Yang 3314 </span> 3315 </p> 3316 </a> 3317 <a class="w3-text" href="oura24_interspeech.html"> 3318 <p> 3319 Preprocessing for acoustic-to-articulatory inversion using real-time MRI movies of Japanese speech 3320 <br> 3321 <span class="w3-text w3-text-theme"> 3322 Anna Oura, Hideaki Kikuchi, Tetsunori Kobayashi 3323 </span> 3324 </p> 3325 </a> 3326 </div> 3327 </div> 3328 <br> 3329 <div class="w3-content" style="height:10px" id="Voice, Tones and F0"></div> 3330 <div class="w3-card w3-round w3-white w3-padding"> 3331 <div class="w3-container" style="margin-top:40px"> 3332 <h4 class="w3-center">Voice, Tones and F0</h4> 3333 <hr> 3334 <a class="w3-text" href="li24f_interspeech.html"> 3335 <p> 3336 Impact of the tonal factor on diphthong realizations in Standard Mandarin with Generalized Additive Mixed Models 3337 <br> 3338 <span class="w3-text w3-text-theme"> 3339 Chenyu Li, Jalal Al-Tamimi 3340 </span> 3341 </p> 3342 </a> 3343 <a class="w3-text" href="xiaowang24_interspeech.html"> 3344 <p> 3345 A Study on the Information Mechanism of the 3rd Tone Sandhi Rule in Mandarin Disyllabic Words 3346 <br> 3347 <span class="w3-text w3-text-theme"> 3348 Liu Xiaowang, Jinsong Zhang 3349 </span> 3350 </p> 3351 </a> 3352 <a class="w3-text" href="weirich24_interspeech.html"> 3353 <p> 3354 Gender and age based f0-variation in the German Plapper Corpus 3355 <br> 3356 <span class="w3-text w3-text-theme"> 3357 Melanie Weirich, Daniel Duran, Stefanie Jannedy 3358 </span> 3359 </p> 3360 </a> 3361 <a class="w3-text" href="xu24j_interspeech.html"> 3362 <p> 3363 Voice quality in telephone speech: Comparing acoustic measures between VoIP telephone and high-quality recordings 3364 <br> 3365 <span class="w3-text w3-text-theme"> 3366 Chenzi Xu, Jessica Wormald, Paul Foulkes, Philip Harrison, Vincent Hughes, Poppy Welch, Finnian Kelly, David van der Vloed 3367 </span> 3368 </p> 3369 </a> 3370 <a class="w3-text" href="gessinger24_interspeech.html"> 3371 <p> 3372 The Use of Modifiers and f0 in Remote Referential Communication with Human and Computer Partners 3373 <br> 3374 <span class="w3-text w3-text-theme"> 3375 Iona Gessinger, Bistra Andreeva, Benjamin R.
3375Cowan 3376 </span> 3377 </p> 3378 </a> 3379 </div> 3380 </div> 3381 <br> 3382 <div class="w3-content" style="height:10px" id="Emotion Recognition: Resources and Benchmarks"></div> 3383 <div class="w3-card w3-round w3-white w3-padding"> 3384 <div class="w3-container" style="margin-top:40px"> 3385 <h4 class="w3-center">Emotion Recognition: Resources and Benchmarks</h4> 3386 <hr> 3387 <a class="w3-text" href="ma24b_interspeech.html"> 3388 <p> 3389 EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark 3390 <br> 3391 <span class="w3-text w3-text-theme"> 3392 Ziyang Ma, Mingjie Chen, Hezhao Zhang, Zhisheng Zheng, Wenxi Chen, Xiquan Li, Jiaxin Ye, Xie Chen, Thomas Hain 3393 </span> 3394 </p> 3395 </a> 3396 <a class="w3-text" href="triantafyllopoulos24b_interspeech.html"> 3397 <p> 3398 INTERSPEECH 2009 Emotion Challenge Revisited: Benchmarking 15 Years of Progress in Speech Emotion Recognition 3399 <br> 3400 <span class="w3-text w3-text-theme"> 3401 Andreas Triantafyllopoulos, Anton Batliner, Simon Rampp, Manuel Milling, Björn Schuller 3402 </span> 3403 </p> 3404 </a> 3405 <a class="w3-text" href="ibrahim24_interspeech.html"> 3406 <p> 3407 What Does it Take to Generalize SER Model Across Datasets? A Comprehensive Benchmark 3408 <br> 3409 <span class="w3-text w3-text-theme"> 3410 Adham Ibrahim, Shady Shehata, Ajinkya Kulkarni, Mukhtar Mohamed, Muhammad Abdul-Mageed 3411 </span> 3412 </p> 3413 </a> 3414 <a class="w3-text" href="naini24_interspeech.html"> 3415 <p> 3416 WHiSER: White House Tapes Speech Emotion Recognition Corpus 3417 <br> 3418 <span class="w3-text w3-text-theme"> 3419 Abinay Reddy Naini, Lucas Goncalves, Mary A. Kohler, Donita Robinson, Elizabeth Richerson, Carlos Busso 3420 </span> 3421 </p> 3422 </a> 3423 <a class="w3-text" href="latif24_interspeech.html"> 3424 <p> 3425 Evaluating Transformer-Enhanced Deep Reinforcement Learning for Speech Emotion Recognition 3426 <br> 3427 <span class="w3-text w3-text-theme"> 3428 Siddique Latif, Raja Jurdak, Björn W. Schuller 3429 </span> 3430 </p> 3431 </a> 3432 <a class="w3-text" href="wang24ia_interspeech.html"> 3433 <p> 3434 Boosting Cross-Corpus Speech Emotion Recognition using CycleGAN with Contrastive Learning 3435 <br> 3436 <span class="w3-text w3-text-theme"> 3437 Jincen Wang, Yan Zhao, Cheng Lu, Chuangao Tang, Sunan Li, Yuan Zong, Wenming Zheng 3438 </span> 3439 </p> 3440 </a> 3441 </div> 3442 </div> 3443 <br> 3444 <div class="w3-content" style="height:10px" id="Speaker and Language Identification and Diarization"></div> 3445 <div class="w3-card w3-round w3-white w3-padding"> 3446 <div class="w3-container" style="margin-top:40px"> 3447 <h4 class="w3-center">Speaker and Language Identification and Diarization</h4> 3448 <hr>
3449 <a class="w3-text" href="rahou24_interspeech.html"> 3450 <p> 3451 Multi-latency look-ahead for streaming speaker segmentation 3452 <br> 3453 <span class="w3-text w3-text-theme"> 3454 Bilal Rahou, Hervé Bredin 3455 </span> 3456 </p> 3457 </a> 3458 <a class="w3-text" href="boeddeker24_interspeech.html"> 3459 <p> 3460 Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment 3461 <br> 3462 <span class="w3-text w3-text-theme"> 3463 Christoph Boeddeker, Tobias Cord-Landwehr, Reinhold Haeb-Umbach 3464 </span> 3465 </p> 3466 </a> 3467 <a class="w3-text" href="mariotte24_interspeech.html"> 3468 <p> 3469 ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings 3470 <br> 3471 <span class="w3-text w3-text-theme"> 3472 Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas 3473 </span> 3474 </p> 3475 </a> 3476 <a class="w3-text" href="pirlogeanu24_interspeech.html"> 3477 <p> 3478 Hybrid-Diarization System with Overlap Post-Processing for the DISPLACE 2024 Challenge 3479 <br> 3480 <span class="w3-text w3-text-theme"> 3481 Gabriel Pîrlogeanu, Octavian Pascu, Alexandru-Lucian Georgescu, Horia Cucu 3482 </span> 3483 </p> 3484 </a> 3485 <a class="w3-text" href="kalluri24_interspeech.html"> 3486 <p> 3487 The Second DISPLACE Challenge: DIarization of SPeaker and LAnguage in Conversational Environments 3488 <br> 3489 <span class="w3-text w3-text-theme"> 3490 Shareef Babu Kalluri, Prachi Singh, Pratik Roy Chowdhuri, Apoorva Kulkarni, Shikha Baghel, Pradyoth Hegde, Swapnil Sontakke, Deepak K T, S.R. Mahadeva Prasanna, Deepu Vijayasenan, Sriram Ganapathy 3491 </span> 3492 </p> 3493 </a> 3494 <a class="w3-text" href="kalda24_interspeech.html"> 3495 <p> 3496 TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024 3497 <br> 3498 <span class="w3-text w3-text-theme"> 3499 Joonas Kalda, Tanel Alumae, Martin Lebourdais, Hervé Bredin, Séverin Baroudi, Ricard Marxer 3500 </span> 3501 </p> 3502 </a> 3503 <a class="w3-text" href="hao24b_interspeech.html"> 3504 <p> 3505 Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification 3506 <br> 3507 <span class="w3-text w3-text-theme"> 3508 Yaqian Hao, Chenguang Hu, Yingying Gao, Shilei Zhang, Junlan Feng 3509 </span> 3510 </p> 3511 </a> 3512 <a class="w3-text" href="valente24_interspeech.html"> 3513 <p> 3514 Exploring Spoken Language Identification Strategies for Automatic Transcription of Multilingual Broadcast and Institutional Speech 3515 <br>
3516 <span class="w3-text w3-text-theme"> 3517 Martina Valente, Fabio Brugnara, Giovanni Morrone, Enrico Zovato, Leonardo Badino 3518 </span> 3519 </p> 3520 </a> 3521 <a class="w3-text" href="paturi24_interspeech.html"> 3522 <p> 3523 AG-LSEC: Audio Grounded Lexical Speaker Error Correction 3524 <br> 3525 <span class="w3-text w3-text-theme"> 3526 Rohit Paturi, Xiang Li, Sundararajan Srinivasan 3527 </span> 3528 </p> 3529 </a> 3530 <a class="w3-text" href="su24_interspeech.html"> 3531 <p> 3532 Speaker Change Detection with Weighted-sum Knowledge Distillation based on Self-supervised Pre-trained Models 3533 <br> 3534 <span class="w3-text w3-text-theme"> 3535 Hang Su, Yuxiang Kong, Lichun Fan, Peng Gao, Yujun Wang, Zhiyong Wu 3536 </span> 3537 </p> 3538 </a> 3539 <a class="w3-text" href="makishima24_interspeech.html"> 3540 <p> 3541 SOMSRED: Sequential Output Modeling for Joint Multi-talker Overlapped Speech Recognition and Speaker Diarization 3542 <br> 3543 <span class="w3-text w3-text-theme"> 3544 Naoki Makishima, Naotaka Kawata, Mana Ihori, Tomohiro Tanaka, Shota Orihashi, Atsushi Ando, Ryo Masumura 3545 </span> 3546 </p> 3547 </a> 3548 <a class="w3-text" href="munakata24_interspeech.html"> 3549 <p> 3550 Song Data Cleansing for End-to-End Neural Singer Diarization Using Neural Analysis and Synthesis Framework 3551 <br> 3552 <span class="w3-text w3-text-theme"> 3553 Hokuto Munakata, Ryo Terashima, Yusuke Fujita 3554 </span> 3555 </p> 3556 </a> 3557 </div> 3558 </div> 3559 <br> 3560 <div class="w3-content" style="height:10px" id="Audio-Text Retrieval"></div> 3561 <div class="w3-card w3-round w3-white w3-padding"> 3562 <div class="w3-container" style="margin-top:40px"> 3563 <h4 class="w3-center">Audio-Text Retrieval</h4> 3564 <hr> 3565 <a class="w3-text" href="xin24_interspeech.html"> 3566 <p> 3567 DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval 3568 <br> 3569 <span class="w3-text w3-text-theme"> 3570 Yifei Xin, Xuxin Cheng, Zhihong Zhu, Xusheng Yang, Yuexian Zou 3571 </span> 3572 </p> 3573 </a> 3574 <a class="w3-text" href="yan24_interspeech.html"> 3575 <p> 3576 Bridging Language Gaps in Audio-Text Retrieval 3577 <br> 3578 <span class="w3-text w3-text-theme"> 3579 Zhiyong Yan, Heinrich Dinkel, Yongqing Wang, Jizhong Liu, Junbo Zhang, Yujun Wang, Bin Wang 3580 </span> 3581 </p> 3582 </a> 3583 <a class="w3-text" href="deshmukh24_interspeech.html"> 3584 <p> 3585 Domain Adaptation for Contrastive Audio-Language Models 3586 <br>
3587 <span class="w3-text w3-text-theme"> 3588 Soham Deshmukh, Rita Singh, Bhiksha Raj 3589 </span> 3590 </p> 3591 </a> 3592 <a class="w3-text" href="paissan24_interspeech.html"> 3593 <p> 3594 tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models 3595 <br> 3596 <span class="w3-text w3-text-theme"> 3597 Francesco Paissan, Elisabetta Farella 3598 </span> 3599 </p> 3600 </a> 3601 <a class="w3-text" href="kim24f_interspeech.html"> 3602 <p> 3603 BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification 3604 <br> 3605 <span class="w3-text w3-text-theme"> 3606 June-Woo Kim, Miika Toikkanen, Yera Choi, Seoung-Eun Moon, Ho-Young Jung 3607 </span> 3608 </p> 3609 </a> 3610 <a class="w3-text" href="tang24b_interspeech.html"> 3611 <p> 3612 Enhanced Feature Learning with Normalized Knowledge Distillation for Audio Tagging 3613 <br> 3614 <span class="w3-text w3-text-theme"> 3615 Yuwu Tang, Ziang Ma, Haitao Zhang 3616 </span> 3617 </p> 3618 </a> 3619 </div> 3620 </div> 3621 <br> 3622 <div class="w3-content" style="height:10px" id="Speech Enhancement"></div> 3623 <div class="w3-card w3-round w3-white w3-padding"> 3624 <div class="w3-container" style="margin-top:40px"> 3625 <h4 class="w3-center">Speech Enhancement</h4> 3626 <hr> 3627 <a class="w3-text" href="liu24n_interspeech.html"> 3628 <p> 3629 RaD-Net 2: A causal two-stage repairing and denoising speech enhancement network with knowledge distillation and complex axial self-attention 3630 <br> 3631 <span class="w3-text w3-text-theme"> 3632 Mingshuai Liu, Zhuangqi Chen, Xiaopeng Yan, Yuanjun Lv, Xianjun Xia, Chuanzeng Huang, Yijian Xiao, Lei Xie 3633 </span> 3634 </p> 3635 </a> 3636 <a class="w3-text" href="liu24o_interspeech.html"> 3637 <p> 3638 DNN-based monaural speech enhancement using alternate analysis windows for phase and magnitude modification 3639 <br> 3640 <span class="w3-text w3-text-theme"> 3641 Xi Liu, John H.L. Hansen 3642 </span> 3643 </p> 3644 </a> 3645 <a class="w3-text" href="li24aa_interspeech.html"> 3646 <p> 3647 Improved Remixing Process for Domain Adaptation-Based Speech Enhancement by Mitigating Data Imbalance in Signal-to-Noise Ratio 3648 <br> 3649 <span class="w3-text w3-text-theme"> 3650 Li Li, Shogo Seki 3651 </span> 3652 </p> 3653 </a> 3654 <a class="w3-text" href="zhang24_interspeech.html"> 3655 <p> 3656 Neural Network Augmented Kalman Filter for Robust Acoustic Howling Suppression 3657 <br>
3658 <span class="w3-text w3-text-theme"> 3659 Yixuan Zhang, Hao Zhang, Meng Yu, Dong Yu 3660 </span> 3661 </p> 3662 </a> 3663 <a class="w3-text" href="li24w_interspeech.html"> 3664 <p> 3665 Improving Speech Enhancement by Integrating Inter-Channel and Band Features with Dual-branch Conformer 3666 <br> 3667 <span class="w3-text w3-text-theme"> 3668 Jizhen Li, Xinmeng Xu, Weiping Tu, Yuhong Yang, Rong Zhu 3669 </span> 3670 </p> 3671 </a> 3672 <a class="w3-text" href="zhang24n_interspeech.html"> 3673 <p> 3674 An Exploration of Length Generalization in Transformer-Based Speech Enhancement 3675 <br> 3676 <span class="w3-text w3-text-theme"> 3677 Qiquan Zhang, Hongxu Zhu, Xinyuan Qian, Eliathamby Ambikairajah, Haizhou Li 3678 </span> 3679 </p> 3680 </a> 3681 <a class="w3-text" href="guan24_interspeech.html"> 3682 <p> 3683 Reducing Speech Distortion and Artifacts for Speech Enhancement by Loss Function 3684 <br> 3685 <span class="w3-text w3-text-theme"> 3686 Haixin Guan, Wei Dai, Guangyong Wang, Xiaobin Tan, Peng Li, Jiaen Liang 3687 </span> 3688 </p> 3689 </a> 3690 <a class="w3-text" href="mawalim24_interspeech.html"> 3691 <p> 3692 Are Recent Deep Learning-Based Speech Enhancement Methods Ready to Confront Real-World Noisy Environments? 3693 <br> 3694 <span class="w3-text w3-text-theme"> 3695 Candy Olivia Mawalim, Shogo Okada, Masashi Unoki 3696 </span> 3697 </p> 3698 </a> 3699 <a class="w3-text" href="zhang24i_interspeech.html"> 3700 <p> 3701 Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement 3702 <br> 3703 <span class="w3-text w3-text-theme"> 3704 Wangyou Zhang, Kohei Saijo, Jee-weon Jung, Chenda Li, Shinji Watanabe, Yanmin Qian 3705 </span> 3706 </p> 3707 </a> 3708 </div> 3709 </div> 3710 <br> 3711 <div class="w3-content" style="height:10px" id="Speech Coding"></div> 3712 <div class="w3-card w3-round w3-white w3-padding"> 3713 <div class="w3-container" style="margin-top:40px"> 3714 <h4 class="w3-center">Speech Coding</h4> 3715 <hr> 3716 <a class="w3-text" href="zhang24g_interspeech.html"> 3717 <p> 3718 TD-PLC: A Semantic-Aware Speech Encoding for Improved Packet Loss Concealment 3719 <br> 3720 <span class="w3-text w3-text-theme"> 3721 Jinghong Zhang, Zugang Zhao, Yonghui Liu, Jianbing Liu, Zhiqiang He, Kai Niu 3722 </span> 3723 </p> 3724 </a> 3725 <a class="w3-text" href="zhang24m_interspeech.html"> 3726 <p> 3727 BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation 3728 <br>
3729 <span class="w3-text w3-text-theme"> 3730 Zihan Zhang, Xianjun Xia, Chuanzeng Huang, Yijian Xiao, Lei Xie 3731 </span> 3732 </p> 3733 </a> 3734 <a class="w3-text" href="gupta24c_interspeech.html"> 3735 <p> 3736 On Improving Error Resilience of Neural End-to-End Speech Coders 3737 <br> 3738 <span class="w3-text w3-text-theme"> 3739 Kishan Gupta, Nicola Pia, Srikanth Korse, Andreas Brendel, Guillaume Fuchs, Markus Multrus 3740 </span> 3741 </p> 3742 </a> 3743 <a class="w3-text" href="muller24c_interspeech.html"> 3744 <p> 3745 Speech quality evaluation of neural audio codecs 3746 <br> 3747 <span class="w3-text w3-text-theme"> 3748 Thomas Muller, Stephane Ragot, Laetitia Gros, Pierrick Philippe, Pascal Scalart 3749 </span> 3750 </p> 3751 </a> 3752 <a class="w3-text" href="ai24b_interspeech.html"> 3753 <p> 3754 A Low-Bitrate Neural Audio Codec Framework with Bandwidth Reduction and Recovery for High-Sampling-Rate Waveforms 3755 <br> 3756 <span class="w3-text w3-text-theme"> 3757 Yang Ai, Ye-Xin Lu, Xiao-Hang Jiang, Zheng-Yan Sheng, Rui-Chen Zheng, Zhen-Hua Ling 3758 </span> 3759 </p> 3760 </a> 3761 <a class="w3-text" href="wu24p_interspeech.html"> 3762 <p> 3763 CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems 3764 <br> 3765 <span class="w3-text w3-text-theme"> 3766 Haibin Wu, Yuan Tseng, Hung-yi Lee 3767 </span> 3768 </p> 3769 </a> 3770 </div> 3771 </div> 3772 <br> 3773 <div class="w3-content" style="height:10px" id="Speech Synthesis: Expressivity and Emotion"></div> 3774 <div class="w3-card w3-round w3-white w3-padding"> 3775 <div class="w3-container" style="margin-top:40px"> 3776 <h4 class="w3-center">Speech Synthesis: Expressivity and Emotion</h4> 3777 <hr> 3778 <a class="w3-text" href="li24pa_interspeech.html"> 3779 <p> 3780 GTR-Voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis 3781 <br> 3782 <span class="w3-text w3-text-theme"> 3783 Zehua Kcriss Li, Meiying Melissa Chen, Yi Zhong, Pinxin Liu, Zhiyao Duan 3784 </span> 3785 </p> 3786 </a> 3787 <a class="w3-text" href="seong24b_interspeech.html"> 3788 <p> 3789 TSP-TTS: Text-based Style Predictor with Residual Vector Quantization for Expressive Text-to-Speech 3790 <br> 3791 <span class="w3-text w3-text-theme"> 3792 Donghyun Seong, Hoyoung Lee, Joon-Hyuk Chang 3793 </span> 3794 </p> 3795 </a> 3796 <a class="w3-text" href="li24na_interspeech.html"> 3797 <p> 3798 Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models 3799 <br>
3800 <span class="w3-text w3-text-theme"> 3801 Weiqin Li, Peiji Yang, Yicheng Zhong, Yixuan Zhou, Zhisheng Wang, Zhiyong Wu, Xixin Wu, Helen Meng 3802 </span> 3803 </p> 3804 </a> 3805 <a class="w3-text" href="guo24d_interspeech.html"> 3806 <p> 3807 Text-aware and Context-aware Expressive Audiobook Speech Synthesis 3808 <br> 3809 <span class="w3-text w3-text-theme"> 3810 Dake Guo, Xinfa Zhu, Liumeng Xue, Yongmao Zhang, Wenjie Tian, Lei Xie 3811 </span> 3812 </p> 3813 </a> 3814 <a class="w3-text" href="bott24_interspeech.html"> 3815 <p> 3816 Controlling Emotion in Text-to-Speech with Natural Language Prompts 3817 <br> 3818 <span class="w3-text w3-text-theme"> 3819 Thomas Bott, Florian Lux, Ngoc Thang Vu 3820 </span> 3821 </p> 3822 </a> 3823 <a class="w3-text" href="xue24b_interspeech.html"> 3824 <p> 3825 Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretraining 3826 <br> 3827 <span class="w3-text w3-text-theme"> 3828 Jinlong Xue, Yayue Deng, Yingming Gao, Ya Li 3829 </span> 3830 </p> 3831 </a> 3832 <a class="w3-text" href="kalyan24_interspeech.html"> 3833 <p> 3834 Emotion Arithmetic: Emotional Speech Synthesis via Weight Space Interpolation 3835 <br> 3836 <span class="w3-text w3-text-theme"> 3837 Pavan Kalyan, Preeti Rao, Preethi Jyothi, Pushpak Bhattacharyya 3838 </span> 3839 </p> 3840 </a> 3841 <a class="w3-text" href="cho24_interspeech.html"> 3842 <p> 3843 EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech 3844 <br> 3845 <span class="w3-text w3-text-theme"> 3846 Deok-Hyeon Cho, Hyung-Seok Oh, Seung-Bin Kim, Sang-Hoon Lee, Seong-Whan Lee 3847 </span> 3848 </p> 3849 </a> 3850 <a class="w3-text" href="li24da_interspeech.html"> 3851 <p> 3852 Expressive paragraph text-to-speech synthesis with multi-step variational autoencoder 3853 <br> 3854 <span class="w3-text w3-text-theme"> 3855 Xuyuan Li, Zengqiang Shang, Peiyang Shi, Hua Hua, Ta Li, Pengyuan Zhang 3856 </span> 3857 </p> 3858 </a> 3859 <a class="w3-text" href="yu24b_interspeech.html"> 3860 <p> 3861 Differentiable Time-Varying Linear Prediction in the Context of End-to-End Analysis-by-Synthesis 3862 <br> 3863 <span class="w3-text w3-text-theme"> 3864 Chin-Yun Yu, György Fazekas 3865 </span> 3866 </p> 3867 </a> 3868 </div> 3869 </div> 3870 <br> 3871 <div class="w3-content" style="height:10px" id="Speech Synthesis: Tools and Data"></div> 3872 <div class="w3-card w3-round w3-white w3-padding"> 3873 <div class="w3-container" style="margin-top:40px"> 3874 <h4 class="w3-center">Speech Synthesis: Tools and Data</h4> 3875 <hr> 3876 <a class="w3-text" href="saito24_interspeech.html"> 3877 <p> 3878 SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark 3879 <br>
3880 <span class="w3-text w3-text-theme"> 3881 Yuki Saito, Takuto Igarashi, Kentaro Seki, Shinnosuke Takamichi, Ryuichi Yamamoto, Kentaro Tachibana, Hiroshi Saruwatari 3882 </span> 3883 </p> 3884 </a> 3885 <a class="w3-text" href="srinivasavaradhan24_interspeech.html"> 3886 <p> 3887 Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings 3888 <br> 3889 <span class="w3-text w3-text-theme"> 3890 Praveen Srinivasa Varadhan, Ashwin Sankar, Giri Raju, Mitesh M Khapra 3891 </span> 3892 </p> 3893 </a> 3894 <a class="w3-text" href="ma24c_interspeech.html"> 3895 <p> 3896 FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks 3897 <br> 3898 <span class="w3-text w3-text-theme"> 3899 Min Ma, Yuma Koizumi, Shigeki Karita, Heiga Zen, Jason Riesa, Haruko Ishikawa, Michiel Bacchiani 3900 </span> 3901 </p> 3902 </a> 3903 <a class="w3-text" href="ma24d_interspeech.html"> 3904 <p> 3905 WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark 3906 <br> 3907 <span class="w3-text w3-text-theme"> 3908 Linhan Ma, Dake Guo, Kun Song, Yuepeng Jiang, Shuai Wang, Liumeng Xue, Weiming Xu, Huan Zhao, Binbin Zhang, Lei Xie 3909 </span> 3910 </p> 3911 </a> 3912 <a class="w3-text" href="yang24d_interspeech.html"> 3913 <p> 3914 MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis 3915 <br> 3916 <span class="w3-text w3-text-theme"> 3917 Qian Yang, Jialong Zuo, Zhe Su, Ziyue Jiang, Mingze Li, Zhou Zhao, Feiyang Chen, Zhefeng Wang, Baoxing Huai 3918 </span> 3919 </p> 3920 </a> 3921 <a class="w3-text" href="kawamura24_interspeech.html"> 3922 <p> 3923 LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning 3924 <br> 3925 <span class="w3-text w3-text-theme"> 3926 Masaya Kawamura, Ryuichi Yamamoto, Yuma Shirahata, Takuya Hasumi, Kentaro Tachibana 3927 </span> 3928 </p> 3929 </a> 3930 <a class="w3-text" href="ogun24_interspeech.html"> 3931 <p> 3932 1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis 3933 <br> 3934 <span class="w3-text w3-text-theme"> 3935 Sewade Ogun, Abraham T. Owodunni, Tobi Olatunji, Eniola Alese, Babatunde Oladimeji, Tejumade Afonja, Kayode Olaleye, Naome A. Etori, Tosin Adewumi 3936 </span> 3937 </p> 3938 </a> 3939 <a class="w3-text" href="take24_interspeech.html"> 3940 <p> 3941 SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis 3942 <br>
3943 <span class="w3-text w3-text-theme"> 3944 Osamu Take, Shinnosuke Takamichi, Kentaro Seki, Yoshiaki Bando, Hiroshi Saruwatari 3945 </span> 3946 </p> 3947 </a> 3948 </div> 3949 </div> 3950 <br> 3951 <div class="w3-content" style="height:10px" id="Speech Synthesis: Singing Voice Synthesis"></div> 3952 <div class="w3-card w3-round w3-white w3-padding"> 3953 <div class="w3-container" style="margin-top:40px"> 3954 <h4 class="w3-center">Speech Synthesis: Singing Voice Synthesis</h4> 3955 <hr> 3956 <a class="w3-text" href="kim24i_interspeech.html"> 3957 <p> 3958 MakeSinger: A Semi-Supervised Training Method for Data-Efficient Singing Voice Synthesis via Classifier-free Diffusion Guidance 3959 <br> 3960 <span class="w3-text w3-text-theme"> 3961 Semin Kim, Myeonghun Jeong, Hyeonseung Lee, Minchan Kim, Byoung Jin Choi, Nam Soo Kim 3962 </span> 3963 </p> 3964 </a> 3965 <a class="w3-text" href="okamoto24_interspeech.html"> 3966 <p> 3967 Challenge of Singing Voice Synthesis Using Only Text-To-Speech Corpus With FIRNet Source-Filter Neural Vocoder 3968 <br> 3969 <span class="w3-text w3-text-theme"> 3970 Takuma Okamoto, Yamato Ohtani, Sota Shimizu, Tomoki Toda, Hisashi Kawai 3971 </span> 3972 </p> 3973 </a> 3974 <a class="w3-text" href="kim24p_interspeech.html"> 3975 <p> 3976 Period Singer: Integrating Periodic and Aperiodic Variational Autoencoders for Natural-Sounding End-to-End Singing Voice Synthesis 3977 <br> 3978 <span class="w3-text w3-text-theme"> 3979 Taewoo Kim, Choonsang Cho, Young Han Lee 3980 </span> 3981 </p> 3982 </a> 3983 <a class="w3-text" href="shi24_interspeech.html"> 3984 <p> 3985 Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing 3986 <br> 3987 <span class="w3-text w3-text-theme"> 3988 Jiatong Shi, Yueqian Lin, Xinyi Bai, Keyi Zhang, Yuning Wu, Yuxun Tang, Yifeng Yu, Qin Jin, Shinji Watanabe 3989 </span> 3990 </p> 3991 </a> 3992 <a class="w3-text" href="hwang24_interspeech.html"> 3993 <p> 3994 X-Singer: Code-Mixed Singing Voice Synthesis via Cross-Lingual Learning 3995 <br> 3996 <span class="w3-text w3-text-theme"> 3997 Ji-Sang Hwang, Hyeongrae Noh, Yoonseok Hong, Insoo Oh 3998 </span> 3999 </p> 4000 </a> 4001 <a class="w3-text" href="gao24e_interspeech.html"> 4002 <p> 4003 An End-to-End Approach for Chord-Conditioned Song Generation 4004 <br> 4005 <span class="w3-text w3-text-theme"> 4006 Shuochen Gao, Shun Lei, Fan Zhuo, Hangyu Liu, Feng Liu, Boshi Tang, Qiaochu Huang, Shiyin Kang, Zhiyong Wu 4007 </span> 4008 </p> 4009 </a> 4010 </div> 4011 </div> 4012 <br> 4013 <div class="w3-content" style="height:10px" id="LLM in ASR"></div> 4014 <div class="w3-card w3-round w3-white w3-padding"> 4015 <div class="w3-container" style="margin-top:40px"> 4016 <h4 class="w3-center">LLM in ASR</h4> 4017 <hr> 4018 <a class="w3-text" href="baskar24_interspeech.html"> 4019 <p> 4020 Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions 4021 <br>
4022 <span class="w3-text w3-text-theme"> 4023 Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Neeraj Gaur, Zhong Meng 4024 </span> 4025 </p> 4026 </a> 4027 <a class="w3-text" href="seide24_interspeech.html"> 4028 <p> 4029 Speech ReaLLM â Real-time Speech Recognition with Multimodal Language Models by Teaching the Flow of Time 4030 <br> 4031 <span class="w3-text w3-text-theme"> 4032 Frank Seide, Yangyang Shi, Morrie Doulaty, Yashesh Gaur, Junteng Jia, Chunyang Wu 4033 </span> 4034 </p> 4035 </a> 4036 <a class="w3-text" href="li24t_interspeech.html"> 4037 <p> 4038 A Transcription Prompt-based Efficient Audio Large Language Model for Robust Speech Recognition 4039 <br> 4040 <span class="w3-text w3-text-theme"> 4041 Yangze Li, Xiong Wang, Songjun Cao, Yike Zhang, Long Ma, Lei Xie 4042 </span> 4043 </p> 4044 </a> 4045 <a class="w3-text" href="tang24_interspeech.html"> 4046 <p> 4047 Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models 4048 <br> 4049 <span class="w3-text w3-text-theme"> 4050 Zhiyuan Tang, Dong Wang, Shen Huang, Shidong Shang 4051 </span> 4052 </p> 4053 </a> 4054 </div> 4055 </div> 4056 <br> 4057 <div class="w3-content" style="height:10px" id="Vision and Speech"></div> 4058 <div class="w3-card w3-round w3-white w3-padding"> 4059 <div class="w3-container" style="margin-top:40px"> 4060 <h4 class="w3-center">Vision and Speech</h4> 4061 <hr> 4062 <a class="w3-text" href="kim24g_interspeech.html"> 4063 <p> 4064 AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning 4065 <br> 4066 <span class="w3-text w3-text-theme"> 4067 Jongsuk Kim, Jiwon Shin, Junmo Kim 4068 </span> 4069 </p> 4070 </a> 4071 <a class="w3-text" href="ghosh24b_interspeech.html"> 4072 <p> 4073 LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition 4074 <br> 4075 <span class="w3-text w3-text-theme"> 4076 Sreyan Ghosh, Sonal Kumar, Ashish Seth, Purva Chiniya, Utkarsh Tyagi, Ramani Duraiswami, Dinesh Manocha 4077 </span> 4078 </p> 4079 </a> 4080 <a class="w3-text" href="li24v_interspeech.html"> 4081 <p> 4082 Joint Speaker Features Learning for Audio-visual Multichannel Speech Separation and Recognition 4083 <br> 4084 <span class="w3-text w3-text-theme"> 4085 Guinan Li, Jiajun Deng, Youjun Chen, Mengzhe Geng, Shujie Hu, Zhe Li, Zengrui Jin, Tianzi Wang, Xurong Xie, Helen Meng, Xunying Liu 4086 </span> 4087 </p> 4088 </a> 4089 <a class="w3-text" href="chen24y_interspeech.html"> 4090 <p> 4091 CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge 4092 <br>
4093 <span class="w3-text w3-text-theme"> 4094 Chen Chen, Zehua Liu, Xiaolou Li, Lantian Li, Dong Wang 4095 </span> 4096 </p> 4097 </a> 4098 </div> 4099 </div> 4100 <br> 4101 <div class="w3-content" style="height:10px" id="Spoken Document Summarization"></div> 4102 <div class="w3-card w3-round w3-white w3-padding"> 4103 <div class="w3-container" style="margin-top:40px"> 4104 <h4 class="w3-center">Spoken Document Summarization</h4> 4105 <hr> 4106 <a class="w3-text" href="kroll24_interspeech.html"> 4107 <p> 4108 Optimizing the role of human evaluation in LLM-based spoken document summarization systems 4109 <br> 4110 <span class="w3-text w3-text-theme"> 4111 Margaret Kroll, Kelsey Kraus 4112 </span> 4113 </p> 4114 </a> 4115 <a class="w3-text" href="ryu24_interspeech.html"> 4116 <p> 4117 Key-Element-Informed sLLM Tuning for Document Summarization 4118 <br> 4119 <span class="w3-text w3-text-theme"> 4120 Sangwon Ryu, Heejin Do, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok 4121 </span> 4122 </p> 4123 </a> 4124 <a class="w3-text" href="matsuura24_interspeech.html"> 4125 <p> 4126 Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation 4127 <br> 4128 <span class="w3-text w3-text-theme"> 4129 Kohei Matsuura, Takanori Ashihara, Takafumi Moriya, Masato Mimura, Takatomo Kano, Atsunori Ogawa, Marc Delcroix 4130 </span> 4131 </p> 4132 </a> 4133 <a class="w3-text" href="shang24_interspeech.html"> 4134 <p> 4135 An End-to-End Speech Summarization Using Large Language Model 4136 <br> 4137 <span class="w3-text w3-text-theme"> 4138 Hengchao Shang, Zongyao Li, Jiaxin Guo, Shaojun Li, Zhiqiang Rao, Yuanchang Luo, Daimeng Wei, Hao Yang 4139 </span> 4140 </p> 4141 </a> 4142 <a class="w3-text" href="kang24d_interspeech.html"> 4143 <p> 4144 Prompting Large Language Models with Audio for General-Purpose Speech Summarization 4145 <br> 4146 <span class="w3-text w3-text-theme"> 4147 Wonjune Kang, Deb Roy 4148 </span> 4149 </p> 4150 </a> 4151 <a class="w3-text" href="leduc24_interspeech.html"> 4152 <p> 4153 Real-time Speech Summarization for Medical Conversations 4154 <br> 4155 <span class="w3-text w3-text-theme"> 4156 Khai Le-Duc, Khai-Nguyen Nguyen, Long Vo-Dang, Truong-Son Hy 4157 </span> 4158 </p> 4159 </a> 4160 </div> 4161 </div> 4162 <br> 4163 <div class="w3-content" style="height:10px" id="Speech and Language in Health: from Remote Monitoring to Medical Conversations - 2 (Special Sessions)"></div> 4164 <div class="w3-card w3-round w3-white w3-padding"> 4165 <div class="w3-container" style="margin-top:40px"> 4166 <h4 class="w3-center">Speech and Language in Health: from Remote Monitoring to Medical Conversations - 2 (Special Sessions)</h4> 4167 <hr> 4168 <a class="w3-text" href="escobargrisales24_interspeech.html"> 4169 <p> 4170 Itâs Time to Take Action: Acoustic Modeling of Motor Verbs to Detect Parkinsonâs Disease 4171 <br>
4172 <span class="w3-text w3-text-theme"> 4173 Daniel Escobar-Grisales, Cristian David RÃos-Urrego, Ilja Baumann, Korbinian Riedhammer, Elmar Noeth, Tobias Bocklet, Adolfo M. Garcia, Juan Rafael Orozco-Arroyave 4174 </span> 4175 </p> 4176 </a> 4177 <a class="w3-text" href="maisonneuve24_interspeech.html"> 4178 <p> 4179 Towards objective and interpretable speech disorder assessment: a comparative analysis of CNN and transformer-based models 4180 <br> 4181 <span class="w3-text w3-text-theme"> 4182 Malo Maisonneuve, Corinne Fredouille, Muriel Lalain, Alain Ghio, Virginie Woisard 4183 </span> 4184 </p> 4185 </a> 4186 <a class="w3-text" href="botelho24_interspeech.html"> 4187 <p> 4188 Macro-descriptors for Alzheimer's disease detection using large language models 4189 <br> 4190 <span class="w3-text w3-text-theme"> 4191 Catarina Botelho, John Mendonça, Anna Pompili, Tanja Schultz, Alberto Abad, Isabel Trancoso 4192 </span> 4193 </p> 4194 </a> 4195 <a class="w3-text" href="braun24_interspeech.html"> 4196 <p> 4197 Infusing Acoustic Pause Context into Text-Based Dementia Assessment 4198 <br> 4199 <span class="w3-text w3-text-theme"> 4200 Franziska Braun, Sebastian P. Bayerl, Florian Hönig, Hartmut Lehfeld, Thomas Hillemacher, Tobias Bocklet, Korbinian Riedhammer 4201 </span> 4202 </p> 4203 </a> 4204 <a class="w3-text" href="roesler24_interspeech.html"> 4205 <p> 4206 Towards Scalable Remote Assessment of Mild Cognitive Impairment Via Multimodal Dialog 4207 <br> 4208 <span class="w3-text w3-text-theme"> 4209 Oliver Roesler, Jackson Liscombe, Michael Neumann, Hardik Kothare, Abhishek Hosamath, Lakshmi Arbatti, Doug Habberstad, Christiane Suendermann-Oeft, Meredith Bartlett, Cathy Zhang, Nikhil Sukhdev, Kolja Wilms, Anusha Badathala, Sandrine Istas, Steve Ruhmel, Bryan Hansen, Madeline Hannan, David Henley, Arthur Wallace, Ira Shoulson, David Suendermann-Oeft, Vikram Ramanarayanan 4210 </span> 4211 </p> 4212 </a> 4213 <a class="w3-text" href="barberis24_interspeech.html"> 4214 <p> 4215 Automatic recognition and detection of aphasic natural speech 4216 <br> 4217 <span class="w3-text w3-text-theme"> 4218 Mara Barberis, Pieter De Clercq, Bastiaan Tamm, Hugo Van hamme, Maaike Vandermosten 4219 </span> 4220 </p> 4221 </a> 4222 <a class="w3-text" href="sanguedolce24_interspeech.html"> 4223 <p> 4224 When Whisper Listens to Aphasia: Advancing Robust Post-Stroke Speech Recognition 4225 <br> 4226 <span class="w3-text w3-text-theme"> 4227 Giulia Sanguedolce, Sophie Brook, Dragos C. Gruia, Patrick A. Naylor, Fatemeh Geranmayeh 4228 </span> 4229 </p> 4230 </a> 4231 <a class="w3-text" href="wang24e_interspeech.html"> 4232 <p> 4233 Automatic Prediction of Amyotrophic Lateral Sclerosis Progression using Longitudinal Speech Transformer 4234 <br>
4235 <span class="w3-text w3-text-theme"> 4236 Liming Wang, Yuan Gong, Nauman Dawalatabad, Marco Vilela, Katerina Placek, Brian Tracey, Yishu Gong, Alan Premasiri, Fernando Vieira, James Glass 4237 </span> 4238 </p> 4239 </a> 4240 <a class="w3-text" href="kothare24_interspeech.html"> 4241 <p> 4242 How Consistent are Speech-Based Biomarkers in Remote Tracking of ALS Disease Progression Across Languages? A Case Study of English and Dutch 4243 <br> 4244 <span class="w3-text w3-text-theme"> 4245 Hardik Kothare, Michael Neumann, Cathy Zhang, Jackson Liscombe, Jordi W J van Unnik, Lianne C M Botman, Leonard H van den Berg, Ruben P A van Eijk, Vikram Ramanarayanan 4246 </span> 4247 </p> 4248 </a> 4249 <a class="w3-text" href="spiesberger24_interspeech.html"> 4250 <p> 4251 âSo . . . my child . . . â â How Child ADHD Influences the Way Parents Talk 4252 <br> 4253 <span class="w3-text w3-text-theme"> 4254 Anika A. Spiesberger, Andreas Triantafyllopoulos, Alexander Kathan, Anastasia Semertzidou, Caterina Gawrilow, Tilman Reinelt, Wolfgang A. Rauch, Björn Schuller 4255 </span> 4256 </p> 4257 </a> 4258 <a class="w3-text" href="dineley24_interspeech.html"> 4259 <p> 4260 Variability of speech timing features across repeated recordings: a comparison of open-source extraction techniques 4261 <br> 4262 <span class="w3-text w3-text-theme"> 4263 Judith Dineley, Ewan Carr, Lauren L. White, Catriona Lucas, Zahia Rahman, Tian Pan, Faith Matcham, Johnny Downs, Richard J. Dobson, Thomas F. Quatieri, Nicholas Cummins 4264 </span> 4265 </p> 4266 </a> 4267 <a class="w3-text" href="labrak24_interspeech.html"> 4268 <p> 4269 Zero-Shot End-To-End Spoken Question Answering In Medical Domain 4270 <br> 4271 <span class="w3-text w3-text-theme"> 4272 Yanis Labrak, Adel Moumen, Richard Dufour, Mickael Rouvier 4273 </span> 4274 </p> 4275 </a> 4276 <a class="w3-text" href="jiang24b_interspeech.html"> 4277 <p> 4278 Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition 4279 <br> 4280 <span class="w3-text w3-text-theme"> 4281 Yicong Jiang, Tianzi Wang, Xurong Xie, Juan Liu, Wei Sun, Nan Yan, Hui Chen, Lan Wang, Xunying Liu, Feng Tian 4282 </span> 4283 </p> 4284 </a> 4285 </div> 4286 </div> 4287 <br> 4288 <div class="w3-content" style="height:10px" id="Show and Tell 2"></div> 4289 <div class="w3-card w3-round w3-white w3-padding"> 4290 <div class="w3-container" style="margin-top:40px"> 4291 <h4 class="w3-center">Show and Tell 2</h4> 4292 <hr> 4293 <a class="w3-text" href="v24_interspeech.html"> 4294 <p> 4295 Custom wake word detection 4296 <br>
4297 <span class="w3-text w3-text-theme"> 4298 Kesavaraj V, Charan Devarkonda, Vamshiraghusimha Narasinga, Anil Kumar Vuppala 4299 </span> 4300 </p> 4301 </a> 4302 <a class="w3-text" href="chen24z_interspeech.html"> 4303 <p> 4304 Edged based audio-visual speech enhancement demonstrator 4305 <br> 4306 <span class="w3-text w3-text-theme"> 4307 Song Chen, Mandar Gogate, Kia Dashtipour, Jasper Kirton-Wingate, Adeel Hussain, Faiyaz Doctor, Tughrul Arslan, Amir Hussain 4308 </span> 4309 </p> 4310 </a> 4311 <a class="w3-text" href="anway24_interspeech.html"> 4312 <p> 4313 Real-Time Gaze-directed speech enhancement for audio-visual hearing-aids 4314 <br> 4315 <span class="w3-text w3-text-theme"> 4316 Arif Reza Anway, Bryony Buck, Mandar Gogate, Kia Dashtipour, Michael Akeroyd, Amir Hussain 4317 </span> 4318 </p> 4319 </a> 4320 <a class="w3-text" href="kumar24c_interspeech.html"> 4321 <p> 4322 Detection of background agents speech in contact centers 4323 <br> 4324 <span class="w3-text w3-text-theme"> 4325 Abhishek Kumar, Srikanth Konjeti, Jithendra Vepa 4326 </span> 4327 </p> 4328 </a> 4329 <a class="w3-text" href="koilakuntla24_interspeech.html"> 4330 <p> 4331 Leveraging large language models for post-transcription correction in contact centers 4332 <br> 4333 <span class="w3-text w3-text-theme"> 4334 Bramhendra Koilakuntla, Prajesh Rana, Paras Ahuja, Srikanth Konjeti, Jithendra Vepa 4335 </span> 4336 </p> 4337 </a> 4338 <a class="w3-text" href="schade24_interspeech.html"> 4339 <p> 4340 Understanding âunderstandingâ: presenting a richly annotated multimodal corpus of dyadic interaction 4341 <br> 4342 <span class="w3-text w3-text-theme"> 4343 Leonie Schade, Nico Dallmann, Olcay Tük, Stefan Lazarov, Petra Wagner 4344 </span> 4345 </p> 4346 </a> 4347 <a class="w3-text" href="possamaidemenezes24_interspeech.html"> 4348 <p> 4349 A demonstrator for articulation-based command word recognition 4350 <br> 4351 <span class="w3-text w3-text-theme"> 4352 Joao Vitor Possamai de Menezes, Arne-Lukas Fietkau, Tom Diener, Steffen Kurbis, Peter Birkholz 4353 </span> 4354 </p> 4355 </a> 4356 <a class="w3-text" href="ward24b_interspeech.html"> 4357 <p> 4358 Pragmatically similar utterance finder demonstration 4359 <br> 4360 <span class="w3-text w3-text-theme"> 4361 Nigel G. Ward, Andres Segura 4362 </span> 4363 </p> 4364 </a> 4365 <a class="w3-text" href="liu24s_interspeech.html"> 4366 <p> 4367 Real-time scheme for rapid extraction of speaker embeddings in challenging recording conditions 4368 <br>
4369 <span class="w3-text w3-text-theme"> 4370 Kai Liu, Ziqing Du, Zhou Huan, Xucheng Wan, Naijun Zheng 4371 </span> 4372 </p> 4373 </a> 4374 <a class="w3-text" href="chen24aa_interspeech.html"> 4375 <p> 4376 TEEMI: a speaking practice tool for L2 English learners 4377 <br> 4378 <span class="w3-text w3-text-theme"> 4379 Szu-Yu Chen, Tien-Hong Lo, Yao-Ting Sung, Ching-Yu Tseng, Berlin Chen 4380 </span> 4381 </p> 4382 </a> 4383 </div> 4384 </div> 4385 <br> 4386 <div class="w3-content" style="height:10px" id="Prosody"></div> 4387 <div class="w3-card w3-round w3-white w3-padding"> 4388 <div class="w3-container" style="margin-top:40px"> 4389 <h4 class="w3-center">Prosody</h4> 4390 <hr> 4391 <a class="w3-text" href="hu24b_interspeech.html"> 4392 <p> 4393 Automatic pitch accent classification through image classification 4394 <br> 4395 <span class="w3-text w3-text-theme"> 4396 Na Hu, Hugo Schnack, Amalia Arvaniti 4397 </span> 4398 </p> 4399 </a> 4400 <a class="w3-text" href="geng24_interspeech.html"> 4401 <p> 4402 Form and Function in Prosodic Representation: In the Case of 'ma' in Tianjin Mandarin 4403 <br> 4404 <span class="w3-text w3-text-theme"> 4405 Tianqi Geng, Hui Feng 4406 </span> 4407 </p> 4408 </a> 4409 <a class="w3-text" href="chakraborty24_interspeech.html"> 4410 <p> 4411 On Comparing Time- and Frequency-Domain Rhythm Measures in Classifying Assamese Dialects 4412 <br> 4413 <span class="w3-text w3-text-theme"> 4414 Joyshree Chakraborty, Leena Dihingia, Priyankoo Sarmah, Rohit Sinha 4415 </span> 4416 </p> 4417 </a> 4418 <a class="w3-text" href="riegger24_interspeech.html"> 4419 <p> 4420 The prosody of the verbal prefix ge-: historical and experimental evidence 4421 <br> 4422 <span class="w3-text w3-text-theme"> 4423 Chiara Riegger, Tina Bögel, George Walkden 4424 </span> 4425 </p> 4426 </a> 4427 <a class="w3-text" href="wu24n_interspeech.html"> 4428 <p> 4429 Influences of Morphosyntax and Semantics on the Intonation of Mandarin Chinese Wh-indeterminates 4430 <br> 4431 <span class="w3-text w3-text-theme"> 4432 Hongchen Wu, Jiwon Yun 4433 </span> 4434 </p> 4435 </a> 4436 <a class="w3-text" href="mumtaz24_interspeech.html"> 4437 <p> 4438 Urdu Alternative Questions: A Hat Pattern 4439 <br>
4440 <span class="w3-text w3-text-theme"> 4441 Benazir Mumtaz, Miriam Butt 4442 </span> 4443 </p> 4444 </a> 4445 </div> 4446 </div> 4447 <br> 4448 <div class="w3-content" style="height:10px" id="Foundational Models for Deepfake and Spoofed Speech Detection"></div> 4449 <div class="w3-card w3-round w3-white w3-padding"> 4450 <div class="w3-container" style="margin-top:40px"> 4451 <h4 class="w3-center">Foundational Models for Deepfake and Spoofed Speech Detection</h4> 4452 <hr> 4453 <a class="w3-text" href="tran24_interspeech.html"> 4454 <p> 4455 Spoofed Speech Detection with a Focus on Speaker Embedding 4456 <br> 4457 <span class="w3-text w3-text-theme"> 4458 Hoan My Tran, David Guennec, Philippe Martin, Aghilas Sini, Damien Lolive, Arnaud Delhay, Pierre-François Marteau 4459 </span> 4460 </p> 4461 </a> 4462 <a class="w3-text" href="martindonas24_interspeech.html"> 4463 <p> 4464 Exploring Self-supervised Embeddings and Synthetic Data Augmentation for Robust Audio Deepfake Detection 4465 <br> 4466 <span class="w3-text w3-text-theme"> 4467 Juan M. MartÃn-Doñas, Aitor Ãlvarez, Eros Rosello, Angel M. Gomez, Antonio M. Peinado 4468 </span> 4469 </p> 4470 </a> 4471 <a class="w3-text" href="pan24c_interspeech.html"> 4472 <p> 4473 Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection 4474 <br> 4475 <span class="w3-text w3-text-theme"> 4476 Zihan Pan, Tianchi Liu, Hardik B. Sailor, Qiongqiong Wang 4477 </span> 4478 </p> 4479 </a> 4480 <a class="w3-text" href="wu24c_interspeech.html"> 4481 <p> 4482 Adapter Learning from Pre-trained Model for Robust Spoof Speech Detection 4483 <br> 4484 <span class="w3-text w3-text-theme"> 4485 Haochen Wu, Wu Guo, Shengyu Peng, Zhuhai Li, Jie Zhang 4486 </span> 4487 </p> 4488 </a> 4489 <a class="w3-text" href="liu24b_interspeech.html"> 4490 <p> 4491 Speech Formants Integration for Generalized Detection of Synthetic Speech Spoofing Attacks 4492 <br> 4493 <span class="w3-text w3-text-theme"> 4494 Kexu Liu, Yuanxin Wang, Shengchen Li, Xi Shao 4495 </span> 4496 </p> 4497 </a> 4498 <a class="w3-text" href="doan24_interspeech.html"> 4499 <p> 4500 Balance, Multiple Augmentation, and Re-synthesis: A Triad Training Strategy for Enhanced Audio Deepfake Detection 4501 <br> 4502 <span class="w3-text w3-text-theme"> 4503 Thien-Phuc Doan, Long Nguyen-Vu, Kihun Hong, Souhwan Jung 4504 </span> 4505 </p> 4506 </a> 4507 </div> 4508 </div> 4509 <br> 4510 <div class="w3-content" style="height:10px" id="Speaker Recognition 1"></div> 4511 <div class="w3-card w3-round w3-white w3-padding"> 4512 <div class="w3-container" style="margin-top:40px"> 4513 <h4 class="w3-center">Speaker Recognition 1</h4> 4514 <hr> 4515 <a class="w3-text" href="peng24_interspeech.html"> 4516 <p> 4517 Fine-tune Pre-Trained Models with Multi-Level Feature Fusion for Speaker Verification 4518 <br>
4519 <span class="w3-text w3-text-theme"> 4520 Shengyu Peng, Wu Guo, Haochen Wu, Zuoliang Li, Jie Zhang 4521 </span> 4522 </p> 4523 </a> 4524 <a class="w3-text" href="yu24_interspeech.html"> 4525 <p> 4526 Speaker Conditional Sinc-Extractor for Personal VAD 4527 <br> 4528 <span class="w3-text w3-text-theme"> 4529 En-Lun Yu, Kuan-Hsun Ho, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen 4530 </span> 4531 </p> 4532 </a> 4533 <a class="w3-text" href="liou24_interspeech.html"> 4534 <p> 4535 Enhancing ECAPA-TDNN with Feature Processing Module and Attention Mechanism for Speaker Verification 4536 <br> 4537 <span class="w3-text w3-text-theme"> 4538 Shiu-Hsiang Liou, Po-Cheng Chan, Chia-Ping Chen, Tzu-Chieh Lin, Chung-Li Lu, Yu-Han Cheng, Hsiang-Feng Chuang, Wei-Yu Chen 4539 </span> 4540 </p> 4541 </a> 4542 <a class="w3-text" href="kim24j_interspeech.html"> 4543 <p> 4544 MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms 4545 <br> 4546 <span class="w3-text w3-text-theme"> 4547 Seung-bin Kim, Chan-yeong Lim, Jungwoo Heo, Ju-ho Kim, Hyun-seo Shin, Kyo-Won K
4547oo, Ha-Jin Yu 4548 </span> 4549 </p> 4550 </a> 4551 <a class="w3-text" href="nam24b_interspeech.html"> 4552 <p> 4553 Disentangled Representation Learning for Environment-agnostic Speaker Recognition 4554 <br> 4555 <span class="w3-text w3-text-theme"> 4556 KiHyun Nam, Hee-Soo Heo, Jee-weon Jung, Joonson Chung 4557 </span> 4558 </p> 4559 </a> 4560 <a class="w3-text" href="mosner24_interspeech.html"> 4561 <p> 4562 Multi-Channel Extension of Pre-trained Models for Speaker Verification 4563 <br> 4564 <span class="w3-text w3-text-theme"> 4565 Ladislav MoÅ¡ner, Romain Serizel, Lukáš Burget, OldÅich Plchot, Emmanuel Vincent, Junyi Peng, Jan Äernocký 4566 </span> 4567 </p> 4568 </a> 4569 <a class="w3-text" href="li24la_interspeech.html"> 4570 <p> 4571 Efficient Integrated Features Based on Pre-trained Models for Speaker Verification 4572 <br> 4573 <span class="w3-text w3-text-theme"> 4574 Yishuang Li, Wenhao Guan, Hukai Huang, Shiyu Miao, Qi Su, Lin Li, Qingyang Hong 4575 </span> 4576 </p> 4577 </a> 4578 <a class="w3-text" href="wang24ma_interspeech.html"> 4579 <p> 4580 SE/BN Adapter: Parametric Efficient Domain Adaptation for Speaker Recognition 4581 <br> 4582 <span class="w3-text w3-text-theme"> 4583 Tianhao Wang, Lantian Li, Dong Wang 4584 </span> 4585 </p> 4586 </a> 4587 <a class="w3-text" href="xie24b_interspeech.html"> 4588 <p> 4589 DB-PMAE: Dual-Branch Prototypical Masked AutoEncoder with locality for domain robust speaker verification 4590 <br> 4591 <span class="w3-text w3-text-theme"> 4592 Wei-lin Xie, Yu-Xuan Xi, Yan Song, Jian-tao Zhang, Hao-yu Song, Ian McLoughlin 4593 </span> 4594 </p> 4595 </a> 4596 <a class="w3-text" href="maciejewski24_interspeech.html"> 4597 <p> 4598 Evaluating the Santa Barbara Corpus: Challenges of the Breadth of Conversational Spoken Language 4599 <br> 4600 <span class="w3-text w3-text-theme"> 4601 Matthew Maciejewski, Dominik Klement, Ruizhe Huang, Matthew Wiesner, Sanjeev Khudanpur 4602 </span> 4603 </p> 4604 </a> 4605 <a class="w3-text" href="zhou24f_interspeech.html"> 4606 <p> 4607 A Comprehensive Investigation on Speaker Augmentation for Speaker Recognition 4608 <br> 4609 <span class="w3-text w3-text-theme"> 4610 Zhenyu Zhou, Shibiao Xu, Shi Yin, Lantian Li, Dong Wang 4611 </span> 4612 </p> 4613 </a> 4614 </div> 4615 </div> 4616 <br> 4617 <div class="w3-content" style="height:10px" id="Source Separation 1"></div> 4618 <div class="w3-card w3-round w3-white w3-padding"> 4619 <div class="w3-container" style="margin-top:40px"> 4620 <h4 class="w3-center">Source Separation 1</h4> 4621 <hr> 4622 <a class="w3-text" href="wang24i_interspeech.html"> 4623 <p> 4624 Noise-robust Speech Separation with Fast Generative Correction 4625 <br>
4626 <span class="w3-text w3-text-theme"> 4627 Helin Wang, Jesús Villalba, Laureano Moro-Velazquez, Jiarui Hai, Thomas Thebaud, Najim Dehak 4628 </span> 4629 </p> 4630 </a> 4631 <a class="w3-text" href="hartanto24_interspeech.html"> 4632 <p> 4633 MSDET: Multitask Speaker Separation and Direction-of-Arrival Estimation Training 4634 <br> 4635 <span class="w3-text w3-text-theme"> 4636 Roland Hartanto, Sakriani Sakti, Koichi Shinoda 4637 </span> 4638 </p> 4639 </a> 4640 <a class="w3-text" href="kealey24_interspeech.html"> 4641 <p> 4642 Unsupervised Improved MVDR Beamforming for Sound Enhancement 4643 <br> 4644 <span class="w3-text w3-text-theme"> 4645 Jacob Kealey, John R. Hershey, François Grondin 4646 </span> 4647 </p> 4648 </a> 4649 <a class="w3-text" href="chen24h_interspeech.html"> 4650 <p> 4651 Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation 4652 <br> 4653 <span class="w3-text w3-text-theme"> 4654 Ke Chen, Jiaqi Su, Taylor Berg-Kirkpatrick, Shlomo Dubnov, Zeyu Jin 4655 </span> 4656 </p> 4657 </a> 4658 <a class="w3-text" href="kim24m_interspeech.html"> 4659 <p> 4660 Enhanced Deep Speech Separation in Clustered Ad Hoc Distributed Microphone Environments 4661 <br> 4662 <span class="w3-text w3-text-theme"> 4663 Jihyun Kim, Stijn Kindt, Nilesh Madhu, Hong-Goo Kang 4664 </span> 4665 </p> 4666 </a> 4667 <a class="w3-text" href="yip24_interspeech.html"> 4668 <p> 4669 Towards Audio Codec-based Speech Separation 4670 <br> 4671 <span class="w3-text w3-text-theme"> 4672 Jia Qi Yip, Shengkui Zhao, Dianwen Ng, Eng Siong Chng, Bin Ma 4673 </span> 4674 </p> 4675 </a> 4676 </div> 4677 </div> 4678 <br> 4679 <div class="w3-content" style="height:10px" id="Audio-Visual and Generative Speech Enhancement"></div> 4680 <div class="w3-card w3-round w3-white w3-padding"> 4681 <div class="w3-container" style="margin-top:40px"> 4682 <h4 class="w3-center">Audio-Visual and Generative Speech Enhancement</h4> 4683 <hr> 4684 <a class="w3-text" href="li24d_interspeech.html"> 4685 <p> 4686 Locally Aligned Rectified Flow Model for Speech Enhancement Towards Single-Step Diffusion 4687 <br> 4688 <span class="w3-text w3-text-theme"> 4689 Zhengxiao Li, Nakamasa Inoue 4690 </span> 4691 </p> 4692 </a> 4693 <a class="w3-text" href="wang24m_interspeech.html"> 4694 <p> 4695 Diffusion Gaussian Mixture Audio Denoise 4696 <br>
4697 <span class="w3-text w3-text-theme"> 4698 Pu Wang, Junhui Li, Jialu Li, Liangdong Guo, Youshan Zhang 4699 </span> 4700 </p> 4701 </a> 4702 <a class="w3-text" href="lay24_interspeech.html"> 4703 <p> 4704 An Analysis of the Variance of Diffusion-based Speech Enhancement 4705 <br> 4706 <span class="w3-text w3-text-theme"> 4707 Bunlong Lay, Timo Gerkmann 4708 </span> 4709 </p> 4710 </a> 4711 <a class="w3-text" href="jung24b_interspeech.html"> 4712 <p> 4713 FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching 4714 <br> 4715 <span class="w3-text w3-text-theme"> 4716 Chaeyoung Jung, Suyeon Lee, Ji-Hoon Kim, Joon Son Chung 4717 </span> 4718 </p> 4719 </a> 4720 <a class="w3-text" href="chen24g_interspeech.html"> 4721 <p> 4722 RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement 4723 <br> 4724 <span class="w3-text w3-text-theme"> 4725 Honglie Chen, Rodrigo Mira, Stavros Petridis, Maja Pantic 4726 </span> 4727 </p> 4728 </a> 4729 <a class="w3-text" href="li24m_interspeech.html"> 4730 <p> 4731 Complex Image-Generative Diffusion Transformer for Audio Denoising 4732 <br> 4733 <span class="w3-text w3-text-theme"> 4734 Junhui Li, Pu Wang, Jialu Li, Youshan Zhang 4735 </span> 4736 </p> 4737 </a> 4738 <a class="w3-text" href="hu24c_interspeech.html"> 4739 <p> 4740 Noise-aware Speech Enhancement using Diffusion Probabilistic Model 4741 <br> 4742 <span class="w3-text w3-text-theme"> 4743 Yuchen Hu, Chen Chen, Ruizhe Li, Qiushi Zhu, Eng Siong Chng 4744 </span> 4745 </p> 4746 </a> 4747 </div> 4748 </div> 4749 <br> 4750 <div class="w3-content" style="height:10px" id="Speech Privacy and Bandwidth Expansion"></div> 4751 <div class="w3-card w3-round w3-white w3-padding"> 4752 <div class="w3-container" style="margin-top:40px"> 4753 <h4 class="w3-center">Speech Privacy and Bandwidth Expansion</h4> 4754 <hr> 4755 <a class="w3-text" href="vali24_interspeech.html"> 4756 <p> 4757 Privacy PORCUPINE: Anonymization of Speaker Attributes Using Occurrence Normalization for Space-Filling Vector Quantization 4758 <br> 4759 <span class="w3-text w3-text-theme"> 4760 Mohammad Hassan Vali, Tom Bäckström 4761 </span> 4762 </p> 4763 </a> 4764 <a class="w3-text" href="singh24_interspeech.html"> 4765 <p> 4766 SilentCipher: Deep Audio Watermarking 4767 <br>
4768 <span class="w3-text w3-text-theme"> 4769 Mayank Kumar Singh, Naoya Takahashi, Weihsiang Liao, Yuki Mitsufuji 4770 </span> 4771 </p> 4772 </a> 4773 <a class="w3-text" href="fan24_interspeech.html"> 4774 <p> 4775 Frequency-mix Knowledge Distillation for Fake Speech Detection 4776 <br> 4777 <span class="w3-text w3-text-theme"> 4778 Cunhang Fan, Shunbo Dong, Jun Xue, Yujie Chen, Jiangyan Yi, Zhao Lv 4779 </span> 4780 </p> 4781 </a> 4782 <a class="w3-text" href="muller24_interspeech.html"> 4783 <p> 4784 A New Approach to Voice Authenticity 4785 <br> 4786 <span class="w3-text w3-text-theme"> 4787 Nicolas M. Müller, Piotr Kawa, Shen Hu, Matthias Neu, Jennifer Williams, Philip Sperl, Konstantin Böttinger 4788 </span> 4789 </p> 4790 </a> 4791 <a class="w3-text" href="zhou24b_interspeech.html"> 4792 <p> 4793 TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking 4794 <br> 4795 <span class="w3-text w3-text-theme"> 4796 Junzuo Zhou, Jiangyan Yi, Tao Wang, Jianhua Tao, Ye Bai, Chu Yuan Zhang, Yong Ren, Zhengqi Wen 4797 </span> 4798 </p> 4799 </a> 4800 <a class="w3-text" href="liu24g_interspeech.html"> 4801 <p> 4802 HarmoNet: Partial DeepFake Detection Network based on Multi-scale HarmoF0 Feature Fusion 4803 <br> 4804 <span class="w3-text w3-text-theme"> 4805 Liwei Liu, Huihui Wei, Dongya Liu, Zhonghua Fu 4806 </span> 4807 </p> 4808 </a> 4809 <a class="w3-text" href="moussa24_interspeech.html"> 4810 <p> 4811 Unmasking Neural Codecs: Forensic Identification of AI-compressed Speech 4812 <br> 4813 <span class="w3-text w3-text-theme"> 4814 Denise Moussa, Sandra Bergmann, Christian Riess 4815 </span> 4816 </p> 4817 </a> 4818 <a class="w3-text" href="lin24c_interspeech.html"> 4819 <p> 4820 SWiBE: A Parameterized Stochastic Diffusion Process for Noise-Robust Bandwidth Expansion 4821 <br> 4822 <span class="w3-text w3-text-theme"> 4823 Yin-Tse Lin, Shreya G. Upadhyay, Bo-Hao Su, Chi-Chun Lee 4824 </span> 4825 </p> 4826 </a> 4827 <a class="w3-text" href="lu24_interspeech.html"> 4828 <p> 4829 MultiStage Speech Bandwidth Extension with Flexible Sampling Rate Control 4830 <br> 4831 <span class="w3-text w3-text-theme"> 4832 Ye-Xin Lu, Yang Ai, Zheng-Yan Sheng, Zhen-Hua Ling 4833 </span> 4834 </p> 4835 </a> 4836 <a class="w3-text" href="li24ea_interspeech.html"> 4837 <p> 4838 MaskSR: Masked Language Model for Full-band Speech Restoration 4839 <br>
4840 <span class="w3-text w3-text-theme"> 4841 Xu Li, Qirui Wang, Xiaoyu Liu 4842 </span> 4843 </p> 4844 </a> 4845 </div> 4846 </div> 4847 <br> 4848 <div class="w3-content" style="height:10px" id="Speech Synthesis: Prosody"></div> 4849 <div class="w3-card w3-round w3-white w3-padding"> 4850 <div class="w3-container" style="margin-top:40px"> 4851 <h4 class="w3-center">Speech Synthesis: Prosody</h4> 4852 <hr> 4853 <a class="w3-text" href="korotkova24_interspeech.html"> 4854 <p> 4855 Word-level Text Markup for Prosody Control in Speech Synthesis 4856 <br> 4857 <span class="w3-text w3-text-theme"> 4858 Yuliya Korotkova, Ilya Kalinovskiy, Tatiana Vakhrusheva 4859 </span> 4860 </p> 4861 </a> 4862 <a class="w3-text" href="mehta24b_interspeech.html"> 4863 <p> 4864 Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech 4865 <br> 4866 <span class="w3-text w3-text-theme"> 4867 Shivam Mehta, Harm Lameris, Rajiv Punmiya, Jonas Beskow, Eva Szekely, Gustav Eje Henter 4868 </span> 4869 </p> 4870 </a> 4871 <a class="w3-text" href="eskimez24_interspeech.html"> 4872 <p> 4873 Total-Duration-Aware Duration Modeling for Text-to-Speech Systems 4874 <br> 4875 <span class="w3-text w3-text-theme"> 4876 Sefik Emre Eskimez, Xiaofei Wang, Manthan Thakker, Chung-Hsien Tsai, Canrun Li, Zhen Xiao, Hemin Yang, Zirun Zhu, Min Tang, Jinyu Li, Sheng Zhao, Naoyuki Kanda 4877 </span> 4878 </p> 4879 </a> 4880 <a class="w3-text" href="maurya24_interspeech.html"> 4881 <p> 4882 A Human-in-the-Loop Approach to Improving Cross-Text Prosody Transfer 4883 <br> 4884 <span class="w3-text w3-text-theme"> 4885 Himanshu Maurya, Atli Sigurgeirsson 4886 </span> 4887 </p> 4888 </a> 4889 <a class="w3-text" href="jiang24d_interspeech.html"> 4890 <p> 4891 Towards Expressive Zero-Shot Speech Synthesis with Hierarchical Prosody Modeling 4892 <br> 4893 <span class="w3-text w3-text-theme"> 4894 Yuepeng Jiang, Tao Li, Fengyu Yang, Lei Xie, Meng Meng, Yujun Wang 4895 </span> 4896 </p> 4897 </a> 4898 <a class="w3-text" href="zhong24c_interspeech.html"> 4899 <p> 4900 Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of Speech-Silence and Word-Punctuation 4901 <br> 4902 <span class="w3-text w3-text-theme"> 4903 Jinzuomu Zhong, Yang Li, Hui Huang, Korin Richmond, Jie Liu, Zhiba Su, Jing Guo, Benlai Tang, Fengjie Zhu 4904 </span> 4905 </p> 4906 </a> 4907 </div> 4908 </div> 4909 <br> 4910 <div class="w3-content" style="height:10px" id="Accented Speech, Prosodic Features, Dialect, Emotion, Sound Classification"></div> 4911 <div class="w3-card w3-round w3-white w3-padding"> 4912 <div class="w3-container" style="margin-top:40px"> 4913 <h4 class="w3-center">Accented Speech, Prosodic Features, Dialect, Emotion, Sound Classification</h4> 4914 <hr> 4915 <a class="w3-text" href="prabhu24b_interspeech.html"> 4916 <p> 4917 Improving Self-supervised Pre-training using Accent-Specific Codebooks 4918 <br>
4919 <span class="w3-text w3-text-theme"> 4920 Darshan Prabhu, Abhishek Gupta, Omkar Nitsure, Preethi Jyothi, Sriram Ganapathy 4921 </span> 4922 </p> 4923 </a> 4924 <a class="w3-text" href="afonja24_interspeech.html"> 4925 <p> 4926 Performant ASR Models for Medical Entities in Accented Speech 4927 <br> 4928 <span class="w3-text w3-text-theme"> 4929 Tejumade Afonja, Tobi Olatunji, Sewade Ogun, Naome A. Etori, Abraham Owodunni, Moshood Yekini 4930 </span> 4931 </p> 4932 </a> 4933 <a class="w3-text" href="javed24_interspeech.html"> 4934 <p> 4935 LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systems 4936 <br> 4937 <span class="w3-text w3-text-theme"> 4938 Tahir Javed, Janki Nawale, Sakshi Joshi, Eldho George, Kaushal Bhogale, Deovrat Mehendale, Mitesh M. Khapra 4939 </span> 4940 </p> 4941 </a> 4942 <a class="w3-text" href="kim24v_interspeech.html"> 4943 <p> 4944 LearnerVoice: A Dataset of Non-Native English Learnersâ Spontaneous Speech 4945 <br> 4946 <span class="w3-text w3-text-theme"> 4947 Haechan Kim, Junho Myung, Seoyoung Kim, Sungpah Lee, Dongyeop Kang, Juho Kim 4948 </span> 4949 </p> 4950 </a> 4951 <a class="w3-text" href="lin24m_interspeech.html"> 4952 <p> 4953 MinSpeech: A Corpus of Southern Min Dialect for Automatic Speech Recognition 4954 <br> 4955 <span class="w3-text w3-text-theme"> 4956 Jiayan Lin, Shenghui Lu, Hukai Huang, Wenhao Guan, Binbin Xu, Hui Bu, Qingyang Hong, Lin Li 4957 </span> 4958 </p> 4959 </a> 4960 <a class="w3-text" href="hu24e_interspeech.html"> 4961 <p> 4962 Cross-modal Features Interaction-and-Aggregation Network with Self-consistency Training for Speech Emotion Recognition 4963 <br> 4964 <span class="w3-text w3-text-theme"> 4965 Ying Hu, Huamin Yang, Hao Huang, Liang He 4966 </span> 4967 </p> 4968 </a> 4969 <a class="w3-text" href="goel24_interspeech.html"> 4970 <p> 4971 Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-Attention Cues in Multitask Learning 4972 <br> 4973 <span class="w3-text w3-text-theme"> 4974 Arnav Goel, Medha Hira, Anubha Gupta 4975 </span> 4976 </p> 4977 </a> 4978 <a class="w3-text" href="bukhari24_interspeech.html"> 4979 <p> 4980 SELM: Enhancing Speech Emotion Recognition for Out-of-Domain Scenarios 4981 <br>
4982 <span class="w3-text w3-text-theme"> 4983 Hazim Bukhari, Soham Deshmukh, Hira Dhamyal, Bhiksha Raj, Rita Singh 4984 </span> 4985 </p> 4986 </a> 4987 <a class="w3-text" href="bentum24_interspeech.html"> 4988 <p> 4989 The Processing of Stress in End-to-End Automatic Speech Recognition Models 4990 <br> 4991 <span class="w3-text w3-text-theme"> 4992 Martijn Bentum, Louis ten Bosch, Tom Lentz 4993 </span> 4994 </p> 4995 </a> 4996 <a class="w3-text" href="nguyen24b_interspeech.html"> 4997 <p> 4998 LingWav2Vec2: Linguistic-augmented wav2vec 2.0 for Vietnamese Mispronunciation Detection 4999 <br> 5000 <span class="w3-text w3-text-theme"> 5001 Tuan Nguyen, Huy Dat Tran 5002 </span> 5003 </p> 5004 </a> 5005 <a class="w3-text" href="mogridge24_interspeech.html"> 5006 <p> 5007 Learning from memory-based models 5008 <br> 5009 <span class="w3-text w3-text-theme"> 5010 Rhiannon Mogridge, Anton Ragni 5011 </span> 5012 </p> 5013 </a> 5014 <a class="w3-text" href="chen24s_interspeech.html"> 5015 <p> 5016 Towards End-to-End Unified Recognition for Mandarin and Cantonese 5017 <br> 5018 <span class="w3-text w3-text-theme"> 5019 Meiling Chen, Pengjie Liu, Heng Yang, Haofeng Wang 5020 </span> 5021 </p> 5022 </a> 5023 </div> 5024 </div> 5025 <br> 5026 <div class="w3-content" style="height:10px" id="Neural Network Adaptation"></div> 5027 <div class="w3-card w3-round w3-white w3-padding"> 5028 <div class="w3-container" style="margin-top:40px"> 5029 <h4 class="w3-center">Neural Network Adaptation</h4> 5030 <hr> 5031 <a class="w3-text" href="rolland24b_interspeech.html"> 5032 <p> 5033 Shared-Adapters: A Novel Transformer-based Parameter Efficient Transfer Learning Approach For Childrenâs Automatic Speech Recognition 5034 <br> 5035 <span class="w3-text w3-text-theme"> 5036 Thomas Rolland, Alberto Abad 5037 </span> 5038 </p> 5039 </a> 5040 <a class="w3-text" href="huo24_interspeech.html"> 5041 <p> 5042 AdaRA: Adaptive Rank Allocation of Residual Adapters for Speech Foundation Model 5043 <br> 5044 <span class="w3-text w3-text-theme"> 5045 Zhouyuan Huo, Dongseong Hwang, Gan Song, Khe Chai Sim, Weiran Wang 5046 </span> 5047 </p> 5048 </a> 5049 <a class="w3-text" href="shim24_interspeech.html"> 5050 <p> 5051 Leveraging Adapter for Parameter-Efficient ASR Encoder 5052 <br>
5053 <span class="w3-text w3-text-theme"> 5054 Kyuhong Shim, Jinkyu Lee, Hyunjae Kim 5055 </span> 5056 </p> 5057 </a> 5058 <a class="w3-text" href="kang24_interspeech.html"> 5059 <p> 5060 Whisper Multilingual Downstream Task Tuning Using Task Vectors 5061 <br> 5062 <span class="w3-text w3-text-theme"> 5063 Ji-Hun Kang, Jae-Hong Lee, Mun-Hak Lee, Joon-Hyuk Chang 5064 </span> 5065 </p> 5066 </a> 5067 <a class="w3-text" href="li24ka_interspeech.html"> 5068 <p> 5069 Speaker-Smoothed kNN Speaker Adaptation for End-to-End ASR 5070 <br> 5071 <span class="w3-text w3-text-theme"> 5072 Shaojun Li, Daimeng Wei, Hengchao Shang, Jiaxin Guo, ZongYao Li, Zhanglin Wu, Zhiqiang Rao, Yuanchang Luo, Xianghui He, Hao Yang 5073 </span> 5074 </p> 5075 </a> 5076 <a class="w3-text" href="chen24n_interspeech.html"> 5077 <p> 5078 Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition 5079 <br> 5080 <span class="w3-text w3-text-theme"> 5081 Jinming Chen, Jingyi Fang, Yuanzhong Zheng, Yaoxuan Wang, Haojun Fei 5082 </span> 5083 </p> 5084 </a> 5085 </div> 5086 </div> 5087 <br> 5088 <div class="w3-content" style="height:10px" id="ASR and LLMs"></div> 5089 <div class="w3-card w3-round w3-white w3-padding"> 5090 <div class="w3-container" style="margin-top:40px"> 5091 <h4 class="w3-center">ASR and LLMs</h4> 5092 <hr> 5093 <a class="w3-text" href="yoon24_interspeech.html"> 5094 <p> 5095 HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition 5096 <br> 5097 <span class="w3-text w3-text-theme"> 5098 Ji Won Yoon, Beom Jun Woo, Nam Soo Kim 5099 </span> 5100 </p> 5101 </a> 5102 <a class="w3-text" href="yang24f_interspeech.html"> 5103 <p> 5104 MaLa-ASR: Multimedia-Assisted LLM-Based ASR 5105 <br> 5106 <span class="w3-text w3-text-theme"> 5107 Guanrou Yang, Ziyang Ma, Fan Yu, Zhifu Gao, Shiliang Zhang, Xie Chen 5108 </span> 5109 </p> 5110 </a> 5111 <a class="w3-text" href="choi24_interspeech.html"> 5112 <p> 5113 Spoken-to-written text conversion with Large Language Model 5114 <br> 5115 <span class="w3-text w3-text-theme"> 5116 HyunJung Choi, Muyeol Choi, Yohan Lim, Minkyu Lee, Seonhui Kim, Seung Yun, Donghyun Kim, SangHun Kim 5117 </span> 5118 </p> 5119 </a> 5120 <a class="w3-text" href="ai24_interspeech.html"> 5121 <p> 5122 MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting 5123 <br>
5124 <span class="w3-text w3-text-theme"> 5125 Zhiqi Ai, Zhiyong Chen, Shugong Xu 5126 </span> 5127 </p> 5128 </a> 5129 <a class="w3-text" href="rouditchenko24_interspeech.html"> 5130 <p> 5131 Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation 5132 <br> 5133 <span class="w3-text w3-text-theme"> 5134 Andrew Rouditchenko, Yuan Gong, Samuel Thomas, Leonid Karlinsky, Hilde Kuehne, Rogerio Feris, James Glass 5135 </span> 5136 </p> 5137 </a> 5138 <a class="w3-text" href="prajwal24_interspeech.html"> 5139 <p> 5140 Speech Recognition Models are Strong Lip-readers 5141 <br> 5142 <span class="w3-text w3-text-theme"> 5143 K R Prajwal, Triantafyllos Afouras, Andrew Zisserman 5144 </span> 5145 </p> 5146 </a> 5147 </div> 5148 </div> 5149 <br> 5150 <div class="w3-content" style="height:10px" id="Pathological Speech Analysis 3"></div> 5151 <div class="w3-card w3-round w3-white w3-padding"> 5152 <div class="w3-container" style="margin-top:40px"> 5153 <h4 class="w3-center">Pathological Speech Analysis 3</h4> 5154 <hr> 5155 <a class="w3-text" href="baumann24b_interspeech.html"> 5156 <p> 5157 Towards Self-Attention Understanding for Automatic Articulatory Processes Analysis in Cleft Lip and Palate Speech 5158 <br> 5159 <span class="w3-text w3-text-theme"> 5160 Ilja Baumann, Dominik Wagner, Maria Schuster, Korbinian Riedhammer, Elmar Noeth, Tobias Bocklet 5161 </span> 5162 </p> 5163 </a> 5164 <a class="w3-text" href="liu24f_interspeech.html"> 5165 <p> 5166 Clever Hans Effect Found in Automatic Detection of Alzheimer's Disease through Speech 5167 <br> 5168 <span class="w3-text w3-text-theme"> 5169 Yin-Long Liu, Rui Feng, Jia-Hong Yuan, Zhen-Hua Ling 5170 </span> 5171 </p> 5172 </a> 5173 <a class="w3-text" href="lin24k_interspeech.html"> 5174 <p> 5175 Leveraging Phonemic Transcription and Whisper toward Clinically Significant Indices for Automatic Child Speech Assessment 5176 <br> 5177 <span class="w3-text w3-text-theme"> 5178 Yeh-Sheng Lin, Shu-Chuan Tseng, Jyh-Shing Roger Jang 5179 </span> 5180 </p> 5181 </a> 5182 <a class="w3-text" href="dang24b_interspeech.html"> 5183 <p> 5184 Developing vocal system impaired patient-aimed voice quality assessment approach using ASR representation-included multiple features 5185 <br> 5186 <span class="w3-text w3-text-theme">
5187 Shaoxiang Dang, Tetsuya Matsumoto, Yoshinori Takeuchi, Takashi Tsuboi, Yasuhiro Tanaka, Daisuke Nakatsubo, Satoshi Maesawa, Ryuta Saito, Masahisa Katsuno, Hiroaki Kudo 5188 </span> 5189 </p> 5190 </a> 5191 <a class="w3-text" href="hsu24_interspeech.html"> 5192 <p> 5193 A Cluster-based Personalized Federated Learning Strategy for End-to-End ASR of Dementia Patients 5194 <br> 5195 <span class="w3-text w3-text-theme"> 5196 Wei-Tung Hsu, Chin-Po Chen, Yun-Shao Lin, Chi-Chun Lee 5197 </span> 5198 </p> 5199 </a> 5200 <a class="w3-text" href="kalabakov24_interspeech.html"> 5201 <p> 5202 A Comparative Analysis of Federated Learning for Speech-Based Cognitive Decline Detection 5203 <br> 5204 <span class="w3-text w3-text-theme"> 5205 Stefan Kalabakov, Monica Gonzalez-Machorro, Florian Eyben, Björn W. Schuller, Bert Arnrich 5206 </span> 5207 </p> 5208 </a> 5209 <a class="w3-text" href="neumann24_interspeech.html"> 5210 <p> 5211 Multimodal Digital Biomarkers for Longitudinal Tracking of Speech Impairment Severity in ALS: An Investigation of Clinically Important Differences 5212 <br> 5213 <span class="w3-text w3-text-theme"> 5214 Michael Neumann, Hardik Kothare, Jackson Liscombe, Emma C.L. Leschly, Oliver Roesler, Vikram Ramanarayanan 5215 </span> 5216 </p> 5217 </a> 5218 </div> 5219 </div> 5220 <br> 5221 <div class="w3-content" style="height:10px" id="Speech Disorders 3"></div> 5222 <div class="w3-card w3-round w3-white w3-padding"> 5223 <div class="w3-container" style="margin-top:40px"> 5224 <h4 class="w3-center">Speech Disorders 3</h4> 5225 <hr> 5226 <a class="w3-text" href="gao24c_interspeech.html"> 5227 <p> 5228 Enhancing Voice Wake-Up for Dysarthria: Mandarin Dysarthria Speech Corpus Release and Customized System Design 5229 <br> 5230 <span class="w3-text w3-text-theme"> 5231 Ming Gao, Hang Chen, Jun Du, Xin Xu, Hongxiao Guo, Hui Bu, Jianxing Yang, Ming Li, Chin-Hui Lee 5232 </span> 5233 </p> 5234 </a> 5235 <a class="w3-text" href="shah24_interspeech.html"> 5236 <p> 5237 Towards Improving NAM-to-Speech Synthesis Intelligibility using Self-Supervised Speech Models 5238 <br> 5239 <span class="w3-text w3-text-theme"> 5240 Neil Shah, Shirish Karande, Vineet Gandhi 5241 </span> 5242 </p> 5243 </a> 5244 <a class="w3-text" href="um24_interspeech.html"> 5245 <p> 5246 PARAN: Variational Autoencoder-based End-to-End Articulation-to-Speech System for Speech Intelligibility 5247 <br>
5248 <span class="w3-text w3-text-theme"> 5249 Seyun Um, Doyeon Kim, Hong-Goo Kang 5250 </span> 5251 </p> 5252 </a> 5253 <a class="w3-text" href="chen24b_interspeech.html"> 5254 <p> 5255 Acoustic changes in speech prosody produced by children with autism after robot-assisted speech training 5256 <br> 5257 <span class="w3-text w3-text-theme"> 5258 Si Chen, Bruce Xiao Wang, Yitian Hong, Fang Zhou, Angel Chan, Po-yi Tang, Bin Li, Chunyi Wen, James Cheung, Yan Liu, Zhuoming Chen 5259 </span> 5260 </p> 5261 </a> 5262 <a class="w3-text" href="zheng24c_interspeech.html"> 5263 <p> 5264 Fine-Tuning Automatic Speech Recognition for People with Parkinson's: An Effective Strategy for Enhancing Speech Technology Accessibility 5265 <br> 5266 <span class="w3-text w3-text-theme"> 5267 Xiuwen Zheng, Bornali Phukon, Mark Hasegawa-Johnson 5268 </span> 5269 </p> 5270 </a> 5271 <a class="w3-text" href="jiang24_interspeech.html"> 5272 <p> 5273 Learnings from curating a trustworthy, well-annotated, and useful dataset of disordered English speech 5274 <br> 5275 <span class="w3-text w3-text-theme"> 5276 Pan-Pan Jiang, Jimmy Tobin, Katrin Tomanek, Robert MacDonald, Katie Seaver, Richard Cave, Marilyn Ladewig, Rus Heywood, Jordan Green 5277 </span> 5278 </p> 5279 </a> 5280 <a class="w3-text" href="leung24_interspeech.html"> 5281 <p> 5282 Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis 5283 <br> 5284 <span class="w3-text w3-text-theme"> 5285 Wing-Zin Leung, Mattias Cross, Anton Ragni, Stefan Goetze 5286 </span> 5287 </p> 5288 </a> 5289 <a class="w3-text" href="gosztolya24b_interspeech.html"> 5290 <p> 5291 Wav2vec 2.0 Embeddings Are No Swiss Army Knife -- A Case Study for Multiple Sclerosis 5292 <br> 5293 <span class="w3-text w3-text-theme"> 5294 Gábor Gosztolya, Mercedes Vetráb, Veronika Svindt, Judit Bóna, Ildikó Hoffmann 5295 </span> 5296 </p> 5297 </a> 5298 </div> 5299 </div> 5300 <br> 5301 <div class="w3-content" style="height:10px" id="Speech Recognition with Large Pretrained Speech Models for Under-represented Languages (Special Session)"></div> 5302 <div class="w3-card w3-round w3-white w3-padding"> 5303 <div class="w3-container" style="margin-top:40px"> 5304 <h4 class="w3-center">Speech Recognition with Large Pretrained Speech Models for Under-represented Languages (Special Session)</h4> 5305 <hr> 5306 <a class="w3-text" href="shih24_interspeech.html"> 5307 <p> 5308 Interface Design for Self-Supervised Speech Models 5309 <br>
5310 <span class="w3-text w3-text-theme"> 5311 Yi-Jen Shih, David Harwath 5312 </span> 5313 </p> 5314 </a> 5315 <a class="w3-text" href="xu24d_interspeech.html"> 5316 <p> 5317 Comparing Discrete and Continuous Space LLMs for Speech Recognition 5318 <br> 5319 <span class="w3-text w3-text-theme"> 5320 Yaoxun Xu, Shi-Xiong Zhang, Jianwei Yu, Zhiyong Wu, Dong Yu 5321 </span> 5322 </p> 5323 </a> 5324 <a class="w3-text" href="li24ia_interspeech.html"> 5325 <p> 5326 Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text 5327 <br> 5328 <span class="w3-text w3-text-theme"> 5329 Jinpeng Li, Yu Pu, Qi Sun, Wei-Qiang Zhang 5330 </span> 5331 </p> 5332 </a> 5333 <a class="w3-text" href="bhogale24_interspeech.html"> 5334 <p> 5335 Empowering Low-Resource Language ASR via Large-Scale Pseudo Labeling 5336 <br> 5337 <span class="w3-text w3-text-theme"> 5338 Kaushal Santosh Bhogale, Deovrat Mehendale, Niharika Parasa, Sathish Kumar Reddy G, Tahir Javed, Pratyush Kumar, Mitesh M. Khapra 5339 </span> 5340 </p> 5341 </a> 5342 <a class="w3-text" href="li24i_interspeech.html"> 5343 <p> 5344 Interleaved Audio/Audiovisual Transfer Learning for AV-ASR in Low-Resourced Languages 5345 <br> 5346 <span class="w3-text w3-text-theme"> 5347 Zhengyang Li, Patrick Blumenberg, Jing Liu, Thomas Graave, Timo Lohrenz, Siegfried Kunzmann, Tim Fingscheidt 5348 </span> 5349 </p> 5350 </a> 5351 <a class="w3-text" href="udupa24_interspeech.html"> 5352 <p> 5353 Adapter pre-training for improved speech recognition in unseen domains using low resource adapter tuning of self-supervised models 5354 <br> 5355 <span class="w3-text w3-text-theme"> 5356 Sathvik Udupa, Jesuraj Bandekar, Saurabh Kumar, Deekshitha G, Sandhya B, Abhayjeet S, Savitha Murthy, Priyanka Pai, Srinivasa Raghavan, Raoul Nanavati, Prasanta Kumar Ghosh 5357 </span> 5358 </p> 5359 </a> 5360 <a class="w3-text" href="xu24h_interspeech.html"> 5361 <p> 5362 Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper 5363 <br> 5364 <span class="w3-text w3-text-theme"> 5365 Tianyi Xu, Kaixun Huang, Pengcheng Guo, Yu Zhou, Longtao Huang, Hui Xue, Lei Xie 5366 </span> 5367 </p> 5368 </a> 5369 <a class="w3-text" href="getman24b_interspeech.html"> 5370 <p> 5371 Exploring adaptation techniques of large speech foundation models for low-resource ASR: a case study on Northern Sámi 5372 <br>
5373 <span class="w3-text w3-text-theme"> 5374 Yaroslav Getman, Tamas Grosz, Katri Hiovain-Asikainen, Mikko Kurimo 5375 </span> 5376 </p> 5377 </a> 5378 <a class="w3-text" href="qian24_interspeech.html"> 5379 <p> 5380 Learn and Don't Forget: Adding a New Language to ASR Foundation Models 5381 <br> 5382 <span class="w3-text w3-text-theme"> 5383 Mengjie Qian, Siyuan Tang, Rao Ma, Kate M. Knill, Mark J.F. Gales 5384 </span> 5385 </p> 5386 </a> 5387 </div> 5388 </div> 5389 <br> 5390 <div class="w3-content" style="height:10px" id="Speech Processing Using Discrete Speech Units (Special Session)"></div> 5391 <div class="w3-card w3-round w3-white w3-padding"> 5392 <div class="w3-container" style="margin-top:40px"> 5393 <h4 class="w3-center">Speech Processing Using Discrete Speech Units (Special Session)</h4> 5394 <hr> 5395 <a class="w3-text" href="wu24q_interspeech.html"> 5396 <p> 5397 TokSing: Singing Voice Synthesis based on Discrete Tokens 5398 <br> 5399 <span class="w3-text w3-text-theme"> 5400 Yuning Wu, Chunlei Zhang, Jiatong Shi, Yuxun Tang, Shan Yang, Qin Jin 5401 </span> 5402 </p> 5403 </a> 5404 <a class="w3-text" href="mousavi24_interspeech.html"> 5405 <p> 5406 How Should We Extract Discrete Audio Tokens from Self-Supervised Models? 5407 <br> 5408 <span class="w3-text w3-text-theme"> 5409 Pooneh Mousavi, Jarod Duret, Salah Zaiem, Luca Della Libera, Artem Ploujnikov, Cem Subakan, Mirco Ravanelli 5410 </span> 5411 </p> 5412 </a> 5413 <a class="w3-text" href="chang24b_interspeech.html"> 5414 <p> 5415 The Interspeech 2024 Challenge on Speech Processing Using Discrete Units 5416 <br> 5417 <span class="w3-text w3-text-theme"> 5418 Xuankai Chang, Jiatong Shi, Jinchuan Tian, Yuning Wu, Yuxun Tang, Yihan Wu, Shinji Watanabe, Yossi Adi, Xie Chen, Qin Jin 5419 </span> 5420 </p> 5421 </a> 5422 <a class="w3-text" href="tang24c_interspeech.html"> 5423 <p> 5424 SingOMD: Singing Oriented Multi-resolution Discrete Representation Construction from Speech Models 5425 <br> 5426 <span class="w3-text w3-text-theme"> 5427 Yuxun Tang, Yuning Wu, Jiatong Shi, Qin Jin 5428 </span> 5429 </p> 5430 </a> 5431 <a class="w3-text" href="shi24h_interspeech.html"> 5432 <p> 5433 MMM: Multi-Layer Multi-Residual Multi-Stream Discrete Speech Representation from Self-supervised Learning Model 5434 <br> 5435 <span class="w3-text w3-text-theme"> 5436 Jiatong Shi, Xutai Ma, Hirofumi Inaguma, Anna Sun, Shinji Watanabe 5437 </span> 5438 </p> 5439 </a> 5440 <a class="w3-text" href="dhawan24_interspeech.html"> 5441 <p> 5442 Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations 5443 <br>
5444 <span class="w3-text w3-text-theme"> 5445 Kunal Dhawan, Nithin Rao Koluguri, Ante JukiÄ, Ryan Langman, Jagadeesh Balam, Boris Ginsburg 5446 </span> 5447 </p> 5448 </a> 5449 </div> 5450 </div> 5451 <br> 5452 <div class="w3-content" style="height:10px" id="Keynote 3"></div> 5453 <div class="w3-card w3-round w3-white w3-padding"> 5454 <div class="w3-container" style="margin-top:40px"> 5455 <h4 class="w3-center">Keynote 3</h4> 5456 <hr> 5457 <a class="w3-text" href="noeth24_interspeech.html"> 5458 <p> 5459 Analysis of Pathological Speech â Pitfalls along the Way 5460 <br> 5461 <span class="w3-text w3-text-theme"> 5462 Elmar Noeth 5463 </span> 5464 </p> 5465 </a> 5466 </div> 5467 </div> 5468 <br> 5469 <div class="w3-content" style="height:10px" id="Databases and Progress in Methodology"></div> 5470 <div class="w3-card w3-round w3-white w3-padding"> 5471 <div class="w3-container" style="margin-top:40px"> 5472 <h4 class="w3-center">Databases and Progress in Methodology</h4> 5473 <hr> 5474 <a class="w3-text" href="ahn24b_interspeech.html"> 5475 <p> 5476 VoxSim: A perceptual voice similarity dataset 5477 <br> 5478 <span class="w3-text w3-text-theme"> 5479 Junseok Ahn, Youkyum Kim, Yeunju Choi, Doyeop Kwak, Ji-Hoon Kim, Seongkyu Mun, Joon Son Chung 5480 </span> 5481 </p> 5482 </a> 5483 <a class="w3-text" href="nijat24_interspeech.html"> 5484 <p> 5485 UY/CH-CHILD -- A Public Chinese L2 Speech Database of Uyghur Children 5486 <br> 5487 <span class="w3-text w3-text-theme"> 5488 Mewlude Nijat, Chen Chen, Dong Wang, Askar Hamdulla 5489 </span> 5490 </p> 5491 </a> 5492 <a class="w3-text" href="kumar24b_interspeech.html"> 5493 <p> 5494 State-of-the-art speech production MRI protocol for new 0.55 Tesla scanners 5495 <br> 5496 <span class="w3-text w3-text-theme"> 5497 Prakash Kumar, Ye Tian, Yongwan Lim, Sophia X. Cui, Christina Hagedorn, Dani Byrd, Uttam K. Sinha, Shrikanth Narayanan, Krishna S. Nayak 5498 </span> 5499 </p> 5500 </a> 5501 <a class="w3-text" href="shi24c_interspeech.html"> 5502 <p> 5503 DBD-CI: Doubling the Band Density for Bilateral Cochlear Implants 5504 <br> 5505 <span class="w3-text w3-text-theme"> 5506 Mingyue Shi, Huali Zhou, Qinglin Meng, Nengheng Zheng 5507 </span> 5508 </p> 5509 </a> 5510 <a class="w3-text" href="zhong24b_interspeech.html"> 5511 <p> 5512 Leveraging Large Language Models to Refine Automatic Feedback Generation at Articulatory Level in Computer Aided Pronunciation Training 5513 <br>
5514 <span class="w3-text w3-text-theme"> 5515 Huihang Zhong, Yanlu Xie, ZiJin Yao 5516 </span> 5517 </p> 5518 </a> 5519 <a class="w3-text" href="zhao24e_interspeech.html"> 5520 <p> 5521 Decoding Human Language Acquisition: EEG Evidence for Predictive Probabilistic Statistics in Word Segmentation 5522 <br> 5523 <span class="w3-text w3-text-theme"> 5524 Bin Zhao, Mingxuan Huang, Chenlu Ma, Jinyi Xue, Aijun Li, Kunyu Xu 5525 </span> 5526 </p> 5527 </a> 5528 </div> 5529 </div> 5530 <br> 5531 <div class="w3-content" style="height:10px" id="Articulation, Convergence and Perception"></div> 5532 <div class="w3-card w3-round w3-white w3-padding"> 5533 <div class="w3-container" style="margin-top:40px"> 5534 <h4 class="w3-center">Articulation, Convergence and Perception</h4> 5535 <hr> 5536 <a class="w3-text" href="giroud24_interspeech.html"> 5537 <p> 5538 Behavioral evidence for higher speech rate convergence following natural than artificial time altered speech 5539 <br> 5540 <span class="w3-text w3-text-theme"> 5541 Jérémy Giroud, Jessica Lei, Kirsty Phillips, Matthew H. Davis 5542 </span> 5543 </p> 5544 </a> 5545 <a class="w3-text" href="shen24c_interspeech.html"> 5546 <p> 5547 A novel experimental design for the study of listener-to-listener convergence in phoneme categorization 5548 <br> 5549 <span class="w3-text w3-text-theme"> 5550 Qingye Shen, Leonardo Lancia, Noel Nguyen 5551 </span> 5552 </p> 5553 </a> 5554 <a class="w3-text" href="li24ga_interspeech.html"> 5555 <p> 5556 Cross-Attention-Guided WaveNet for EEG-to-MEL Spectrogram Reconstruction 5557 <br> 5558 <span class="w3-text w3-text-theme"> 5559 Hao Li, Yuan Fang, Xueliang Zhang, Fei Chen, Guanglai Gao 5560 </span> 5561 </p> 5562 </a> 5563 <a class="w3-text" href="loddo24_interspeech.html"> 5564 <p> 5565 What if HAL breathed? Enhancing Empathy in Human-AI Interactions with Breathing Speech Synthesis 5566 <br> 5567 <span class="w3-text w3-text-theme"> 5568 Nicolò Loddo, Francisca Pessanha, Almila Akdag 5569 </span> 5570 </p> 5571 </a> 5572 <a class="w3-text" href="svenssonlundmark24_interspeech.html"> 5573 <p> 5574 Magnitude and timing of acceleration peaks in stressed and unstressed syllables 5575 <br> 5576 <span class="w3-text w3-text-theme"> 5577 Malin Svensson Lundmark 5578 </span> 5579 </p> 5580 </a> 5581 </div> 5582 </div> 5583 <br> 5584 <div class="w3-content" style="height:10px" id="Speech Emotion Recognition"></div> 5585 <div class="w3-card w3-round w3-white w3-padding"> 5586 <div class="w3-container" style="margin-top:40px"> 5587 <h4 class="w3-center">Speech Emotion Recognition</h4> 5588 <hr> 5589 <a class="w3-text" href="amiriparian24_interspeech.html"> 5590 <p>
5591 ExHuBERT: Enhancing HuBERT Through Block Extension and Fine-Tuning on 37 Emotion Datasets 5592 <br> 5593 <span class="w3-text w3-text-theme"> 5594 Shahin Amiriparian, Filip PackaÅ, Maurice Gerczuk, Björn W. Schuller 5595 </span> 5596 </p> 5597 </a> 5598 <a class="w3-text" href="rittergutierrez24_interspeech.html"> 5599 <p> 5600 Dataset-Distillation Generative Model for Speech Emotion Recognition 5601 <br> 5602 <span class="w3-text w3-text-theme"> 5603 Fabian Ritter-Gutierrez, Kuan-Po Huang, Jeremy H. M. Wong, Dianwen Ng, Hung-yi Lee, Nancy F. Chen, Eng-Siong Chng 5604 </span> 5605 </p> 5606 </a> 5607 <a class="w3-text" href="mai24_interspeech.html"> 5608 <p> 5609 DropFormer: A Dynamic Noise-Dropping Transformer for Speech Emotion Recognition 5610 <br> 5611 <span class="w3-text w3-text-theme"> 5612 Jialong Mai, Xiaofen Xing, Weidong Chen, Xiangmin Xu 5613 </span> 5614 </p> 5615 </a> 5616 <a class="w3-text" href="niu24d_interspeech.html"> 5617 <p> 5618 From Text to Emotion: Unveiling the Emotion Annotation Capabilities of LLMs 5619 <br> 5620 <span class="w3-text w3-text-theme"> 5621 Minxue Niu, Mimansa Jaiswal, Emily Mower Provost 5622 </span> 5623 </p> 5624 </a> 5625 </div> 5626 </div> 5627 <br> 5628 <div class="w3-content" style="height:10px" id="Self-Supervised Models in Speaker Recognition"></div> 5629 <div class="w3-card w3-round w3-white w3-padding"> 5630 <div class="w3-container" style="margin-top:40px"> 5631 <h4 class="w3-center">Self-Supervised Models in Speaker Recognition</h4> 5632 <hr> 5633 <a class="w3-text" href="kim24c_interspeech.html"> 5634 <p> 5635 Self-supervised speaker verification with relational mask prediction 5636 <br> 5637 <span class="w3-text w3-text-theme"> 5638 Ju-ho Kim, Hee-Soo Heo, Bong-Jin Lee, Youngki Kwon, Minjae Lee, Ha-Jin Yu 5639 </span> 5640 </p> 5641 </a> 5642 <a class="w3-text" href="miara24_interspeech.html"> 5643 <p> 5644 Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models 5645 <br> 5646 <span class="w3-text w3-text-theme"> 5647 Victor Miara, Theo Lepage, Reda Dehak 5648 </span> 5649 </p> 5650 </a> 5651 <a class="w3-text" href="lim24_interspeech.html"> 5652 <p> 5653 Improving Noise Robustness in Self-supervised Pre-trained Model for Speaker Verification 5654 <br>
5655 <span class="w3-text w3-text-theme"> 5656 Chan-yeong Lim, Hyun-seo Shin, Ju-ho Kim, Jungwoo Heo, Kyo-Won Koo, Seung-bin Kim, Ha-Jin Yu 5657 </span> 5658 </p> 5659 </a> 5660 <a class="w3-text" href="fathan24_interspeech.html"> 5661 <p> 5662 On the impact of several regularization techniques on label noise robustness of self-supervised speaker verification systems 5663 <br> 5664 <span class="w3-text w3-text-theme"> 5665 Abderrahim Fathan, Xiaolin Zhu, Jahangir Alam 5666 </span> 5667 </p> 5668 </a> 5669 <a class="w3-text" href="li24e_interspeech.html"> 5670 <p> 5671 Parameter-efficient Fine-tuning of Speaker-Aware Dynamic Prompts for Speaker Verification 5672 <br> 5673 <span class="w3-text w3-text-theme"> 5674 Zhe Li, Man-wai Mak, Hung-yi Lee, Helen Meng 5675 </span> 5676 </p> 5677 </a> 5678 <a class="w3-text" href="zhao24f_interspeech.html"> 5679 <p> 5680 Whisper-PMFA: Partial Multi-Scale Feature Aggregation for Speaker Verification using Whisper Models 5681 <br> 5682 <span class="w3-text w3-text-theme"> 5683 Yiyang Zhao, Shuai Wang, Guangzhi Sun, Zehua Chen, Chao Zhang, Mingxing Xu, Thomas Fang Zheng 5684 </span> 5685 </p> 5686 </a> 5687 </div> 5688 </div> 5689 <br> 5690 <div class="w3-content" style="height:10px" id="Speech Quality Assessment"></div> 5691 <div class="w3-card w3-round w3-white w3-padding"> 5692 <div class="w3-container" style="margin-top:40px"> 5693 <h4 class="w3-center">Speech Quality Assessment</h4> 5694 <hr> 5695 <a class="w3-text" href="hu24d_interspeech.html"> 5696 <p> 5697 Embedding Learning for Preference-based Speech Quality Assessment 5698 <br> 5699 <span class="w3-text w3-text-theme"> 5700 ChengHung Hu, Yusuke Yasuda, Tomoki Toda 5701 </span> 5702 </p> 5703 </a> 5704 <a class="w3-text" href="udupa24b_interspeech.html"> 5705 <p> 5706 IndicMOS: Multilingual MOS Prediction for 7 Indian languages 5707 <br> 5708 <span class="w3-text w3-text-theme"> 5709 Sathvik Udupa, Soumi Maiti, Prasanta Kumar Ghosh 5710 </span> 5711 </p> 5712 </a> 5713 <a class="w3-text" href="wells24_interspeech.html"> 5714 <p> 5715 Experimental evaluation of MOS, AB and BWS listening test designs 5716 <br> 5717 <span class="w3-text w3-text-theme"> 5718 Dan Wells, Andrea Lorena Aldana Blanco, Cassia Valentini, Erica Cooper, Aidan Pine, Junichi Yamagishi, Korin Richmond 5719 </span> 5720 </p> 5721 </a> 5722 <a class="w3-text" href="ta24_interspeech.html"> 5723 <p> 5724 Enhancing No-Reference Speech Quality Assessment with Pairwise, Triplet Ranking Losses, and ASR Pretraining 5725 <br>
5726 <span class="w3-text w3-text-theme"> 5727 Bao Thang Ta, Minh Tu Le, Van Hai Do, Huynh Thi Thanh Binh 5728 </span> 5729 </p> 5730 </a> 5731 </div> 5732 </div> 5733 <br> 5734 <div class="w3-content" style="height:10px" id="Privacy and Security in Speech Communication 1"></div> 5735 <div class="w3-card w3-round w3-white w3-padding"> 5736 <div class="w3-container" style="margin-top:40px"> 5737 <h4 class="w3-center">Privacy and Security in Speech Communication 1</h4> 5738 <hr> 5739 <a class="w3-text" href="muller24b_interspeech.html"> 5740 <p> 5741 Harder or Different? Understanding Generalization of Audio Deepfake Detection 5742 <br> 5743 <span class="w3-text w3-text-theme"> 5744 Nicolas M. Müller, Nicholas Evans, Hemlata Tak, Philip Sperl, Konstantin Böttinger 5745 </span> 5746 </p> 5747 </a> 5748 <a class="w3-text" href="oiso24_interspeech.html"> 5749 <p> 5750 Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset 5751 <br> 5752 <span class="w3-text w3-text-theme"> 5753 Hideyuki Oiso, Yuto Matsunaga, Kazuya Kakizaki, Taiki Miyagawa 5754 </span> 5755 </p> 5756 </a> 5757 <a class="w3-text" href="looney24_interspeech.html"> 5758 <p> 5759 Robust spread spectrum speech watermarking using linear prediction and deep spectral shaping 5760 <br> 5761 <span class="w3-text w3-text-theme"> 5762 David Looney, Nikolay D. Gaubitch 5763 </span> 5764 </p> 5765 </a> 5766 <a class="w3-text" href="chen24k_interspeech.html"> 5767 <p> 5768 RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection 5769 <br> 5770 <span class="w3-text w3-text-theme"> 5771 Yujie Chen, Jiangyan Yi, Jun Xue, Chenglong Wang, Xiaohui Zhang, Shunbo Dong, Siding Zeng, Jianhua Tao, Zhao Lv, Cunhang Fan 5772 </span> 5773 </p> 5774 </a> 5775 <a class="w3-text" href="liu24i_interspeech.html"> 5776 <p> 5777 How Private is Low-Frequency Speech Audio in the Wild? An Analysis of Verbal Intelligibility by Humans and Machines 5778 <br> 5779 <span class="w3-text w3-text-theme"> 5780 Ailin Liu, Pepijn Vunderink, Jose Vargas Quiros, Chirag Raman, Hayley Hung 5781 </span> 5782 </p> 5783 </a> 5784 <a class="w3-text" href="yang24e_interspeech.html"> 5785 <p> 5786 RW-VoiceShield: Raw Waveform-based Adversarial Attack on One-shot Voice Conversion 5787 <br> 5788 <span class="w3-text w3-text-theme"> 5789 Ching-Yu Yang, Shreya G. Upadhyay, Ya-Tse Wu, Bo-Hao Su, Chi-Chun Lee 5790 </span> 5791 </p> 5792 </a> 5793 </div> 5794 </div> 5795 <br> 5796 <div class="w3-content" style="height:10px" id="Speech Synthesis: Voice Conversion 2"></div> 5797 <div class="w3-card w3-round w3-white w3-padding"> 5798 <div class="w3-container" style="margin-top:40px"> 5799 <h4 class="w3-center">Speech Synthesis: Voice Conversion 2</h4> 5800 <hr> 5801 <a class="w3-text" href="gusev24_interspeech.html"> 5802 <p> 5803 Improvement Speaker Similarity for Zero-Shot Any-to-Any Voice Conversion of Whispered and Regular Speech 5804 <br>
5805 <span class="w3-text w3-text-theme"> 5806 Aleksei Gusev, Anastasia Avdeeva 5807 </span> 5808 </p> 5809 </a> 5810 <a class="w3-text" href="um24b_interspeech.html"> 5811 <p> 5812 Utilizing Adaptive Global Response Normalization and Cluster-Based Pseudo Labels for Zero-Shot Voice Conversion 5813 <br> 5814 <span class="w3-text w3-text-theme"> 5815 Ji Sub Um, Hoirin Kim 5816 </span> 5817 </p> 5818 </a> 5819 <a class="w3-text" href="ma24e_interspeech.html"> 5820 <p> 5821 Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy 5822 <br> 5823 <span class="w3-text w3-text-theme"> 5824 Linhan Ma, Xinfa Zhu, Yuanjun Lv, Zhichao Wang, Ziqian Wang, Wendi He, Hongbin Zhou, Lei Xie 5825 </span> 5826 </p> 5827 </a> 5828 <a class="w3-text" href="igarashi24_interspeech.html"> 5829 <p> 5830 Noise-Robust Voice Conversion by Conditional Denoising Training Using Latent Variables of Recording Quality and Environment 5831 <br> 5832 <span class="w3-text w3-text-theme"> 5833 Takuto Igarashi, Yuki Saito, Kentaro Seki, Shinnosuke Takamichi, Ryuichi Yamamoto, Kentaro Tachibana, Hiroshi Saruwatari 5834 </span> 5835 </p> 5836 </a> 5837 <a class="w3-text" href="kanagawa24_interspeech.html"> 5838 <p> 5839 Pre-training Neural Transducer-based Streaming Voice Conversion for Faster Convergence and Alignment-free Training 5840 <br> 5841 <span class="w3-text w3-text-theme"> 5842 Hiroki Kanagawa, Takafumi Moriya, Yusuke Ijima 5843 </span> 5844 </p> 5845 </a> 5846 <a class="w3-text" href="xu24b_interspeech.html"> 5847 <p> 5848 Residual Speaker Representation for One-Shot Voice Conversion 5849 <br> 5850 <span class="w3-text w3-text-theme"> 5851 Le Xu, Jiangyan Yi, Tao Wang, Yong Ren, Rongxiu Zhong, Zhengqi Wen, Jianhua Tao 5852 </span> 5853 </p> 5854 </a> 5855 <a class="w3-text" href="gengembre24_interspeech.html"> 5856 <p> 5857 Disentangling prosody and timbre embeddings via voice conversion 5858 <br> 5859 <span class="w3-text w3-text-theme"> 5860 Nicolas Gengembre, Olivier Le Blouch, Cédric Gendrot 5861 </span> 5862 </p> 5863 </a> 5864 <a class="w3-text" href="chen24e_interspeech.html"> 5865 <p> 5866 LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance 5867 <br>
5868 <span class="w3-text w3-text-theme"> 5869 Shihao Chen, Yu Gu, Jie Zhang, Na Li, Rilin Chen, Liping Chen, Lirong Dai 5870 </span> 5871 </p> 5872 </a> 5873 </div> 5874 </div> 5875 <br> 5876 <div class="w3-content" style="height:10px" id="Speech Synthesis: Text Processing"></div> 5877 <div class="w3-card w3-round w3-white w3-padding"> 5878 <div class="w3-container" style="margin-top:40px"> 5879 <h4 class="w3-center">Speech Synthesis: Text Processing</h4> 5880 <hr> 5881 <a class="w3-text" href="roth24_interspeech.html"> 5882 <p> 5883 A Language Modeling Approach to Diacritic-Free Hebrew TTS 5884 <br> 5885 <span class="w3-text w3-text-theme"> 5886 Amit Roth, Arnon Turetzky, Yossi Adi 5887 </span> 5888 </p> 5889 </a> 5890 <a class="w3-text" href="dekel24_interspeech.html"> 5891 <p> 5892 Exploring the Benefits of Tokenization of Discrete Acoustic Units 5893 <br> 5894 <span class="w3-text w3-text-theme"> 5895 Avihu Dekel, Raul Fernandez 5896 </span> 5897 </p> 5898 </a> 5899 <a class="w3-text" href="rezackova24_interspeech.html"> 5900 <p> 5901 Homograph Disambiguation with Text-to-Text Transfer Transformer 5902 <br> 5903 <span class="w3-text w3-text-theme"> 5904 Markéta ÅezáÄková, Daniel Tihelka, JindÅich MatouÅ¡ek 5905 </span> 5906 </p> 5907 </a> 5908 <a class="w3-text" href="kurihara24_interspeech.html"> 5909 <p> 5910 Enhancing Japanese Text-to-Speech Accuracy with a Novel Combination Transformer-BERT-based G2P: Integrating Pronunciation Dictionaries and Accent Sandhi 5911 <br> 5912 <span class="w3-text w3-text-theme"> 5913 Kiyoshi Kurihara, Masanori Sano 5914 </span> 5915 </p> 5916 </a> 5917 <a class="w3-text" href="shirahata24_interspeech.html"> 5918 <p> 5919 Audio-conditioned phonemic and prosodic annotation for building text-to-speech models from unlabeled speech data 5920 <br> 5921 <span class="w3-text w3-text-theme"> 5922 Yuma Shirahata, Byeongseon Park, Ryuichi Yamamoto, Kentaro Tachibana 5923 </span> 5924 </p> 5925 </a> 5926 <a class="w3-text" href="yang24_interspeech.html"> 5927 <p> 5928 G2PA: G2P with Aligned Audio for Mandarin Chinese 5929 <br> 5930 <span class="w3-text w3-text-theme"> 5931 Xingxing Yang 5932 </span> 5933 </p> 5934 </a> 5935 <a class="w3-text" href="sun24_interspeech.html"> 5936 <p> 5937 Learning Pronunciation from Other Accents via Pronunciation Knowledge Transfer 5938 <br>
5939 <span class="w3-text w3-text-theme"> 5940 Siqi Sun, Korin Richmond 5941 </span> 5942 </p> 5943 </a> 5944 <a class="w3-text" href="gupta24d_interspeech.html"> 5945 <p> 5946 Positional Description for Numerical Normalization 5947 <br> 5948 <span class="w3-text w3-text-theme"> 5949 Deepanshu Gupta, Javier Latorre 5950 </span> 5951 </p> 5952 </a> 5953 <a class="w3-text" href="tannander24_interspeech.html"> 5954 <p> 5955 Beyond graphemes and phonemes: continuous phonological features in neural text-to-speech synthesis 5956 <br> 5957 <span class="w3-text w3-text-theme"> 5958 Christina TÃ¥nnander, Shivam Mehta, Jonas Beskow, Jens Edlund 5959 </span> 5960 </p> 5961 </a> 5962 </div> 5963 </div> 5964 <br> 5965 <div class="w3-content" style="height:10px" id="Training Methods, Self-Supervised Learning, Adaptation"></div> 5966 <div class="w3-card w3-round w3-white w3-padding"> 5967 <div class="w3-container" style="margin-top:40px"> 5968 <h4 class="w3-center">Training Methods, Self-Supervised Learning, Adaptation</h4> 5969 <hr> 5970 <a class="w3-text" href="fernandezlopez24_interspeech.html"> 5971 <p> 5972 MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization 5973 <br> 5974 <span class="w3-text w3-text-theme"> 5975 Adriana Fernandez-Lopez, Honglie Chen, Pingchuan Ma, Lu Yin, Qiao Xiao, Stavros Petridis, Shiwei Liu, Maja Pantic 5976 </span> 5977 </p> 5978 </a> 5979 <a class="w3-text" href="prasad24_interspeech.html"> 5980 <p> 5981 Speech and Language Recognition with Low-rank Adaptation of Pretrained Models 5982 <br> 5983 <span class="w3-text w3-text-theme"> 5984 Amrutha Prasad, Srikanth Madikeri, Driss Khalil, Petr Motlicek, Christof Schuepbach 5985 </span> 5986 </p> 5987 </a> 5988 <a class="w3-text" href="kim24s_interspeech.html"> 5989 <p> 5990 Convolution-Augmented Parameter-Efficient Fine-Tuning for Speech Recognition 5991 <br> 5992 <span class="w3-text w3-text-theme"> 5993 Kwangyoun Kim, Suwon Shon, Yi-Te Hsu, Prashant Sridhar, Karen Livescu, Shinji Watanabe 5994 </span> 5995 </p> 5996 </a> 5997 <a class="w3-text" href="meghanani24_interspeech.html"> 5998 <p> 5999 LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks 6000 <br> 6001 <span class="w3-text w3-text-theme"> 6002 Amit Meghanani, Thomas Hain 6003 </span> 6004 </p> 6005 </a> 6006 <a class="w3-text" href="flynn24_interspeech.html"> 6007 <p> 6008 Self-Train Before You Transcribe 6009 <br>
6010 <span class="w3-text w3-text-theme"> 6011 Robert Flynn, Anton Ragni 6012 </span> 6013 </p> 6014 </a> 6015 <a class="w3-text" href="vandereeckt24_interspeech.html"> 6016 <p> 6017 Unsupervised Online Continual Learning for Automatic Speech Recognition 6018 <br> 6019 <span class="w3-text w3-text-theme"> 6020 Steven Vander Eeckt, Hugo Van hamme 6021 </span> 6022 </p> 6023 </a> 6024 <a class="w3-text" href="shi24b_interspeech.html"> 6025 <p> 6026 Dual-path Adaptation of Pretrained Feature Extraction Module for Robust Automatic Speech Recognition 6027 <br> 6028 <span class="w3-text w3-text-theme"> 6029 Hao Shi, Tatsuya Kawahara 6030 </span> 6031 </p> 6032 </a> 6033 <a class="w3-text" href="kusunoki24_interspeech.html"> 6034 <p> 6035 Hierarchical Multi-Task Learning with CTC and Recursive Operation 6036 <br> 6037 <span class="w3-text w3-text-theme"> 6038 Nahomi Kusunoki, Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi 6039 </span> 6040 </p> 6041 </a> 6042 <a class="w3-text" href="hojo24_interspeech.html"> 6043 <p> 6044 Boosting CTC-based ASR using inter-layer attention-based CTC loss 6045 <br> 6046 <span class="w3-text w3-text-theme"> 6047 Keigo Hojo, Yukoh Wakabayashi, Kengo Ohta, Atsunori Ogawa, Norihide Kitaoka 6048 </span> 6049 </p> 6050 </a> 6051 <a class="w3-text" href="kim24t_interspeech.html"> 6052 <p> 6053 Self-training ASR Guided by Unsupervised ASR Teacher 6054 <br> 6055 <span class="w3-text w3-text-theme"> 6056 Hyung Yong Kim, Byeong-Yeol Kim, Yunkyu Lim, Jihwan Park, Shukjae Choi, Yooncheol Ju, Jinseok Park, Youshin Lim, Seung Woo Yu, Hanbin Lee, Shinji Watanabe 6057 </span> 6058 </p> 6059 </a> 6060 <a class="w3-text" href="gu24b_interspeech.html"> 6061 <p> 6062 Personality-memory Gated Adaptation: An Efficient Speaker Adaptation for Personalized End-to-end Automatic Speech Recognition 6063 <br> 6064 <span class="w3-text w3-text-theme"> 6065 Yue Gu, Zhihao Du, Shiliang Zhang, jiqing Han, Yongjun He 6066 </span> 6067 </p> 6068 </a> 6069 <a class="w3-text" href="joseph24_interspeech.html"> 6070 <p> 6071 Speaker Personalization for Automatic Speech Recognition using Weight-Decomposed Low-Rank Adaptation 6072 <br> 6073 <span class="w3-text w3-text-theme"> 6074 George Joseph, Arun Baby 6075 </span> 6076 </p> 6077 </a> 6078 <a class="w3-text" href="lee24j_interspeech.html"> 6079 <p> 6080 Online Subloop Search via Uncertainty Quantization for Efficient Test-Time Adaptation 6081 <br>
6082 <span class="w3-text w3-text-theme"> 6083 Jae-Hong Lee, Sang-Eon Lee, Dong-Hyun Kim, DoHee Kim, Joon-Hyuk Chang 6084 </span> 6085 </p> 6086 </a> 6087 <a class="w3-text" href="singh24c_interspeech.html"> 6088 <p> 6089 ROAR: Reinforcing Original to Augmented Data Ratio Dynamics for Wav2vec2.0 Based ASR 6090 <br> 6091 <span class="w3-text w3-text-theme"> 6092 Vishwanath Pratap Singh, Federico Malato, Ville Hautamäki, Md. Sahidullah, Tomi Kinnunen 6093 </span> 6094 </p> 6095 </a> 6096 <a class="w3-text" href="lee24b_interspeech.html"> 6097 <p> 6098 Online Knowledge Distillation of Decoder-Only Large Language Models for Efficient Speech Recognition 6099 <br> 6100 <span class="w3-text w3-text-theme"> 6101 Jeehye Lee, Hyeji Seo 6102 </span> 6103 </p> 6104 </a> 6105 </div> 6106 </div> 6107 <br> 6108 <div class="w3-content" style="height:10px" id="Novel Architectures for ASR"></div> 6109 <div class="w3-card w3-round w3-white w3-padding"> 6110 <div class="w3-container" style="margin-top:40px"> 6111 <h4 class="w3-center">Novel Architectures for ASR</h4> 6112 <hr> 6113 <a class="w3-text" href="honda24_interspeech.html"> 6114 <p> 6115 Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer 6116 <br> 6117 <span class="w3-text w3-text-theme"> 6118 Tomoki Honda, Shinsuke Sakai, Tatsuya Kawahara 6119 </span> 6120 </p> 6121 </a> 6122 <a class="w3-text" href="kashiwagi24_interspeech.html"> 6123 <p> 6124 Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting 6125 <br> 6126 <span class="w3-text w3-text-theme"> 6127 Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo, Siddhant Arora, Shinji Watanabe 6128 </span> 6129 </p> 6130 </a> 6131 <a class="w3-text" href="shejwalkar24_interspeech.html"> 6132 <p> 6133 Quantifying Unintended Memorization in BEST-RQ ASR Encoders 6134 <br> 6135 <span class="w3-text w3-text-theme"> 6136 Virat Shejwalkar, Om Thakkar, Arun Narayanan 6137 </span> 6138 </p> 6139 </a> 6140 <a class="w3-text" href="kang24b_interspeech.html"> 6141 <p> 6142 SWAN: SubWord Alignment Network for HMM-free word timing estimation in end-to-end automatic speech recognition 6143 <br> 6144 <span class="w3-text w3-text-theme"> 6145 Woo Hyun Kang, Srikanth Vishnubhotla, Rudolf Braun, Yogesh Virkar, Raghuveer Peri, Kyu J. Han 6146 </span> 6147 </p> 6148 </a> 6149 </div> 6150 </div> 6151 <br> 6152 <div class="w3-content" style="height:10px" id="Multimodality and Foundation Models"></div> 6153 <div class="w3-card w3-round w3-white w3-padding"> 6154 <div class="w3-container" style="margin-top:40px"> 6155 <h4 class="w3-center">Multimodality and Foundation Models</h4> 6156 <hr> 6157 <a class="w3-text" href="cui24_interspeech.html"> 6158 <p> 6159 Spontaneous Speech-Based Suicide Risk Detection Using Whisper and Large Language Models 6160 <br>
6161 <span class="w3-text w3-text-theme"> 6162 Ziyun Cui, Chang Lei, Wen Wu, Yinan Duan, Diyang Qu, Ji Wu, Runsen Chen, Chao Zhang 6163 </span> 6164 </p> 6165 </a> 6166 <a class="w3-text" href="sayeed24_interspeech.html"> 6167 <p> 6168 Spoken Word2Vec: Learning Skipgram Embeddings from Speech 6169 <br> 6170 <span class="w3-text w3-text-theme"> 6171 Mohammad Amaan Sayeed, Hanan Aldarmaki 6172 </span> 6173 </p> 6174 </a> 6175 <a class="w3-text" href="bujnowski24_interspeech.html"> 6176 <p> 6177 SAMSEMO: New dataset for multilingual and multimodal emotion recognition 6178 <br> 6179 <span class="w3-text w3-text-theme"> 6180 Pawel Bujnowski, Bartlomiej Kuzma, Bartlomiej Paziewski, Jacek Rutkowski, Joanna Marhula, Zuzanna Bordzicka, Piotr Andruszkiewicz 6181 </span> 6182 </p> 6183 </a> 6184 <a class="w3-text" href="jia24_interspeech.html"> 6185 <p> 6186 LLM-Driven Multimodal Opinion Expression Identification 6187 <br> 6188 <span class="w3-text w3-text-theme"> 6189 Bonian Jia, Huiyao Chen, Yueheng Sun, Meishan Zhang, Min Zhang 6190 </span> 6191 </p> 6192 </a> 6193 <a class="w3-text" href="li24ta_interspeech.html"> 6194 <p> 6195 Zero-Shot Fake Video Detection by Audio-Visual Consistency 6196 <br> 6197 <span class="w3-text w3-text-theme"> 6198 Xiaolou Li, Zehua Liu, Chen Chen, Lantian Li, Li Guo, Dong Wang 6199 </span> 6200 </p> 6201 </a> 6202 <a class="w3-text" href="eungi24_interspeech.html"> 6203 <p> 6204 Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert 6205 <br> 6206 <span class="w3-text w3-text-theme"> 6207 Han EunGi, Oh Hyun-Bin, Kim Sung-Bin, Corentin Nivelet Etcheberry, Suekyeong Nam, Janghoon Ju, Tae-Hyun Oh 6208 </span> 6209 </p> 6210 </a> 6211 </div> 6212 </div> 6213 <br> 6214 <div class="w3-content" style="height:10px" id="Spoken Dialogue Systems and Conversational Analysis 1"></div> 6215 <div class="w3-card w3-round w3-white w3-padding"> 6216 <div class="w3-container" style="margin-top:40px"> 6217 <h4 class="w3-center">Spoken Dialogue Systems and Conversational Analysis 1</h4> 6218 <hr> 6219 <a class="w3-text" href="mcneill24_interspeech.html"> 6220 <p> 6221 Autoregressive cross-interlocutor attention scores meaningfully capture conversational dynamics 6222 <br> 6223 <span class="w3-text w3-text-theme"> 6224 Matthew McNeill, Rivka Levitan 6225 </span> 6226 </p> 6227 </a> 6228 <a class="w3-text" href="atkins24_interspeech.html"> 6229 <p> 6230 ConvoCache: Smart Re-Use of Chatbot Responses 6231 <br>
6232 <span class="w3-text w3-text-theme"> 6233 Conor Atkins, Ian Wood, Mohamed Ali Kaafar, Hassan Asghar, Nardine Basta, Michal Kepkowski 6234 </span> 6235 </p> 6236 </a> 6237 <a class="w3-text" href="qian24b_interspeech.html"> 6238 <p> 6239 Joint Learning of Context and Feedback Embeddings in Spoken Dialogue 6240 <br> 6241 <span class="w3-text w3-text-theme"> 6242 Livia Qian, Gabriel Skantze 6243 </span> 6244 </p> 6245 </a> 6246 <a class="w3-text" href="sahipjohn24_interspeech.html"> 6247 <p> 6248 DubWise: Video-Guided Speech Duration Control in Multimodal LLM-based Text-to-Speech for Dubbing 6249 <br> 6250 <span class="w3-text w3-text-theme"> 6251 Neha Sahipjohn, Ashishkumar Gudmalwar, Nirmesh Shah, Pankaj Wasnik, Rajiv Ratn Shah 6252 </span> 6253 </p> 6254 </a> 6255 <a class="w3-text" href="wang24t_interspeech.html"> 6256 <p> 6257 Contextual Interactive Evaluation of TTS Models in Dialogue Systems 6258 <br> 6259 <span class="w3-text w3-text-theme"> 6260 Siyang Wang, Ãva Székely, Joakim Gustafson 6261 </span> 6262 </p> 6263 </a> 6264 <a class="w3-text" href="shih24b_interspeech.html"> 6265 <p> 6266 GSQA: An End-to-End Model for Generative Spoken Question Answering 6267 <br> 6268 <span class="w3-text w3-text-theme"> 6269 Min-Han Shih, Ho-Lam Chung, Yu-Chi Pai, Ming-Hao Hsu, Guan-Ting Lin, Shang-Wen Li, Hung-yi Lee 6270 </span> 6271 </p> 6272 </a> 6273 </div> 6274 </div> 6275 <br> 6276 <div class="w3-content" style="height:10px" id="Speech Technology"></div> 6277 <div class="w3-card w3-round w3-white w3-padding"> 6278 <div class="w3-container" style="margin-top:40px"> 6279 <h4 class="w3-center">Speech Technology</h4> 6280 <hr> 6281 <a class="w3-text" href="nilsson24_interspeech.html"> 6282 <p> 6283 Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps 6284 <br> 6285 <span class="w3-text w3-text-theme"> 6286 Mattias Nilsson, Riccardo Miccini, Clement Laroche, Tobias Piechowiak, Friedemann Zenke 6287 </span> 6288 </p> 6289 </a> 6290 <a class="w3-text" href="naderi24_interspeech.html"> 6291 <p> 6292 Towards interfacing large language models with ASR systems using confidence measures and prompting 6293 <br> 6294 <span class="w3-text w3-text-theme"> 6295 Maryam Naderi, Enno Hermann, Alexandre Nanchen, Sevada Hovsepyan, Mathew Magimai.-Doss 6296 </span> 6297 </p> 6298 </a> 6299 <a class="w3-text" href="meng24d_interspeech.html"> 6300 <p> 6301 Text Injection for Neural Contextual Biasing 6302 <br>
6303 <span class="w3-text w3-text-theme"> 6304 Zhong Meng, Zelin Wu, Rohit Prabhavalkar, Cal Peyser, Weiran Wang, Nanxin Chen, Tara N. Sainath, Bhuvana Ramabhadran 6305 </span> 6306 </p> 6307 </a> 6308 <a class="w3-text" href="wu24l_interspeech.html"> 6309 <p> 6310 Prompting Large Language Models with Mispronunciation Detection and Diagnosis Abilities 6311 <br> 6312 <span class="w3-text w3-text-theme"> 6313 Minglin Wu, Jing Xu, Xixin Wu, Helen Meng 6314 </span> 6315 </p> 6316 </a> 6317 <a class="w3-text" href="sun24d_interspeech.html"> 6318 <p> 6319 Acceleration of Posteriorgram-based DTW by Distilling the Class-to-class Distances Encoded in the Classifier Used to Calculate Posteriors 6320 <br> 6321 <span class="w3-text w3-text-theme"> 6322 Haitong Sun, Jaehyun Choi, Nobuaki Minematsu, Daisuke Saito 6323 </span> 6324 </p> 6325 </a> 6326 <a class="w3-text" href="gudmalwar24_interspeech.html"> 6327 <p> 6328 VECL-TTS: Voice identity and Emotional style controllable Cross-Lingual Text-to-Speech 6329 <br> 6330 <span class="w3-text w3-text-theme"> 6331 Ashishkumar Gudmalwar, Nirmesh Shah, Sai Akarsh, Pankaj Wasnik, Rajiv Ratn Shah 6332 </span> 6333 </p> 6334 </a> 6335 <a class="w3-text" href="svirsky24_interspeech.html"> 6336 <p> 6337 Sparse Binarization for Fast Keyword Spotting 6338 <br> 6339 <span class="w3-text w3-text-theme"> 6340 Jonathan Svirsky, Uri Shaham, Ofir Lindenbaum 6341 </span> 6342 </p> 6343 </a> 6344 </div> 6345 </div> 6346 <br> 6347 <div class="w3-content" style="height:10px" id="Pathological Speech Analysis 2"></div> 6348 <div class="w3-card w3-round w3-white w3-padding"> 6349 <div class="w3-container" style="margin-top:40px"> 6350 <h4 class="w3-center">Pathological Speech Analysis 2</h4> 6351 <hr> 6352 <a class="w3-text" href="halpern24_interspeech.html"> 6353 <p> 6354 Quantifying the effect of speech pathology on automatic and human speaker verification 6355 <br> 6356 <span class="w3-text w3-text-theme"> 6357 Bence Mark Halpern, Thomas Tienkamp, Wen-Chin Huang, Lester Phillip Violeta, Teja Rebernik, Sebastiaan de Visscher, Max Witjes, Martijn Wieling, Defne Abur, Tomoki Toda 6358 </span> 6359 </p> 6360 </a> 6361 <a class="w3-text" href="maji24_interspeech.html"> 6362 <p> 6363 Investigation of Layer-Wise Speech Representations in Self-Supervised Learning Models: A Cross-Lingual Study in Detecting Depression 6364 <br>
6365 <span class="w3-text w3-text-theme"> 6366 Bubai Maji, Rajlakshmi Guha, Aurobinda Routray, Shazia Nasreen, Debabrata Majumdar 6367 </span> 6368 </p> 6369 </a> 6370 <a class="w3-text" href="talkar24_interspeech.html"> 6371 <p> 6372 Detection of Cognitive Impairment And Alzheimer's Disease Using a Speech- and Language-Based Protocol 6373 <br> 6374 <span class="w3-text w3-text-theme"> 6375 Tanya Talkar, Sherman Charles, Chelsea Krantsevich, Kan Kawabata 6376 </span> 6377 </p> 6378 </a> 6379 <a class="w3-text" href="lin24l_interspeech.html"> 6380 <p> 6381 Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection 6382 <br> 6383 <span class="w3-text w3-text-theme"> 6384 Nana Lin, Youxiang Zhu, Xiaohui Liang, John A. Batsis, Caroline Summerour 6385 </span> 6386 </p> 6387 </a> 6388 <a class="w3-text" href="woszczyk24_interspeech.html"> 6389 <p> 6390 Prosody-Driven Privacy-Preserving Dementia Detection 6391 <br> 6392 <span class="w3-text w3-text-theme"> 6393 Dominika Woszczyk, Ranya Aloufi, Soteris Demetriou 6394 </span> 6395 </p> 6396 </a> 6397 <a class="w3-text" href="koudounas24_interspeech.html"> 6398 <p> 6399 Voice Disorder Analysis: a Transformer-based Approach 6400 <br> 6401 <span class="w3-text w3-text-theme"> 6402 Alkis Koudounas, Gabriele Ciravegna, Marco Fantini, Erika Crosetti, Giovanni Succo, Tania Cerquitelli, Elena Baralis 6403 </span> 6404 </p> 6405 </a> 6406 </div> 6407 </div> 6408 <br> 6409 <div class="w3-content" style="height:10px" id="Speech Science, Speech Technology, and Gender (Special Session)"></div> 6410 <div class="w3-card w3-round w3-white w3-padding"> 6411 <div class="w3-container" style="margin-top:40px"> 6412 <h4 class="w3-center">Speech Science, Speech Technology, and Gender (Special Session)</h4> 6413 <hr> 6414 <a class="w3-text" href="schubert24_interspeech.html"> 6415 <p> 6416 Challenges of German Speech Recognition: A Study on Multi-ethnolectal Speech Among Adolescents 6417 <br> 6418 <span class="w3-text w3-text-theme"> 6419 Martha Schubert, Daniel Duran, Ingo Siegert 6420 </span> 6421 </p> 6422 </a> 6423 <a class="w3-text" href="sigurgeirsson24_interspeech.html"> 6424 <p> 6425 Just Because We Camp, Doesn't Mean We Should: The Ethics of Modelling Queer Voices. 6426 <br> 6427 <span class="w3-text w3-text-theme"> 6428 Atli Sigurgeirsson, Eddie L. Ungless 6429 </span> 6430 </p> 6431 </a> 6432 <a class="w3-text" href="pelloin24_interspeech.html"> 6433 <p> 6434 Automatic Classification of News Subjects in Broadcast News: Application to a Gender Bias Representation Analysis 6435 <br>
6436 <span class="w3-text w3-text-theme"> 6437 Valentin Pelloin, Léna Dodson, Ãmile Chapuis, Nicolas Hervé, David Doukhan 6438 </span> 6439 </p> 6440 </a> 6441 <a class="w3-text" href="doukhan24_interspeech.html"> 6442 <p> 6443 Gender Representation in TV and Radio: Automatic Information Extraction methods versus Manual Analyses 6444 <br> 6445 <span class="w3-text w3-text-theme"> 6446 David Doukhan, Lena Dodson, Manon Conan, Valentin Pelloin, Aurélien Clamouse, Mélina Lepape, Géraldine Van Hille, Cécile Méadel, Marlène Coulomb-Gully 6447 </span> 6448 </p> 6449 </a> 6450 <a class="w3-text" href="hughes24_interspeech.html"> 6451 <p> 6452 Acoustic Effects of Facial Feminisation Surgery on Speech and Singing: A Case Study 6453 <br> 6454 <span class="w3-text w3-text-theme"> 6455 Cliodhna Hughes, Guy Brown, Ning Ma, Nicola Dibben 6456 </span> 6457 </p> 6458 </a> 6459 <a class="w3-text" href="szekely24_interspeech.html"> 6460 <p> 6461 An inclusive approach to creating a palette of synthetic voices for gender diversity 6462 <br> 6463 <span class="w3-text w3-text-theme"> 6464 Eva Szekely, Maxwell Hope 6465 </span> 6466 </p> 6467 </a> 6468 <a class="w3-text" href="netzorg24_interspeech.html"> 6469 <p> 6470 Speech After Gender: A Trans-Feminine Perspective on Next Steps for Speech Science and Technology 6471 <br> 6472 <span class="w3-text w3-text-theme"> 6473 Robin Netzorg, Alyssa Cote, Sumi Koshin, Klo Vivienne Garoute, Gopala Krishna Anumanchipalli 6474 </span> 6475 </p> 6476 </a> 6477 <a class="w3-text" href="lai24_interspeech.html"> 6478 <p> 6479 Voice Quality Variation in AAE: An Additional Challenge for Addressing Bias in ASR Models? 6480 <br> 6481 <span class="w3-text w3-text-theme"> 6482 Li-Fang Lai, Nicole Holliday 6483 </span> 6484 </p> 6485 </a> 6486 <a class="w3-text" href="elie24b_interspeech.html"> 6487 <p> 6488 Articulatory Configurations across Genders and Periods in French Radio and TV archives 6489 <br> 6490 <span class="w3-text w3-text-theme"> 6491 Benjamin Elie, David Doukhan, Rémi Uro, Lucas Ondel-Yang, Albert Rilliard, Simon Devauchelle 6492 </span> 6493 </p> 6494 </a> 6495 <a class="w3-text" href="krishnan24_interspeech.html"> 6496 <p> 6497 On the Encoding of Gender in Transformer-based ASR Representations 6498 <br>
6499 <span class="w3-text w3-text-theme"> 6500 Aravind Krishnan, Badr M. Abdullah, Dietrich Klakow 6501 </span> 6502 </p> 6503 </a> 6504 </div> 6505 </div> 6506 <br> 6507 <div class="w3-content" style="height:10px" id="Speech Production and Perception"></div> 6508 <div class="w3-card w3-round w3-white w3-padding"> 6509 <div class="w3-container" style="margin-top:40px"> 6510 <h4 class="w3-center">Speech Production and Perception</h4> 6511 <hr> 6512 <a class="w3-text" href="fan24c_interspeech.html"> 6513 <p> 6514 Towards a Quantitative Analysis of Coarticulation with a Phoneme-to-Articulatory Model 6515 <br> 6516 <span class="w3-text w3-text-theme"> 6517 Chaofei Fan, Jaimie M. Henderson, Chris Manning, Francis R. Willett 6518 </span> 6519 </p> 6520 </a> 6521 <a class="w3-text" href="sharma24_interspeech.html"> 6522 <p> 6523 A comparative study of the impact of voiceless alveolar and palato-alveolar sibilants in English on lip aperture and protrusion during VCV production 6524 <br> 6525 <span class="w3-text w3-text-theme"> 6526 Chetan Sharma, Vaishnavi Chandwanshi, Prasanta Kumar Ghosh 6527 </span> 6528 </p> 6529 </a> 6530 <a class="w3-text" href="birkholz24_interspeech.html"> 6531 <p> 6532 Measurement and simulation of pressure losses due to airflow in vocal tract models 6533 <br> 6534 <span class="w3-text w3-text-theme"> 6535 Peter Birkholz, Patrick Häsner 6536 </span> 6537 </p> 6538 </a> 6539 <a class="w3-text" href="fang24_interspeech.html"> 6540 <p> 6541 On The Performance of EMA-synchronized Speech and Stand-alone Speech in Acoustic-to-articulatory Inversion 6542 <br> 6543 <span class="w3-text w3-text-theme"> 6544 Qiang Fang 6545 </span> 6546 </p> 6547 </a> 6548 <a class="w3-text" href="freixes24_interspeech.html"> 6549 <p> 6550 Glottal inverse filtering and vocal tract tuning for the numerical simulation of vowel /a/ with different levels of vocal effort 6551 <br> 6552 <span class="w3-text w3-text-theme"> 6553 Marc Freixes, Marc Arnela, Joan Claudi Socoró, Luis Joglar-Ongay, Oriol Guasch, Francesc AlÃas-Pujol 6554 </span> 6555 </p> 6556 </a> 6557 <a class="w3-text" href="friedrichs24_interspeech.html"> 6558 <p> 6559 Temporal Co-Registration of Simultaneous Electromagnetic Articulography and Electroencephalography for Precise Articulatory and Neural Data Alignment 6560 <br> 6561 <span class="w3-text w3-text-theme"> 6562 Daniel Friedrichs, Monica Lancheros, Sam Kirkham, Lei He, Andrew Clark, Clemens Lutz, Volker Dellwo, Steven Moran 6563 </span> 6564 </p> 6565 </a> 6566 </div> 6567 </div> 6568 <br> 6569 <div class="w3-content" style="height:10px" id="Phonetics and Phonology: Segmentals and Suprasegmentals"></div> 6570 <div class="w3-card w3-round w3-white w3-padding"> 6571 <div class="w3-container" style="margin-top:40px"> 6572 <h4 class="w3-center">Phonetics and Phonology: Segmentals and Suprasegmentals</h4> 6573 <hr> 6574 <a class="w3-text" href="miodonska24_interspeech.html"> 6575 <p> 6576 Frication noise features of Polish voiceless dental fricative and affricate produced by children with and without speech disorder 6577 <br>
6578 <span class="w3-text w3-text-theme"> 6579 Zuzanna Miodonska, Michal KrÄcichwost, Ewa KwaÅniok, Agata Sage, Pawel Badura 6580 </span> 6581 </p> 6582 </a> 6583 <a class="w3-text" href="hu24_interspeech.html"> 6584 <p> 6585 Key Acoustic Cues for the Realization of Metrical Prominence in Tone Languages: A Cross-Dialect Study 6586 <br> 6587 <span class="w3-text w3-text-theme"> 6588 Yiying Hu, Hui Feng 6589 </span> 6590 </p> 6591 </a> 6592 <a class="w3-text" href="watkins24_interspeech.html"> 6593 <p> 6594 Revisiting Pitch Jumps: F0 Ratio in Seoul Korean 6595 <br> 6596 <span class="w3-text w3-text-theme"> 6597 Michaela Watkins, Paul Boersma, Silke Hamann 6598 </span> 6599 </p> 6600 </a> 6601 <a class="w3-text" href="maselli24_interspeech.html"> 6602 <p> 6603 Aerodynamics of Sakata labial-velar oral stops 6604 <br> 6605 <span class="w3-text w3-text-theme"> 6606 Lorenzo Maselli, Véronique Delvaux 6607 </span> 6608 </p> 6609 </a> 6610 <a class="w3-text" href="erickson24_interspeech.html"> 6611 <p> 6612 Collecting Mandible Movement in Brazilian Portuguese 6613 <br> 6614 <span class="w3-text w3-text-theme"> 6615 Donna Erickson, Albert Rilliard, Malin Svensson Lundmark, Adelaide Silva, Leticia Rebollo Couto, Oliver Niebuhr, João Antonio de Moraes 6616 </span> 6617 </p> 6618 </a> 6619 <a class="w3-text" href="chan24_interspeech.html"> 6620 <p> 6621 Pitch-driven adjustments in tongue positions: Insights from ultrasound imaging 6622 <br> 6623 <span class="w3-text w3-text-theme"> 6624 May Pik Yu Chan, Jianjing Kuang 6625 </span> 6626 </p> 6627 </a> 6628 </div> 6629 </div> 6630 <br> 6631 <div class="w3-content" style="height:10px" id="Topics in Paralinguistics"></div> 6632 <div class="w3-card w3-round w3-white w3-padding"> 6633 <div class="w3-container" style="margin-top:40px"> 6634 <h4 class="w3-center">Topics in Paralinguistics</h4> 6635 <hr> 6636 <a class="w3-text" href="bn24_interspeech.html"> 6637 <p> 6638 Speaking of Health: Leveraging Large Language Models to assess Exercise Motivation and Behavior of Rehabilitation Patients 6639 <br> 6640 <span class="w3-text w3-text-theme"> 6641 Suhas BN, Amanda Rebar, Saeed Abdullah 6642 </span> 6643 </p> 6644 </a> 6645 <a class="w3-text" href="wu24e_interspeech.html"> 6646 <p> 6647 Confidence Estimation for Automatic Detection of Depression and Alzheimerâs Disease Based on Clinical Interviews 6648 <br>
6649 <span class="w3-text w3-text-theme"> 6650 Wen Wu, Chao Zhang, Philip C. Woodland 6651 </span> 6652 </p> 6653 </a> 6654 <a class="w3-text" href="suda24_interspeech.html"> 6655 <p> 6656 Who Finds This Voice Attractive? A Large-Scale Experiment Using In-the-Wild Data 6657 <br> 6658 <span class="w3-text w3-text-theme"> 6659 Hitoshi Suda, Aya Watanabe, Shinnosuke Takamichi 6660 </span> 6661 </p> 6662 </a> 6663 <a class="w3-text" href="setoguchi24_interspeech.html"> 6664 <p> 6665 Acoustical analysis of the initial phones in speech-laugh 6666 <br> 6667 <span class="w3-text w3-text-theme"> 6668 Ryo Setoguchi, Yoshiko Arimoto 6669 </span> 6670 </p> 6671 </a> 6672 <a class="w3-text" href="hao24_interspeech.html"> 6673 <p> 6674 On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations 6675 <br> 6676 <span class="w3-text w3-text-theme"> 6677 Yaqian Hao, Chenguang Hu, Yingying Gao, Shilei Zhang, Junlan Feng 6678 </span> 6679 </p> 6680 </a> 6681 <a class="w3-text" href="liu24r_interspeech.html"> 6682 <p> 6683 Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge 6684 <br> 6685 <span class="w3-text w3-text-theme"> 6686 Rui Liu, Zening Ma 6687 </span> 6688 </p> 6689 </a> 6690 </div> 6691 </div> 6692 <br> 6693 <div class="w3-content" style="height:10px" id="Emotion Recognition: Fairness, Variability, Uncertainty"></div> 6694 <div class="w3-card w3-round w3-white w3-padding"> 6695 <div class="w3-container" style="margin-top:40px"> 6696 <h4 class="w3-center">Emotion Recognition: Fairness, Variability, Uncertainty</h4> 6697 <hr> 6698 <a class="w3-text" href="wu24_interspeech.html"> 6699 <p> 6700 Dual-Constrained Dynamical Neural ODEs for Ambiguity-aware Continuous Emotion Prediction 6701 <br> 6702 <span class="w3-text w3-text-theme"> 6703 Jingyao Wu, Ting Dang, Vidhyasaharan Sethu, Eliathamby Ambikairajah 6704 </span> 6705 </p> 6706 </a> 6707 <a class="w3-text" href="chou24_interspeech.html"> 6708 <p> 6709 An Inter-Speaker Fairness-Aware Speech Emotion Regression Framework 6710 <br> 6711 <span class="w3-text w3-text-theme"> 6712 Hsing-Hang Chou, Woan-Shiuan Chien, Ya-Tse Wu, Chi-Chun Lee 6713 </span> 6714 </p> 6715 </a> 6716 <a class="w3-text" href="tavernor24_interspeech.html"> 6717 <p> 6718 The Whole Is Bigger Than the Sum of Its Parts: Modeling Individual Annotators to Capture Emotional Variability 6719 <br>
6720 <span class="w3-text w3-text-theme"> 6721 James Tavernor, Yara El-Tawil, Emily Mower Provost 6722 </span> 6723 </p> 6724 </a> 6725 <a class="w3-text" href="sun24e_interspeech.html"> 6726 <p> 6727 Iterative Prototype Refinement for Ambiguous Speech Emotion Recognition 6728 <br> 6729 <span class="w3-text w3-text-theme"> 6730 Haoqin Sun, Shiwan Zhao, Xiangyu Kong, Xuechen Wang, Hui Wang, Jiaming Zhou, Yong Qin 6731 </span> 6732 </p> 6733 </a> 6734 <a class="w3-text" href="chien24_interspeech.html"> 6735 <p> 6736 An Investigation of Group versus Individual Fairness in Perceptually Fair Speech Emotion Recognition 6737 <br> 6738 <span class="w3-text w3-text-theme"> 6739 Woan-Shiuan Chien, Chi-Chun Lee 6740 </span> 6741 </p> 6742 </a> 6743 <a class="w3-text" href="schrufer24_interspeech.html"> 6744 <p> 6745 Are you sure? Analysing Uncertainty Quantification Approaches for Real-world Speech Emotion Recognition 6746 <br> 6747 <span class="w3-text w3-text-theme"> 6748 Oliver Schrüfer, Manuel Milling, Felix Burkhardt, Florian Eyben, Björn Schuller 6749 </span> 6750 </p> 6751 </a> 6752 <a class="w3-text" href="garcia24_interspeech.html"> 6753 <p> 6754 Speech emotion recognition with deep learning beamforming on a distant human-robot interaction scenario 6755 <br> 6756 <span class="w3-text w3-text-theme"> 6757 Ricardo GarcÃa, Rodrigo Mahu, Nicolás Grágeda, Alejandro Luzanto, Nicolas Bohmer, Carlos Busso, Néstor Becerra Yoma 6758 </span> 6759 </p> 6760 </a> 6761 </div> 6762 </div> 6763 <br> 6764 <div class="w3-content" style="height:10px" id="Speaker Verification"></div> 6765 <div class="w3-card w3-round w3-white w3-padding"> 6766 <div class="w3-container" style="margin-top:40px"> 6767 <h4 class="w3-center">Speaker Verification</h4> 6768 <hr> 6769 <a class="w3-text" href="stafylakis24_interspeech.html"> 6770 <p> 6771 Challenging margin-based speaker embedding extractors by using the variational information bottleneck 6772 <br> 6773 <span class="w3-text w3-text-theme"> 6774 Themos Stafylakis, Anna Silnova, Johan Rohdin, OldÅich Plchot, Lukáš Burget 6775 </span> 6776 </p> 6777 </a> 6778 <a class="w3-text" href="chien24c_interspeech.html"> 6779 <p> 6780 Collaborative Contrastive Learning for Hypothesis Domain Adaptation 6781 <br> 6782 <span class="w3-text w3-text-theme"> 6783 Jen-Tzung Chien, I-Ping Yeh, Man-Wai Mak 6784 </span> 6785 </p> 6786 </a> 6787 <a class="w3-text" href="benamor24_interspeech.html"> 6788 <p> 6789 Extraction of interpretable and shared speaker-specific speech attributes through binary auto-encoder 6790 <br>
6791 <span class="w3-text w3-text-theme"> 6792 Imen Ben-Amor, Jean-Francois Bonastre, Salima Mdhaffar 6793 </span> 6794 </p> 6795 </a> 6796 <a class="w3-text" href="yakovlev24_interspeech.html"> 6797 <p> 6798 Reshape Dimensions Network for Speaker Recognition 6799 <br> 6800 <span class="w3-text w3-text-theme"> 6801 Ivan Yakovlev, Rostislav Makarov, Andrei Balykin, Pavel Malov, Anton Okhotnikov, Nikita Torgashov 6802 </span> 6803 </p> 6804 </a> 6805 <a class="w3-text" href="jung24d_interspeech.html"> 6806 <p> 6807 To what extent can ASV systems naturally defend against spoofing attacks? 6808 <br> 6809 <span class="w3-text w3-text-theme"> 6810 Jee-weon Jung, Xin Wang, Nicholas Evans, Shinji Watanabe, Hye-jin Shim, Hemlata Tak, Siddhant Arora, Junichi Yamagishi, Joon Son Chung 6811 </span> 6812 </p> 6813 </a> 6814 <a class="w3-text" href="chen24l_interspeech.html"> 6815 <p> 6816 ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiency 6817 <br> 6818 <span class="w3-text w3-text-theme"> 6819 Yafeng Chen, Siqi Zheng, Hui Wang, Luyao Cheng, Qian Chen, Shiliang Zhang, Junjie Li 6820 </span> 6821 </p> 6822 </a> 6823 </div> 6824 </div> 6825 <br> 6826 <div class="w3-content" style="height:10px" id="Spatial Audio and Acoustics"></div> 6827 <div class="w3-card w3-round w3-white w3-padding"> 6828 <div class="w3-container" style="margin-top:40px"> 6829 <h4 class="w3-center">Spatial Audio and Acoustics</h4> 6830 <hr> 6831 <a class="w3-text" href="khokhlov24_interspeech.html"> 6832 <p> 6833 Classification of Room Impulse Responses and its application for channel verification and diarization 6834 <br> 6835 <span class="w3-text w3-text-theme"> 6836 Yuri Khokhlov, Tatiana Prisyach, Anton Mitrofanov, Dmitry Dutov, Igor Agafonov, Tatiana Timofeeva, Aleksei Romanenko, Maxim Korenevsky 6837 </span> 6838 </p> 6839 </a> 6840 <a class="w3-text" href="kelley24_interspeech.html"> 6841 <p> 6842 RIR-in-a-Box: Estimating Room Acoustics from 3D Mesh Data through Shoebox Approximation 6843 <br> 6844 <span class="w3-text w3-text-theme"> 6845 Liam Kelley, Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii 6846 </span> 6847 </p> 6848 </a> 6849 <a class="w3-text" href="ahn24c_interspeech.html"> 6850 <p> 6851 Novel-view Acoustic Synthesis From 3D Reconstructed Rooms 6852 <br>
6853 <span class="w3-text w3-text-theme"> 6854 Byeongjoo Ahn, Karren Yang, Brian Hamilton, Jonathan Sheaffer, Anurag Ranjan, Miguel Sarabia, Oncel Tuzel, Jen-Hao Rick Chang 6855 </span> 6856 </p> 6857 </a> 6858 <a class="w3-text" href="tao24_interspeech.html"> 6859 <p> 6860 Spatial Acoustic Enhancement Using Unbiased Relative Harmonic Coefficients 6861 <br> 6862 <span class="w3-text w3-text-theme"> 6863 Liang Tao, Maoshen Jia, Yonggang Hu, Changchun Bao 6864 </span> 6865 </p> 6866 </a> 6867 <a class="w3-text" href="bayestehtashk24_interspeech.html"> 6868 <p> 6869 Design of Feedback Active Noise Cancellation Filter Using Nested Recurrent Neural Networks 6870 <br> 6871 <span class="w3-text w3-text-theme"> 6872 Alireza Bayestehtashk, Amit Kumar, Mike Wurtz 6873 </span> 6874 </p> 6875 </a> 6876 <a class="w3-text" href="yarga24_interspeech.html"> 6877 <p> 6878 Neuromorphic Keyword Spotting with Pulse Density Modulation MEMS Microphones 6879 <br> 6880 <span class="w3-text w3-text-theme"> 6881 Sidi Yaya Arnaud Yarga, Sean U N Wood 6882 </span> 6883 </p> 6884 </a> 6885 <a class="w3-text" href="bitterman24_interspeech.html"> 6886 <p> 6887 RevRIR: Joint Reverberant Speech and Room Impulse Response Embedding using Contrastive Learning with Application to Room Shape Classification 6888 <br> 6889 <span class="w3-text w3-text-theme"> 6890 Jacob Bitterman, Daniel Levi, Hilel Hagai Diamandi, Sharon Gannot, Tal Rosenwein 6891 </span> 6892 </p> 6893 </a> 6894 </div> 6895 </div> 6896 <br> 6897 <div class="w3-content" style="height:10px" id="Generative Models for Speech and Audio"></div> 6898 <div class="w3-card w3-round w3-white w3-padding"> 6899 <div class="w3-container" style="margin-top:40px"> 6900 <h4 class="w3-center">Generative Models for Speech and Audio</h4> 6901 <hr> 6902 <a class="w3-text" href="bai24b_interspeech.html"> 6903 <p> 6904 ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation 6905 <br> 6906 <span class="w3-text w3-text-theme"> 6907 Yatong Bai, Trung Dang, Dung Tran, Kazuhito Koishida, Somayeh Sojoudi 6908 </span> 6909 </p> 6910 </a> 6911 <a class="w3-text" href="paissan24b_interspeech.html"> 6912 <p> 6913 Audio Editing with Non-Rigid Text Prompts 6914 <br> 6915 <span class="w3-text w3-text-theme"> 6916 Francesco Paissan, Luca Della Libera, Zhepei Wang, Paris Smaragdis, Mirco Ravanelli, Cem Subakan 6917 </span> 6918 </p> 6919 </a> 6920 <a class="w3-text" href="gupta24b_interspeech.html"> 6921 <p> 6922 Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice 6923 <br>
6924 <span class="w3-text w3-text-theme"> 6925 Shubham Gupta, Mirco Ravanelli, Pascal Germain, Cem Subakan 6926 </span> 6927 </p> 6928 </a> 6929 <a class="w3-text" href="moschopoulos24_interspeech.html"> 6930 <p> 6931 Exploring compressibility of transformer based text-to-music (TTM) models 6932 <br> 6933 <span class="w3-text w3-text-theme"> 6934 Vasileios Moschopoulos, Thanasis Kotsiopoulos, Pablo Peso Parada, Konstantinos Nikiforidis, Alexandros Stergiadis, Gerasimos Papakostas, Md Asif Jalal, Jisi Zhang, Anastasios Drosou, Karthikeyan Saravanan 6935 </span> 6936 </p> 6937 </a> 6938 <a class="w3-text" href="kim24n_interspeech.html"> 6939 <p> 6940 Sound of Vision: Audio Generation from Visual Text Embedding through Training Domain Discriminator 6941 <br> 6942 <span class="w3-text w3-text-theme"> 6943 Jaewon Kim, Won-Gook Choi, Seyun Ahn, Joon-Hyuk Chang 6944 </span> 6945 </p> 6946 </a> 6947 <a class="w3-text" href="choi24c_interspeech.html"> 6948 <p> 6949 Retrieval-Augmented Classifier Guidance for Audio Generation 6950 <br> 6951 <span class="w3-text w3-text-theme"> 6952 Ho-Young Choi, Won-Gook Choi, Joon-Hyuk Chang 6953 </span> 6954 </p> 6955 </a> 6956 <a class="w3-text" href="cappellazzo24_interspeech.html"> 6957 <p> 6958 Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters 6959 <br> 6960 <span class="w3-text w3-text-theme"> 6961 Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti 6962 </span> 6963 </p> 6964 </a> 6965 <a class="w3-text" href="deshmukh24b_interspeech.html"> 6966 <p> 6967 PAM: Prompting Audio-Language Models for Audio Quality Assessment 6968 <br> 6969 <span class="w3-text w3-text-theme"> 6970 Soham Deshmukh, Dareen Alharthi, Benjamin Elizalde, Hannes Gamper, Mahmoud Al Ismail, Rita Singh, Bhiksha Raj, Huaming Wang 6971 </span> 6972 </p> 6973 </a> 6974 </div> 6975 </div> 6976 <br> 6977 <div class="w3-content" style="height:10px" id="Speech and Audio Modelling"></div> 6978 <div class="w3-card w3-round w3-white w3-padding"> 6979 <div class="w3-container" style="margin-top:40px"> 6980 <h4 class="w3-center">Speech and Audio Modelling</h4> 6981 <hr> 6982 <a class="w3-text" href="gao24_interspeech.html"> 6983 <p> 6984 GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model 6985 <br> 6986 <span class="w3-text w3-text-theme"> 6987 Yingying Gao, Shilei Zhang, Chao Deng, Junlan Feng 6988 </span> 6989 </p> 6990 </a> 6991 <a class="w3-text" href="guillaume24_interspeech.html"> 6992 <p> 6993 Gender and Language Identification in Multilingual Models of Speech: Exploring the Genericity and Robustness of Speech Representations 6994 <br>
6995 <span class="w3-text w3-text-theme"> 6996 Séverine Guillaume, Maxime Fily, Alexis Michaud, Guillaume Wisniewski 6997 </span> 6998 </p> 6999 </a> 7000 <a class="w3-text" href="wang24u_interspeech.html"> 7001 <p> 7002 Neural Compression Augmentation for Contrastive Audio Representation Learning 7003 <br> 7004 <span class="w3-text w3-text-theme"> 7005 Zhaoyu Wang, Haohe Liu, Harry Coppock, Björn Schuller, Mark D. Plumbley 7006 </span> 7007 </p> 7008 </a> 7009 <a class="w3-text" href="aluru24_interspeech.html"> 7010 <p> 7011 Post-Net: A linguistically inspired sequence-dependent transformed neural architecture for automatic syllable stress detection 7012 <br> 7013 <span class="w3-text w3-text-theme"> 7014 Sai Harshitha Aluru, Jhansi Mallela, Chiranjeevi Yarra 7015 </span> 7016 </p> 7017 </a> 7018 </div> 7019 </div> 7020 <br> 7021 <div class="w3-content" style="height:10px" id="Multi-Channel Speech Enhancement"></div> 7022 <div class="w3-card w3-round w3-white w3-padding"> 7023 <div class="w3-container" style="margin-top:40px"> 7024 <h4 class="w3-center">Multi-Channel Speech Enhancement</h4> 7025 <hr> 7026 <a class="w3-text" href="tammen24_interspeech.html"> 7027 <p> 7028 Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers 7029 <br> 7030 <span class="w3-text w3-text-theme"> 7031 Marvin Tammen, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Shoko Araki, Simon Doclo 7032 </span> 7033 </p> 7034 </a> 7035 <a class="w3-text" href="xu24i_interspeech.html"> 7036 <p> 7037 FoVNet: Configurable Field-of-View Speech Enhancement with Low Computation and Distortion for Smart Glasses 7038 <br> 7039 <span class="w3-text w3-text-theme"> 7040 Zhongweiyang Xu, Ali Aroudi, Ke Tan, Ashutosh Pandey, Jung-Suk Lee, Buye Xu, Francesco Nesta 7041 </span> 7042 </p> 7043 </a> 7044 <a class="w3-text" href="aziz24_interspeech.html"> 7045 <p> 7046 Audio Enhancement from Multiple Crowdsourced Recordings: A Simple and Effective Baseline 7047 <br> 7048 <span class="w3-text w3-text-theme"> 7049 Shiran Aziz, Yossi Adi, Shmuel Peleg 7050 </span> 7051 </p> 7052 </a> 7053 <a class="w3-text" href="lee24g_interspeech.html"> 7054 <p> 7055 DeFTAN-AA: Array Geometry Agnostic Multichannel Speech Enhancement 7056 <br> 7057 <span class="w3-text w3-text-theme"> 7058 Dongheon Lee, Jung-Woo Choi 7059 </span> 7060 </p> 7061 </a> 7062 <a class="w3-text" href="zhou24d_interspeech.html"> 7063 <p> 7064 PLDNet: PLD-Guided Lightweight Deep Network Boosted by Efï¬cient Attention for Handheld Dual-Microphone Speech Enhancement 7065 <br>
7066 <span class="w3-text w3-text-theme"> 7067 Nan Zhou, Youhai Jiang, Jialin Tan, Chongmin Qi 7068 </span> 7069 </p> 7070 </a> 7071 </div> 7072 </div> 7073 <br> 7074 <div class="w3-content" style="height:10px" id="Speech Synthesis: Paradigms and Methods 1"></div> 7075 <div class="w3-card w3-round w3-white w3-padding"> 7076 <div class="w3-container" style="margin-top:40px"> 7077 <h4 class="w3-center">Speech Synthesis: Paradigms and Methods 1</h4> 7078 <hr> 7079 <a class="w3-text" href="mcghee24_interspeech.html"> 7080 <p> 7081 Highly Intelligible Speaker-Independent Articulatory Synthesis 7082 <br> 7083 <span class="w3-text w3-text-theme"> 7084 Charles McGhee, Kate Knill, Mark Gales 7085 </span> 7086 </p> 7087 </a> 7088 <a class="w3-text" href="murata24_interspeech.html"> 7089 <p> 7090 An Attribute Interpolation Method in Speech Synthesis by Model Merging 7091 <br> 7092 <span class="w3-text w3-text-theme"> 7093 Masato Murata, Koichi Miyazaki, Tomoki Koriyama 7094 </span> 7095 </p> 7096 </a> 7097 <a class="w3-text" href="nishihara24_interspeech.html"> 7098 <p> 7099 Low-dimensional Style Token Control for Hyperarticulated Speech Synthesis 7100 <br> 7101 <span class="w3-text w3-text-theme"> 7102 Miku Nishihara, Dan Wells, Korin Richmond, Aidan Pine 7103 </span> 7104 </p> 7105 </a> 7106 <a class="w3-text" href="li24ba_interspeech.html"> 7107 <p> 7108 Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation 7109 <br> 7110 <span class="w3-text w3-text-theme"> 7111 Hanzhao Li, Liumeng Xue, Haohan Guo, Xinfa Zhu, Yuanjun Lv, Lei Xie, Yunlin Chen, Hao Yin, Zhifei Li 7112 </span> 7113 </p> 7114 </a> 7115 <a class="w3-text" href="dang24_interspeech.html"> 7116 <p> 7117 LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes 7118 <br> 7119 <span class="w3-text w3-text-theme"> 7120 Trung Dang, David Aponte, Dung Tran, Kazuhito Koishida 7121 </span> 7122 </p> 7123 </a> 7124 <a class="w3-text" href="kim24h_interspeech.html"> 7125 <p> 7126 ClariTTS: Feature-ratio Normalization and Duration Stabilization for Code-mixed Multi-speaker Speech Synthesis 7127 <br> 7128 <span class="w3-text w3-text-theme"> 7129 Changhwan Kim 7130 </span> 7131 </p> 7132 </a> 7133 <a class="w3-text" href="janiczek24_interspeech.html"> 7134 <p> 7135 Multi-modal Adversarial Training for Zero-Shot Voice Cloning 7136 <br>
7137 <span class="w3-text w3-text-theme"> 7138 John Janiczek, Dading Chong, Dongyang Dai, Arlo Faria, Chao Wang, Tao Wang, Yuzong Liu 7139 </span> 7140 </p> 7141 </a> 7142 <a class="w3-text" href="chien24b_interspeech.html"> 7143 <p> 7144 Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning 7145 <br> 7146 <span class="w3-text w3-text-theme"> 7147 Chung-Ming Chien, Andros Tjandra, Apoorv Vyas, Matt Le, Bowen Shi, Wei-Ning Hsu 7148 </span> 7149 </p> 7150 </a> 7151 <a class="w3-text" href="wu24o_interspeech.html"> 7152 <p> 7153 Modeling Vocal Tract Like Acoustic Tubes Using the Immersed Boundary Method 7154 <br> 7155 <span class="w3-text w3-text-theme"> 7156 Rongshuai Wu, Debasish Ray Mohapatra, Sidney Fels 7157 </span> 7158 </p> 7159 </a> 7160 </div> 7161 </div> 7162 <br> 7163 <div class="w3-content" style="height:10px" id="Speech Synthesis: Paradigms and Methods 2"></div> 7164 <div class="w3-card w3-round w3-white w3-padding"> 7165 <div class="w3-container" style="margin-top:40px"> 7166 <h4 class="w3-center">Speech Synthesis: Paradigms and Methods 2</h4> 7167 <hr> 7168 <a class="w3-text" href="lemerle24_interspeech.html"> 7169 <p> 7170 Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis 7171 <br> 7172 <span class="w3-text w3-text-theme"> 7173 Théodor Lemerle, Nicolas Obin, Axel Roebel 7174 </span> 7175 </p> 7176 </a> 7177 <a class="w3-text" href="neekhara24_interspeech.html"> 7178 <p> 7179 Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment 7180 <br> 7181 <span class="w3-text w3-text-theme"> 7182 Paarth Neekhara, Shehzeen Hussain, Subhankar Ghosh, Jason Li, Boris Ginsburg 7183 </span> 7184 </p> 7185 </a> 7186 <a class="w3-text" href="lai24b_interspeech.html"> 7187 <p> 7188 Synthesizing Long-Form Speech merely from Sentence-Level Corpus with Content Extrapolation and LLM Contextual Enrichment 7189 <br> 7190 <span class="w3-text w3-text-theme"> 7191 Shijie Lai, Minglu He, Zijing Zhao, Kai Wang, Hao Huang, Jichen Yang 7192 </span> 7193 </p> 7194 </a> 7195 <a class="w3-text" href="liu24p_interspeech.html"> 7196 <p> 7197 FluentEditor: Text-based Speech Editing by Considering Acoustic and Prosody Consistency 7198 <br> 7199 <span class="w3-text w3-text-theme"> 7200 Rui Liu, Jiatian Xi, Ziyue Jiang, Haizhou Li 7201 </span> 7202 </p> 7203 </a> 7204 <a class="w3-text" href="zhou24_interspeech.html"> 7205 <p> 7206 Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis 7207 <br>
7208 <span class="w3-text w3-text-theme"> 7209 Kun Zhou, Shengkui Zhao, Yukun Ma, Chong Zhang, Hao Wang, Dianwen Ng, Chongjia Ni, Trung Hieu Nguyen, Jia Qi Yip, Bin Ma 7210 </span> 7211 </p> 7212 </a> 7213 <a class="w3-text" href="lee24f_interspeech.html"> 7214 <p> 7215 High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model 7216 <br> 7217 <span class="w3-text w3-text-theme"> 7218 Joun Yeop Lee, Myeonghun Jeong, Minchan Kim, Ji-Hyun Lee, Hoon-Young Cho, Nam Soo Kim 7219 </span> 7220 </p> 7221 </a> 7222 <a class="w3-text" href="lenglet24_interspeech.html"> 7223 <p> 7224 FastLips: an End-to-End Audiovisual Text-to-Speech System with Lip Features Prediction for Virtual Avatars 7225 <br> 7226 <span class="w3-text w3-text-theme"> 7227 Martin Lenglet, Olivier Perrotin, Gerard Bailly 7228 </span> 7229 </p> 7230 </a> 7231 </div> 7232 </div> 7233 <br> 7234 <div class="w3-content" style="height:10px" id="Neural Network Architectures for ASR 1"></div> 7235 <div class="w3-card w3-round w3-white w3-padding"> 7236 <div class="w3-container" style="margin-top:40px"> 7237 <h4 class="w3-center">Neural Network Architectures for ASR 1</h4> 7238 <hr> 7239 <a class="w3-text" href="yang24g_interspeech.html"> 7240 <p> 7241 Contemplative Mechanism for Speech Recognition: Speech Encoders can Think 7242 <br> 7243 <span class="w3-text w3-text-theme"> 7244 Tien-Ju Yang, Andrew Rosenberg, Bhuvana Ramabhadran 7245 </span> 7246 </p> 7247 </a> 7248 <a class="w3-text" href="parcollet24_interspeech.html"> 7249 <p> 7250 SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding 7251 <br> 7252 <span class="w3-text w3-text-theme"> 7253 Titouan Parcollet, Rogier van Dalen, Shucong Zhang, Sourav Bhattacharya 7254 </span> 7255 </p> 7256 </a> 7257 <a class="w3-text" href="moriya24_interspeech.html"> 7258 <p> 7259 Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding 7260 <br> 7261 <span class="w3-text w3-text-theme"> 7262 Takafumi Moriya, Takanori Ashihara, Masato Mimura, Hiroshi Sato, Kohei Matsuura, Ryo Masumura, Taichi Asami 7263 </span> 7264 </p> 7265 </a> 7266 <a class="w3-text" href="kundu24_interspeech.html"> 7267 <p> 7268 RepCNN: Micro-sized, Mighty Models for Wakeword Detection 7269 <br> 7270 <span class="w3-text w3-text-theme"> 7271 Arnav Kundu, Prateeth Nayak, Priyanka Padmanabhan, Devang Naik 7272 </span> 7273 </p> 7274 </a> 7275 <a class="w3-text" href="vankeirsbilck24_interspeech.html"> 7276 <p> 7277 Conformer without Convolutions 7278 <br>
7279 <span class="w3-text w3-text-theme"> 7280 Matthijs Van keirsbilck, Alexander Keller 7281 </span> 7282 </p> 7283 </a> 7284 <a class="w3-text" href="zhang24e_interspeech.html"> 7285 <p> 7286 Linear-Complexity Self-Supervised Learning for Speech Processing 7287 <br> 7288 <span class="w3-text w3-text-theme"> 7289 Shucong Zhang, Titouan Parcollet, Rogier van Dalen, Sourav Bhattacharya 7290 </span> 7291 </p> 7292 </a> 7293 </div> 7294 </div> 7295 <br> 7296 <div class="w3-content" style="height:10px" id="Error Correction and Rescoring"></div> 7297 <div class="w3-card w3-round w3-white w3-padding"> 7298 <div class="w3-container" style="margin-top:40px"> 7299 <h4 class="w3-center">Error Correction and Rescoring</h4> 7300 <hr> 7301 <a class="w3-text" href="mittal24_interspeech.html"> 7302 <p> 7303 SALSA: Speedy ASR-LLM Synchronous Aggregation 7304 <br> 7305 <span class="w3-text w3-text-theme"> 7306 Ashish Mittal, Darshan Prabhu, Sunita Sarawagi, Preethi Jyothi 7307 </span> 7308 </p> 7309 </a> 7310 <a class="w3-text" href="yoon24c_interspeech.html"> 7311 <p> 7312 LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition 7313 <br> 7314 <span class="w3-text w3-text-theme"> 7315 Eunseop Yoon, Hee Suk Yoon, John Harvill, Mark Hasegawa-Johnson, Chang D. Yoo 7316 </span> 7317 </p> 7318 </a> 7319 <a class="w3-text" href="wang24j_interspeech.html"> 7320 <p> 7321 HypR: A comprehensive study for ASR hypothesis revising with a reference corpus 7322 <br> 7323 <span class="w3-text w3-text-theme"> 7324 Yi-Wei Wang, Ke-Han Lu, Kuan-Yu Chen 7325 </span> 7326 </p> 7327 </a> 7328 <a class="w3-text" href="shu24_interspeech.html"> 7329 <p> 7330 Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition 7331 <br> 7332 <span class="w3-text w3-text-theme"> 7333 Yuchun Shu, Bo Hu, Yifeng He, Hao Shi, Longbiao Wang, Jianwu Dang 7334 </span> 7335 </p> 7336 </a> 7337 <a class="w3-text" href="kang24c_interspeech.html"> 7338 <p> 7339 Transformer-based Model for ASR N-Best Rescoring and Rewriting 7340 <br> 7341 <span class="w3-text w3-text-theme"> 7342 Iwen E Kang, Christophe Van Gysel, Man-Hung Siu 7343 </span> 7344 </p> 7345 </a> 7346 <a class="w3-text" href="yang24b_interspeech.html"> 7347 <p> 7348 RASU: Retrieval Augmented Speech Understanding through Generative Modeling 7349 <br>
7350 <span class="w3-text w3-text-theme"> 7351 Hao Yang, Min Zhang, Minghan Wang, Jiaxin Guo 7352 </span> 7353 </p> 7354 </a> 7355 </div> 7356 </div> 7357 <br> 7358 <div class="w3-content" style="height:10px" id="Spoken Language Understanding"></div> 7359 <div class="w3-card w3-round w3-white w3-padding"> 7360 <div class="w3-container" style="margin-top:40px"> 7361 <h4 class="w3-center">Spoken Language Understanding</h4> 7362 <hr> 7363 <a class="w3-text" href="aimaiti24_interspeech.html"> 7364 <p> 7365 An Uyghur Extension to the MASSIVE Multi-lingual Spoken Language Understanding Corpus with Comprehensive Evaluations 7366 <br> 7367 <span class="w3-text w3-text-theme"> 7368 Ainikaerjiang Aimaiti, Di Wu, Liting Jiang, Gulinigeer Abudouwaili, Hao Huang, Wushour Silamu 7369 </span> 7370 </p> 7371 </a> 7372 <a class="w3-text" href="christ24_interspeech.html"> 7373 <p> 7374 This Paper Had the Smartest Reviewers - Flattery Detection Utilising an Audio-Textual Transformer-Based Approach 7375 <br> 7376 <span class="w3-text w3-text-theme"> 7377 Lukas Christ, Shahin Amiriparian, Friederike Hawighorst, Ann-Kathrin Schill, Angelo Boutalikakis, Lorenz Graf-Vlachy, Andreas König, Björn Schuller 7378 </span> 7379 </p> 7380 </a> 7381 <a class="w3-text" href="akani24_interspeech.html"> 7382 <p> 7383 Unified Framework for Spoken Language Understanding and Summarization in Task-Based Human Dialog processing 7384 <br> 7385 <span class="w3-text w3-text-theme"> 7386 Eunice Akani, Frederic Bechet, Benoît Favre, Romain Gemignani 7387 </span> 7388 </p> 7389 </a> 7390 <a class="w3-text" href="anderson24_interspeech.html"> 7391 <p> 7392 Automated Human-Readable Label Generation in Open Intent Discovery 7393 <br> 7394 <span class="w3-text w3-text-theme">
7395 Grant Anderson, Emma Hart, Dimitra Gkatzia, Ian Beaver 7396 </span> 7397 </p> 7398 </a> 7399 <a class="w3-text" href="chang24_interspeech.html"> 7400 <p> 7401 Applying Reinforcement Learning and Multi-Generators for Stage Transition in an Emotional Support Dialogue System 7402 <br> 7403 <span class="w3-text w3-text-theme"> 7404 Jeremy Chang, Kuan-Yu Chen, Chung-Hsien Wu 7405 </span> 7406 </p> 7407 </a> 7408 </div> 7409 </div> 7410 <br> 7411 <div class="w3-content" style="height:10px" id="Spoken Dialogue Systems and Conversational Analysis 2"></div> 7412 <div class="w3-card w3-round w3-white w3-padding"> 7413 <div class="w3-container" style="margin-top:40px"> 7414 <h4 class="w3-center">Spoken Dialogue Systems and Conversational Analysis 2</h4> 7415 <hr> 7416 <a class="w3-text" href="chen24d_interspeech.html"> 7417 <p> 7418 Target conversation extraction: Source separation using turn-taking dynamics 7419 <br> 7420 <span class="w3-text w3-text-theme"> 7421 Tuochao Chen, Qirui Wang, Bohan Wu, Malek Itani, Emre Sefik Eskimez, Takuya Yoshioka, Shyamnath Gollakota 7422 </span> 7423 </p> 7424 </a> 7425 <a class="w3-text" href="ng24b_interspeech.html"> 7426 <p> 7427 Investigating the Influence of Stance-Taking on Conversational Timing of Task-Oriented Speech 7428 <br> 7429 <span class="w3-text w3-text-theme"> 7430 Sara Ng, Gina-Anne Levow, Mari Ostendorf, Richard Wright 7431 </span> 7432 </p> 7433 </a> 7434 <a class="w3-text" href="uro24_interspeech.html"> 7435 <p> 7436 Detecting the terminality of speech-turn boundary for spoken interactions in French TV and Radio content 7437 <br> 7438 <span class="w3-text w3-text-theme"> 7439 Rémi Uro, Marie Tahon, David Doukhan, Antoine Laurent, Albert Rilliard 7440 </span> 7441 </p> 7442 </a> 7443 <a class="w3-text" href="watanabe24_interspeech.html"> 7444 <p> 7445 Utilization of Text Data for Response Timing Detection in Attentive Listening 7446 <br> 7447 <span class="w3-text w3-text-theme"> 7448 Yu Watanabe, Koichiro Ito, Shigeki Matsubara 7449 </span> 7450 </p> 7451 </a> 7452 <a class="w3-text" href="park24b_interspeech.html"> 7453 <p> 7454 Backchannel prediction, based on who, when and what 7455 <br> 7456 <span class="w3-text w3-text-theme"> 7457 Yo-Han Park, Wencke Liermann, Yong-Seok Choi, Seung Hi Kim, Jeong-Uk Bang, Seung Yun, Kong Joo Lee 7458 </span> 7459 </p> 7460 </a> 7461 <a class="w3-text" href="hutin24_interspeech.html"> 7462 <p> 7463 Uh, um and mh: Are filled pauses prone to conversational converge? 7464 <br>
7465 <span class="w3-text w3-text-theme"> 7466 Mathilde Hutin, Junfei Hu, Liesbeth Degand 7467 </span> 7468 </p> 7469 </a> 7470 <a class="w3-text" href="ohagi24_interspeech.html"> 7471 <p> 7472 Investigation of look-ahead techniques to improve response time in spoken dialogue system 7473 <br> 7474 <span class="w3-text w3-text-theme"> 7475 Masaya Ohagi, Tomoya Mizumoto, Katsumasa Yoshikawa 7476 </span> 7477 </p> 7478 </a> 7479 </div> 7480 </div> 7481 <br> 7482 <div class="w3-content" style="height:10px" id="Computational Models of Human Language Acquisition, Perception, and Production (Special Session)"></div> 7483 <div class="w3-card w3-round w3-white w3-padding"> 7484 <div class="w3-container" style="margin-top:40px"> 7485 <h4 class="w3-center">Computational Models of Human Language Acquisition, Perception, and Production (Special Session)</h4> 7486 <hr> 7487 <a class="w3-text" href="heuser24b_interspeech.html"> 7488 <p> 7489 Information-theoretic hypothesis generation of relative cue weighting for the voicing contrast 7490 <br> 7491 <span class="w3-text w3-text-theme"> 7492 Annika Heuser, Jianjing Kuang 7493 </span> 7494 </p> 7495 </a> 7496 <a class="w3-text" href="hovsepyan24_interspeech.html"> 7497 <p> 7498 Neurocomputational model of speech recognition for pathological speech detection: a case study on Parkinson's disease speech detection 7499 <br> 7500 <span class="w3-text w3-text-theme"> 7501 Sevada Hovsepyan, Mathew Magimai.-Doss 7502 </span> 7503 </p> 7504 </a> 7505 <a class="w3-text" href="ortiztandazo24_interspeech.html"> 7506 <p> 7507 Simulating articulatory trajectories with phonological feature interpolation 7508 <br> 7509 <span class="w3-text w3-text-theme"> 7510 Angelo Ortiz Tandazo, Thomas Schatz, Thomas Hueber, Emmanuel Dupoux 7511 </span> 7512 </p> 7513 </a> 7514 <a class="w3-text" href="onda24_interspeech.html"> 7515 <p> 7516 A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora 7517 <br> 7518 <span class="w3-text w3-text-theme"> 7519 Kentaro Onda, Joonyong Park, Nobuaki Minematsu, Daisuke Saito 7520 </span> 7521 </p> 7522 </a> 7523 <a class="w3-text" href="bonafos24_interspeech.html"> 7524 <p> 7525 Dirichlet process mixture model based on topologically augmented signal representation for clustering infant vocalizations 7526 <br> 7527 <span class="w3-text w3-text-theme"> 7528 Guillem Bonafos, Clara Bourot, Pierre Pudlo, Jean-Marc Freyermuth, Laurence Reboul, Samuel Tronçon, Arnaud Rey 7529 </span> 7530 </p> 7531 </a> 7532 <a class="w3-text" href="elie24_interspeech.html"> 7533 <p> 7534 A data-driven model of acoustic speech intelligibility for optimization-based models of speech production 7535 <br>
7536 <span class="w3-text w3-text-theme"> 7537 Benjamin Elie, Juraj Simko, Alice Turk 7538 </span> 7539 </p> 7540 </a> 7541 <a class="w3-text" href="coffey24_interspeech.html"> 7542 <p> 7543 The Difficulty and Importance of Estimating the Lower and Upper Bounds of Infant Speech Exposure 7544 <br> 7545 <span class="w3-text w3-text-theme"> 7546 Joseph Coffey, Okko Räsänen, Camila Scaff, Alejandrina Cristia 7547 </span> 7548 </p> 7549 </a> 7550 <a class="w3-text" href="vanniekerk24_interspeech.html"> 7551 <p> 7552 Spoken-Term Discovery using Discrete Speech Units 7553 <br> 7554 <span class="w3-text w3-text-theme"> 7555 Benjamin van Niekerk, Julian Zaïdi, Marc-André Carbonneau, Herman Kamper 7556 </span> 7557 </p> 7558 </a> 7559 <a class="w3-text" href="mohamed24_interspeech.html"> 7560 <p> 7561 Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations 7562 <br> 7563 <span class="w3-text w3-text-theme"> 7564 Mukhtar Mohamed, Oli Danyi Liu, Hao Tang, Sharon Goldwater 7565 </span> 7566 </p> 7567 </a> 7568 </div> 7569 </div> 7570 <br> 7571 <div class="w3-content" style="height:10px" id="Show and Tell 3"></div> 7572 <div class="w3-card w3-round w3-white w3-padding"> 7573 <div class="w3-container" style="margin-top:40px"> 7574 <h4 class="w3-center">Show and Tell 3</h4> 7575 <hr> 7576 <a class="w3-text" href="ryumina24_interspeech.html"> 7577 <p> 7578 OCEAN-AI: open multimodal framework for personality traits assessment and HR-processes automatization 7579 <br> 7580 <span class="w3-text w3-text-theme"> 7581 Elena Ryumina, Dmitry Ryumin, Alexey Karpov 7582 </span> 7583 </p> 7584 </a> 7585 <a class="w3-text" href="mundra24_interspeech.html"> 7586 <p> 7587 VoxMed: one-step respiratory disease classifier using digital stethoscope sounds 7588 <br> 7589 <span class="w3-text w3-text-theme"> 7590 Paridhi Mundra, Manik Sharma, Yashwardhan Chaudhuri, Orchid Chetia Phukan, Arun Balaji Buduru 7591 </span> 7592 </p> 7593 </a> 7594 <a class="w3-text" href="sharma24b_interspeech.html"> 7595 <p> 7596 AVR: synergizing foundation models for audio-visual humor detection 7597 <br> 7598 <span class="w3-text w3-text-theme"> 7599 Sarthak Sharma, Orchid Chetia Phukan, Drishti Singh, Arun Balaji Buduru, Rajesh Sharma 7600 </span> 7601 </p> 7602 </a> 7603 <a class="w3-text" href="chaudhuri24_interspeech.html"> 7604 <p> 7605 ASGIR: audio spectrogram transformer guided classification and information retrieval for birds 7606 <br>
7607 <span class="w3-text w3-text-theme"> 7608 Yashwardhan Chaudhuri, Paridhi Mundra, Arnesh Batra, Orchid Chetia Phukan, Arun Balaji Buduru 7609 </span> 7610 </p> 7611 </a> 7612 <a class="w3-text" href="koshal24_interspeech.html"> 7613 <p> 7614 PERSONA: an application for emotion recognition, gender recognition and age estimation 7615 <br> 7616 <span class="w3-text w3-text-theme"> 7617 Devyani Koshal, Orchid Chetia Phukan, Sarthak Jain, Arun Balaji Buduru, Rajesh Sharma 7618 </span> 7619 </p> 7620 </a> 7621 <a class="w3-text" href="akhtar24_interspeech.html"> 7622 <p> 7623 NeuRO: an application for code-switched autism detection in children 7624 <br> 7625 <span class="w3-text w3-text-theme"> 7626 Mohd Mujtaba Akhtar, Girish, Orchid Chetia Phukan, Muskaan Singh 7627 </span> 7628 </p> 7629 </a> 7630 <a class="w3-text" href="phukan24c_interspeech.html"> 7631 <p> 7632 ComFeAT: combination of neural and spectral features for improved depression detection 7633 <br> 7634 <span class="w3-text w3-text-theme"> 7635 Orchid Chetia Phukan, Sarthak Jain, Shubham Singh, Muskaan Singh, Arun Balaji Buduru, Rajesh Sharma 7636 </span> 7637 </p> 7638 </a> 7639 <a class="w3-text" href="jain24b_interspeech.html"> 7640 <p> 7641 The reasonable effectiveness of speaker embeddings for violence detection 7642 <br> 7643 <span class="w3-text w3-text-theme"> 7644 Sarthak Jain, Orchid Chetia Phukan, Arun Balaji Buduru, Rajesh Sharma 7645 </span> 7646 </p> 7647 </a> 7648 <a class="w3-text" href="obukhov24_interspeech.html"> 7649 <p> 7650 ATTEST: an analytics tool for the testing and evaluation of speech technologies 7651 <br> 7652 <span class="w3-text w3-text-theme"> 7653 Dmitrii Obukhov, Marcel de Korte, Andrey Adaschik 7654 </span> 7655 </p> 7656 </a> 7657 <a class="w3-text" href="masson24_interspeech.html"> 7658 <p> 7659 PhoneViz: exploring alignments at a glance 7660 <br> 7661 <span class="w3-text w3-text-theme"> 7662 Margot Masson, Erfan A. Shams, Iona Gessinger, Julie Carson-Berndsen 7663 </span> 7664 </p> 7665 </a> 7666 <a class="w3-text" href="pages24_interspeech.html"> 7667 <p> 7668 Gryannote open-source speaker diarization labeling tool 7669 <br> 7670 <span class="w3-text w3-text-theme"> 7671 Clément Pages, Hervé Bredin 7672 </span> 7673 </p> 7674 </a> 7675 <a class="w3-text" href="morrone24_interspeech.html"> 7676 <p> 7677 A toolkit for joint speaker diarization and identification with application to speaker-attributed ASR 7678 <br>
7679 <span class="w3-text w3-text-theme"> 7680 Giovanni Morrone, Enrico Zovato, Fabio Brugnara, Enrico Sartori, Leonardo Badino 7681 </span> 7682 </p> 7683 </a> 7684 </div> 7685 </div> 7686 <br> 7687 <div class="w3-content" style="height:10px" id="Phonetics, Phonology and Prosody"></div> 7688 <div class="w3-card w3-round w3-white w3-padding"> 7689 <div class="w3-container" style="margin-top:40px"> 7690 <h4 class="w3-center">Phonetics, Phonology and Prosody</h4> 7691 <hr> 7692 <a class="w3-text" href="kinnunen24_interspeech.html"> 7693 <p> 7694 Speaker Detection by the Individual Listener and the Crowd: Parametric Models Applicable to Bonafide and Deepfake Speech 7695 <br> 7696 <span class="w3-text w3-text-theme"> 7697 Tomi H. Kinnunen, Rosa Gonzalez Hautamäki, Xin Wang, Junichi Yamagishi 7698 </span> 7699 </p> 7700 </a> 7701 <a class="w3-text" href="deluca24_interspeech.html"> 7702 <p> 7703 NumberLie: a game-based experiment to understand the acoustics of deception and truthfulness 7704 <br> 7705 <span class="w3-text w3-text-theme"> 7706 Alessandro De Luca, Andrew Clark, Volker Dellwo 7707 </span> 7708 </p> 7709 </a> 7710 <a class="w3-text" href="loiacono24_interspeech.html"> 7711 <p> 7712 Preservation, conservation and phonetic study of the voices of Italian poets: A study on the seven years of the VIP archive 7713 <br> 7714 <span class="w3-text w3-text-theme"> 7715 Federico Lo Iacono, Valentina Colonna, Antonio Romano 7716 </span> 7717 </p> 7718 </a> 7719 <a class="w3-text" href="audibert24_interspeech.html"> 7720 <p> 7721 Do Speaker-dependent Vowel Characteristics depend on Speech Style? 7722 <br> 7723 <span class="w3-text w3-text-theme"> 7724 Nicolas Audibert, Cecile Fougeron, Christine Meunier 7725 </span> 7726 </p> 7727 </a> 7728 <a class="w3-text" href="liu24q_interspeech.html"> 7729 <p> 7730 A comparison of voice similarity through acoustics, human perception and deep neural network (DNN) speaker verification systems 7731 <br> 7732 <span class="w3-text w3-text-theme"> 7733 Suyuan Liu, Molly Babel, Jian Zhu 7734 </span> 7735 </p> 7736 </a> 7737 <a class="w3-text" href="jones24_interspeech.html"> 7738 <p> 7739 Evaluating Italian Vowel Variation with the Recurrent Neural Network Phonet 7740 <br> 7741 <span class="w3-text w3-text-theme"> 7742 Austin Jones, Margaret E. L. Renwick 7743 </span> 7744 </p> 7745 </a> 7746 <a class="w3-text" href="tulchynska24_interspeech.html"> 7747 <p> 7748 Prosodic marking of syntactic boun
7748daries in Khoekhoe 7749 <br> 7750 <span class="w3-text w3-text-theme"> 7751 Kira Tulchynska, Sylvanus Job, Alena Witzlack-Makarevich, Margaret Zellers 7752 </span> 7753 </p> 7754 </a> 7755 </div> 7756 </div> 7757 <br> 7758 <div class="w3-content" style="height:10px" id="Segmentals"></div> 7759 <div class="w3-card w3-round w3-white w3-padding"> 7760 <div class="w3-container" style="margin-top:40px"> 7761 <h4 class="w3-center">Segmentals</h4> 7762 <hr> 7763 <a class="w3-text" href="cronenberg24_interspeech.html"> 7764 <p> 7765 Crosslinguistic Comparison of Acoustic Variation in the Vowel Sequences /ia/ and /io/ in Four Romance Languages 7766 <br> 7767 <span class="w3-text w3-text-theme"> 7768 Johanna Cronenberg, Ioana Chitoran, Lori Lamel, Ioana Vasilescu 7769 </span> 7770 </p> 7771 </a> 7772 <a class="w3-text" href="vegarodriguez24_interspeech.html"> 7773 <p> 7774 Nasal Air Flow During Speech Production In Korebaju 7775 <br> 7776 <span class="w3-text w3-text-theme"> 7777 Jenifer Vega Rodriguez, Nathalie Vallée, Christophe Savariaux, Silvain Gerber 7778 </span> 7779 </p> 7780 </a> 7781 <a class="w3-text" href="kye24_interspeech.html"> 7782 <p> 7783 Affricates in Lushootseed 7784 <br> 7785 <span class="w3-text w3-text-theme"> 7786 Ted Kye 7787 </span> 7788 </p> 7789 </a> 7790 <a class="w3-text" href="terhiija24_interspeech.html"> 7791 <p> 7792 Voiced and voiceless laterals in Angami 7793 <br> 7794 <span class="w3-text w3-text-theme"> 7795 Viyazonuo Terhiija, Priyankoo Sarmah 7796 </span> 7797 </p> 7798 </a> 7799 <a class="w3-text" href="yang24n_interspeech.html"> 7800 <p> 7801 Intrusive schwa within French stop-liquid clusters: An acoustic analysis 7802 <br> 7803 <span class="w3-text w3-text-theme"> 7804 Minmin Yang, Rachid Ridouane 7805 </span> 7806 </p> 7807 </a> 7808 </div> 7809 </div> 7810 <br> 7811 <div class="w3-content" style="height:10px" id="New Avenues in Emotion Recognition"></div> 7812 <div class="w3-card w3-round w3-white w3-padding"> 7813 <div class="w3-container" style="margin-top:40px"> 7814 <h4 class="w3-center">New Avenues in Emotion Recognition</h4> 7815 <hr> 7816 <a class="w3-text" href="wu24d_interspeech.html"> 7817 <p> 7818 Can Modelling Inter-Rater Ambiguity Lead To Noise-Robust Continuous Emotion Predictions? 7819 <br>
7820 <span class="w3-text w3-text-theme"> 7821 Ya-Tse Wu, Jingyao Wu, Vidhyasaharan Sethu, Chi-Chun Lee 7822 </span> 7823 </p> 7824 </a> 7825 <a class="w3-text" href="zhao24g_interspeech.html"> 7826 <p> 7827 MFDR: Multiple-stage Fusion and Dynamically Refined Network for Multimodal Emotion Recognition 7828 <br> 7829 <span class="w3-text w3-text-theme"> 7830 Ziping Zhao, Tian Gao, Haishuai Wang, Björn Schuller 7831 </span> 7832 </p> 7833 </a> 7834 <a class="w3-text" href="shi24i_interspeech.html"> 7835 <p> 7836 Multimodal Fusion of Music Theory-Inspired and Self-Supervised Representations for Improved Emotion Recognition 7837 <br> 7838 <span class="w3-text w3-text-theme"> 7839 Xiaohan Shi, Xingfeng Li, Tomoki Toda 7840 </span> 7841 </p> 7842 </a> 7843 <a class="w3-text" href="triantafyllopoulos24c_interspeech.html"> 7844 <p> 7845 Enrolment-based personalisation for improving individual-level fairness in speech emotion recognition 7846 <br> 7847 <span class="w3-text w3-text-theme"> 7848 Andreas Triantafyllopoulos, Björn Schuller 7849 </span> 7850 </p> 7851 </a> 7852 <a class="w3-text" href="leem24_interspeech.html"> 7853 <p> 7854 Keep, Delete, or Substitute: Frame Selection Strategy for Noise-Robust Speech Emotion Recognition 7855 <br> 7856 <span class="w3-text w3-text-theme"> 7857 Seong-Gyun Leem, Daniel Fulford, Jukka-Pekka Onnela, David Gard, Carlos Busso 7858 </span> 7859 </p> 7860 </a> 7861 <a class="w3-text" href="lu24e_interspeech.html"> 7862 <p> 7863 Hierarchical Distribution Adaptation for Unsupervised Cross-corpus Speech Emotion Recognition 7864 <br> 7865 <span class="w3-text w3-text-theme"> 7866 Cheng Lu, Yuan Zong, Yan Zhao, Hailun Lian, Tianhua Qi, Björn Schuller, Wenming Zheng 7867 </span> 7868 </p> 7869 </a> 7870 </div> 7871 </div> 7872 <br> 7873 <div class="w3-content" style="height:10px" id="Speaker Diarization 2"></div> 7874 <div class="w3-card w3-round w3-white w3-padding"> 7875 <div class="w3-container" style="margin-top:40px"> 7876 <h4 class="w3-center">Speaker Diarization 2</h4> 7877 <hr> 7878 <a class="w3-text" href="zhang24b_interspeech.html"> 7879 <p> 7880 Variable Segment Length and Domain-Adapted Feature Optimization for Speaker Diarization 7881 <br> 7882 <span class="w3-text w3-text-theme"> 7883 Chenyuan Zhang, Linkai Luo, Hong Peng, Wei Wen 7884 </span> 7885 </p> 7886 </a> 7887 <a class="w3-text" href="choi24d_interspeech.html"> 7888 <p> 7889 Efficient Speaker Embedding Extraction Using a Twofold Sliding Window Algorithm for Speaker Diarization 7890 <br>
7891 <span class="w3-text w3-text-theme"> 7892 Jeong-Hwan Choi, Ye-Rin Jeoung, Ilseok Kim, Joon-Hyuk Chang 7893 </span> 7894 </p> 7895 </a> 7896 <a class="w3-text" href="wang24h_interspeech.html"> 7897 <p> 7898 DiarizationLM: Speaker Diarization Post-Processing with Large Language Models 7899 <br> 7900 <span class="w3-text w3-text-theme"> 7901 Quan Wang, Yiling Huang, Guanlong Zhao, Evan Clark, Wei Xia, Hank Liao 7902 </span> 7903 </p> 7904 </a> 7905 <a class="w3-text" href="blatt24_interspeech.html"> 7906 <p> 7907 Joint vs Sequential Speaker-Role Detection and Automatic Speech Recognition for Air-traffic Control 7908 <br> 7909 <span class="w3-text w3-text-theme"> 7910 Alexander Blatt, Aravind Krishnan, Dietrich Klakow 7911 </span> 7912 </p> 7913 </a> 7914 <a class="w3-text" href="plaquet24_interspeech.html"> 7915 <p> 7916 On the calibration of powerset speaker diarization models 7917 <br> 7918 <span class="w3-text w3-text-theme"> 7919 Alexis Plaquet, Hervé Bredin 7920 </span> 7921 </p> 7922 </a> 7923 <a class="w3-text" href="baroudi24_interspeech.html"> 7924 <p> 7925 Specializing Self-Supervised Speech Representations for Speaker Segmentation 7926 <br> 7927 <span class="w3-text w3-text-theme"> 7928 Séverin Baroudi, Thomas Pellegrini, Hervé Bredin 7929 </span> 7930 </p> 7931 </a> 7932 </div> 7933 </div> 7934 <br> 7935 <div class="w3-content" style="height:10px" id="Speaker Recognition 2"></div> 7936 <div class="w3-card w3-round w3-white w3-padding"> 7937 <div class="w3-container" style="margin-top:40px"> 7938 <h4 class="w3-center">Speaker Recognition 2</h4> 7939 <hr> 7940 <a class="w3-text" href="loweimi24_interspeech.html"> 7941 <p> 7942 On the Usefulness of Speaker Embeddings for Speaker Retrieval in the Wild: A Comparative Study of x-vector and ECAPA-TDNN Models 7943 <br> 7944 <span class="w3-text w3-text-theme"> 7945 Erfan Loweimi, Mengjie Qian, Kate Knill, Mark Gales 7946 </span> 7947 </p> 7948 </a> 7949 <a class="w3-text" href="jin24b_interspeech.html"> 7950 <p> 7951 W-GVKT: Within-Global-View Knowledge Transfer for Speaker Verification 7952 <br> 7953 <span class="w3-text w3-text-theme"> 7954 Zezhong Jin, Youzhi Tu, Man-Wai Mak 7955 </span> 7956 </p> 7957 </a> 7958 <a class="w3-text" href="shen24_interspeech.html"> 7959 <p> 7960 CEC: A Noisy Label Detection Method for Speaker Recognition 7961 <br>
7962 <span class="w3-text w3-text-theme"> 7963 Yao Shen, Yingying Gao, Yaqian Hao, Chenguang Hu, Fulin Zhang, Junlan Feng, Shilei Zhang 7964 </span> 7965 </p> 7966 </a> 7967 <a class="w3-text" href="zhang24c_interspeech.html"> 7968 <p> 7969 Disentangling Age and Identity with a Mutual Information Minimization for Cross-Age Speaker Verification 7970 <br> 7971 <span class="w3-text w3-text-theme"> 7972 Fengrun Zhang, Wangjin Zhou, Yiming Liu, Wang Geng, Yahui Shan, Chen Zhang 7973 </span> 7974 </p> 7975 </a> 7976 <a class="w3-text" href="li24u_interspeech.html"> 7977 <p> 7978 Contrastive Learning and Inter-Speaker Distribution Alignment Based Unsupervised Domain Adaptation for Robust Speaker Verification 7979 <br> 7980 <span class="w3-text w3-text-theme"> 7981 Zuoliang Li, Wu Guo, Bin Gu, Shengyu Peng, Jie Zhang 7982 </span> 7983 </p> 7984 </a> 7985 <a class="w3-text" href="nguyen24_interspeech.html"> 7986 <p> 7987 Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models 7988 <br> 7989 <span class="w3-text w3-text-theme"> 7990 Minh Nguyen, Franck Dernoncourt, Seunghyun Yoon, Hanieh Deilamsalehy, Hao Tan, Ryan Rossi, Quan Hung Tran, Trung Bui, Thien Huu Nguyen 7991 </span> 7992 </p> 7993 </a> 7994 <a class="w3-text" href="kc24_interspeech.html"> 7995 <p> 7996 Attention-augmented X-vectors for the Evaluation of Mimicked Speech Using Sparse Autoencoder-LSTM framework 7997 <br> 7998 <span class="w3-text w3-text-theme"> 7999 Bhasi K. C., Rajeev Rajan, Noumida A 8000 </span> 8001 </p> 8002 </a> 8003 </div> 8004 </div> 8005 <br> 8006 <div class="w3-content" style="height:10px" id="Speech and Audio Analysis"></div> 8007 <div class="w3-card w3-round w3-white w3-padding"> 8008 <div class="w3-container" style="margin-top:40px"> 8009 <h4 class="w3-center">Speech and Audio Analysis</h4> 8010 <hr> 8011 <a class="w3-text" href="almudevar24_interspeech.html"> 8012 <p> 8013 Predefined Prototypes for Intra-Class Separation and Disentanglement 8014 <br> 8015 <span class="w3-text w3-text-theme"> 8016 Antonio Almudévar, Théo Mariotte, Alfonso Ortega, Marie Tahon, Luis Vicente, Antonio Miguel, Eduardo Lleida 8017 </span> 8018 </p> 8019 </a> 8020 <a class="w3-text" href="koriyama24_interspeech.html"> 8021 <p> 8022 VAE-based Phoneme Alignment Using Gradient Annealing and SSL Acoustic Features 8023 <br>
8024 <span class="w3-text w3-text-theme"> 8025 Tomoki Koriyama 8026 </span> 8027 </p> 8028 </a> 8029 <a class="w3-text" href="karan24_interspeech.html"> 8030 <p> 8031 A Transformer-Based Voice Activity Detector 8032 <br> 8033 <span class="w3-text w3-text-theme"> 8034 Biswajit Karan, Joshua Jansen van Vüren, Febe de Wet, Thomas Niesler 8035 </span> 8036 </p> 8037 </a> 8038 <a class="w3-text" href="dumpala24_interspeech.html"> 8039 <p> 8040 XANE: eXplainable Acoustic Neural Embeddings 8041 <br> 8042 <span class="w3-text w3-text-theme"> 8043 Sri Harsha Dumpala, Dushyant Sharma, Chandramouli Shama Sastry, Stanislav Kruchinin, James Fosburgh, Patrick A. Naylor 8044 </span> 8045 </p> 8046 </a> 8047 <a class="w3-text" href="mallela24_interspeech.html"> 8048 <p> 8049 A comparative analysis of sequential models that integrate syllable dependency for automatic syllable stress detection 8050 <br> 8051 <span class="w3-text w3-text-theme"> 8052 Jhansi Mallela, Sai Harshitha Aluru, Chiranjeevi Yarra 8053 </span> 8054 </p> 8055 </a> 8056 <a class="w3-text" href="li24p_interspeech.html"> 8057 <p> 8058 Motion Based Audio-Visual Segmentation 8059 <br> 8060 <span class="w3-text w3-text-theme"> 8061 Jiahao Li, Miao Liu, Shu Yang, Jing Wang, Xiang Xie 8062 </span> 8063 </p> 8064 </a> 8065 </div> 8066 </div> 8067 <br> 8068 <div class="w3-content" style="height:10px" id="Speech Quality and Intelligibility: Prediction and Enhancement"></div> 8069 <div class="w3-card w3-round w3-white w3-padding"> 8070 <div class="w3-container" style="margin-top:40px"> 8071 <h4 class="w3-center">Speech Quality and Intelligibility: Prediction and Enhancement</h4> 8072 <hr> 8073 <a class="w3-text" href="best24_interspeech.html"> 8074 <p> 8075 Transfer Learning from Whisper for Microscopic Intelligibility Prediction 8076 <br> 8077 <span class="w3-text w3-text-theme"> 8078 Paul Best, Santiago Cuervo, Ricard Marxer 8079 </span> 8080 </p> 8081 </a> 8082 <a class="w3-text" href="zezario24_interspeech.html"> 8083 <p> 8084 Non-Intrusive Speech Intelligibility Prediction for Hearing Aids using Whisper and Metadata 8085 <br> 8086 <span class="w3-text w3-text-theme"> 8087 Ryandhimas E. Zezario, Fei Chen, Chiou-Shann Fuh, Hsin-Min Wang, Yu Tsao 8088 </span> 8089 </p> 8090 </a> 8091 <a class="w3-text" href="wang24y_interspeech.html"> 8092 <p> 8093 No-Reference Speech Intelligibility Prediction Leveraging a Noisy-Speech ASR Pre-Trained Model 8094 <br>
8095 <span class="w3-text w3-text-theme"> 8096 Haolan Wang, Amin Edraki, Wai-Yip Chan, Iván López-Espejo, Jesper Jensen 8097 </span> 8098 </p> 8099 </a> 8100 <a class="w3-text" href="deoliveira24_interspeech.html"> 8101 <p> 8102 The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement 8103 <br> 8104 <span class="w3-text w3-text-theme"> 8105 Danilo de Oliveira, Simon Welker, Julius Richter, Timo Gerkmann 8106 </span> 8107 </p> 8108 </a> 8109 <a class="w3-text" href="ta24b_interspeech.html"> 8110 <p> 8111 Enhancing Non-Matching Reference Speech Quality Assessment through Dynamic Weight Adaptation 8112 <br> 8113 <span class="w3-text w3-text-theme"> 8114 Bao Thang Ta, Van Hai Do, Huynh Thi Thanh Binh 8115 </span> 8116 </p> 8117 </a> 8118 <a class="w3-text" href="chen24j_interspeech.html"> 8119 <p> 8120 Exploring Sentence Type Effects on the Lombard Effect and Intelligibility Enhancement: A Comparative Study of Natural and Grid Sentences 8121 <br> 8122 <span class="w3-text w3-text-theme"> 8123 Hongyang Chen, Yuhong Yang, Zhongyuan Wang, Weiping Tu, Haojun Ai, Cedar Lin 8124 </span> 8125 </p> 8126 </a> 8127 </div> 8128 </div> 8129 <br> 8130 <div class="w3-content" style="height:10px" id="Speech Synthesis: Vocoders"></div> 8131 <div class="w3-card w3-round w3-white w3-padding"> 8132 <div class="w3-container" style="margin-top:40px"> 8133 <h4 class="w3-center">Speech Synthesis: Vocoders</h4> 8134 <hr> 8135 <a class="w3-text" href="lv24_interspeech.html"> 8136 <p> 8137 FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter 8138 <br> 8139 <span class="w3-text w3-text-theme"> 8140 Yuanjun Lv, Hai Li, Ying Yan, Junhui Liu, Danming Xie, Lei Xie 8141 </span> 8142 </p> 8143 </a> 8144 <a class="w3-text" href="chaudhary24b_interspeech.html"> 8145 <p> 8146 QGAN: Low Footprint Quaternion Neural Vocoder for Speech Synthesis 8147 <br> 8148 <span class="w3-text w3-text-theme"> 8149 Aryan Chaudhary, Vinayak Abrol 8150 </span> 8151 </p> 8152 </a> 8153 <a class="w3-text" href="cho24b_interspeech.html"> 8154 <p> 8155 JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis 8156 <br> 8157 <span class="w3-text w3-text-theme"> 8158 Hyunjae Cho, Junhyeok Lee, Wonbin Jung 8159 </span> 8160 </p> 8161 </a> 8162 <a class="w3-text" href="shen24b_interspeech.html"> 8163 <p> 8164 FA-GAN: Artifacts-free and Phase-aware High-fidelity GAN-based Vocoder 8165 <br>
8166 <span class="w3-text w3-text-theme"> 8167 Rubing Shen, Yanzhen Ren, Zongkun Sun 8168 </span> 8169 </p> 8170 </a> 8171 <a class="w3-text" href="chen24x_interspeech.html"> 8172 <p> 8173 QHM-GAN: Neural Vocoder based on Quasi-Harmonic Modeling 8174 <br> 8175 <span class="w3-text w3-text-theme"> 8176 Shaowen Chen, Tomoki Toda 8177 </span> 8178 </p> 8179 </a> 8180 <a class="w3-text" href="du24_interspeech.html"> 8181 <p> 8182 BiVocoder: A Bidirectional Neural Vocoder Integrating Feature Extraction and Waveform Generation 8183 <br> 8184 <span class="w3-text w3-text-theme"> 8185 Hui-Peng Du, Ye-Xin Lu, Yang Ai, Zhen-Hua Ling 8186 </span> 8187 </p> 8188 </a> 8189 </div> 8190 </div> 8191 <br> 8192 <div class="w3-content" style="height:10px" id="ASR Model Training Methods"></div> 8193 <div class="w3-card w3-round w3-white w3-padding"> 8194 <div class="w3-container" style="margin-top:40px"> 8195 <h4 class="w3-center">ASR Model Training Methods</h4> 8196 <hr> 8197 <a class="w3-text" href="raissi24_interspeech.html"> 8198 <p> 8199 Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality 8200 <br> 8201 <span class="w3-text w3-text-theme"> 8202 Tina Raissi, Christoph Lüscher, Simon Berger, Ralf Schlüter, Hermann Ney 8203 </span> 8204 </p> 8205 </a> 8206 <a class="w3-text" href="gaur24_interspeech.html"> 8207 <p> 8208 ASTRA: Aligning Speech and Text Representations for Asr without Sampling 8209 <br> 8210 <span class="w3-text w3-text-theme"> 8211 Neeraj Gaur, Rohan Agrawal, Gary Wang, Parisa Haghani, Andrew Rosenberg, Bhuvana Ramabhadran 8212 </span> 8213 </p> 8214 </a> 8215 <a class="w3-text" href="shakeel24_interspeech.html"> 8216 <p> 8217 Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss 8218 <br> 8219 <span class="w3-text w3-text-theme"> 8220 Muhammad Shakeel, Yui Sudo, Yifan Peng, Shinji Watanabe 8221 </span> 8222 </p> 8223 </a> 8224 <a class="w3-text" href="chiu24_interspeech.html"> 8225 <p> 8226 Learnable Layer Selection and Model Fusion for Speech Self-Supervised Learning Models 8227 <br> 8228 <span class="w3-text w3-text-theme"> 8229 Sheng-Chieh Chiu, Chia-Hua Wu, Jih-Kang Hsieh, Yu Tsao, Hsin-Min Wang 8230 </span> 8231 </p> 8232 </a> 8233 <a class="w3-text" href="kulshreshtha24_interspeech.html"> 8234 <p> 8235 Sequential Editing for Lifelong Training of Speech Recognition Models 8236 <br>
8237 <span class="w3-text w3-text-theme"> 8238 Devang Kulshreshtha, Nikolaos Pappas, Brady Houston, Saket Dingliwal, Srikanth Ronanki 8239 </span> 8240 </p> 8241 </a> 8242 <a class="w3-text" href="yeh24_interspeech.html"> 8243 <p> 8244 Cross-Modality Diffusion Modeling and Sampling for Speech Recognition 8245 <br> 8246 <span class="w3-text w3-text-theme"> 8247 Chia-Kai Yeh, Chih-Chun Chen, Ching-Hsien Hsu, Jen-Tzung Chien 8248 </span> 8249 </p> 8250 </a> 8251 </div> 8252 </div> 8253 <br> 8254 <div class="w3-content" style="height:10px" id="Cross-Lingual and Multilingual Processing"></div> 8255 <div class="w3-card w3-round w3-white w3-padding"> 8256 <div class="w3-container" style="margin-top:40px"> 8257 <h4 class="w3-center">Cross-Lingual and Multilingual Processing</h4> 8258 <hr> 8259 <a class="w3-text" href="liu24l_interspeech.html"> 8260 <p> 8261 A Parameter-efficient Language Extension Framework for Multilingual ASR 8262 <br> 8263 <span class="w3-text w3-text-theme"> 8264 Wei Liu, Jingyong Hou, Dong Yang, Muyong Cao, Tan Lee 8265 </span> 8266 </p> 8267 </a> 8268 <a class="w3-text" href="song24_interspeech.html"> 8269 <p> 8270 LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR 8271 <br> 8272 <span class="w3-text w3-text-theme"> 8273 Zheshu Song, Jianheng Zhuo, Yifan Yang, Ziyang Ma, Shixiong Zhang, Xie Chen 8274 </span> 8275 </p> 8276 </a> 8277 <a class="w3-text" href="zanonboito24_interspeech.html"> 8278 <p> 8279 mHuBERT-147: A Compact Multilingual HuBERT Model 8280 <br> 8281 <span class="w3-text w3-text-theme"> 8282 Marcely Zanon Boito, Vivek Iyer, Nikolaos Lagos, Laurent Besacier, Ioan Calapodescu 8283 </span> 8284 </p> 8285 </a> 8286 <a class="w3-text" href="lodagala24_interspeech.html"> 8287 <p> 8288 All Ears: Building Self-Supervised Learning based ASR models for Indian Languages at scale 8289 <br> 8290 <span class="w3-text w3-text-theme"> 8291 Vasista Sai Lodagala, Abhishek Biswas, Shoutrik Das, Jordan F, S Umesh 8292 </span> 8293 </p> 8294 </a> 8295 <a class="w3-text" href="jakhar24_interspeech.html"> 8296 <p> 8297 A Unified Approach to Multilingual Automatic Speech Recognition with Improved Language Identification for Indic Languages 8298 <br> 8299 <span class="w3-text w3-text-theme"> 8300 Nikhil Jakhar, Sudhanshu Srivastava, Arun Baby 8301 </span> 8302 </p> 8303 </a> 8304 <a class="w3-text" href="dong24_interspeech.html"> 8305 <p> 8306 Integrating Speech Self-Supervised Learning Models and Large Language Models for ASR 8307 <br>
8308 <span class="w3-text w3-text-theme"> 8309 Ling Dong, Zhengtao Yu, Wenjun Wang, Yuxin Huang, Shengxiang Gao, Guojiang Zhou 8310 </span> 8311 </p> 8312 </a> 8313 <a class="w3-text" href="tian24_interspeech.html"> 8314 <p> 8315 On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models 8316 <br> 8317 <span class="w3-text w3-text-theme"> 8318 Jinchuan Tian, Yifan Peng, William Chen, Kwanghee Choi, Karen Livescu, Shinji Watanabe 8319 </span> 8320 </p> 8321 </a> 8322 <a class="w3-text" href="puvvada24_interspeech.html"> 8323 <p> 8324 Less is More: Accurate Speech Recognition & Translation without Web-Scale Data 8325 <br> 8326 <span class="w3-text w3-text-theme"> 8327 Krishna C. Puvvada, Piotr Żelasko, He Huang, Oleksii Hrinchuk, Nithin Rao Koluguri, Kunal Dhawan, Somshubra Majumdar, Elena Rastorgueva, Zhehuai Chen, Vitaly Lavrukhin, Jagadeesh Balam, Boris Ginsburg 8328 </span> 8329 </p> 8330 </a> 8331 <a class="w3-text" href="paraskevopoulos24_interspeech.html"> 8332 <p> 8333 The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data 8334 <br> 8335 <span class="w3-text w3-text-theme"> 8336 Georgios Paraskevopoulos, Chara Tsoukala, Athanasios Katsamanis, Vassilis Katsouros 8337 </span> 8338 </p> 8339 </a> 8340 <a class="w3-text" href="vakirtzian24_interspeech.html"> 8341 <p> 8342 Speech Recognition for Greek Dialects: A Challenging Benchmark 8343 <br> 8344 <span class="w3-text w3-text-theme"> 8345 Socrates Vakirtzian, Chara Tsoukala, Stavros Bompolas, Katerina Mouzou, Vivian Stamou, Georgios Paraskevopoulos, Antonios Dimakis, Stella Markantonatou, Angela Ralli, Antonios Anastasopoulos 8346 </span> 8347 </p> 8348 </a> 8349 <a class="w3-text" href="liu24k_interspeech.html"> 8350 <p> 8351 LUPET: Incorporating Hierarchical Information Path into Multilingual ASR 8352 <br> 8353 <span class="w3-text w3-text-theme"> 8354 Wei Liu, Jingyong Hou, Dong Yang, Muyong Cao, Tan Lee 8355 </span> 8356 </p> 8357 </a> 8358 <a class="w3-text" href="kummervold24_interspeech.html"> 8359 <p> 8360 Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges 8361 <br> 8362 <span class="w3-text w3-text-theme"> 8363 Per E Kummervold, Javier de la Rosa, Freddy Wetjen, Rolv-Arild Braaten, Per Erik Solberg 8364 </span> 8365 </p> 8366 </a> 8367 <a class="w3-text" href="srivastava24_interspeech.html"> 8368 <p> 8369 EFFUSE: Efficient Self-Supervised Feature Fusion for E2E ASR in Low Resource and Multilingual Scenarios 8370 <br>
8371 <span class="w3-text w3-text-theme"> 8372 Tejes Srivastava, Jiatong Shi, William Chen, Shinji Watanabe 8373 </span> 8374 </p> 8375 </a> 8376 <a class="w3-text" href="hussein24_interspeech.html"> 8377 <p> 8378 Enhancing Neural Transducer for Multilingual ASR with Synchronized Language Diarization 8379 <br> 8380 <span class="w3-text w3-text-theme"> 8381 Amir Hussein, Desh Raj, Matthew Wiesner, Daniel Povey, Paola Garcia, Sanjeev Khudanpur 8382 </span> 8383 </p> 8384 </a> 8385 <a class="w3-text" href="ye24_interspeech.html"> 8386 <p> 8387 SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR 8388 <br> 8389 <span class="w3-text w3-text-theme"> 8390 Shuaishuai Ye, Shunfei Chen, Xinhui Hu, Xinkang Xu 8391 </span> 8392 </p> 8393 </a> 8394 </div> 8395 </div> 8396 <br> 8397 <div class="w3-content" style="height:10px" id="Speech Assessment"></div> 8398 <div class="w3-card w3-round w3-white w3-padding"> 8399 <div class="w3-container" style="margin-top:40px"> 8400 <h4 class="w3-center">Speech Assessment</h4> 8401 <hr> 8402 <a class="w3-text" href="wu24i_interspeech.html"> 8403 <p> 8404 Optimizing Automatic Speech Assessment: W-RankSim Regularization and Hybrid Feature Fusion Strategies 8405 <br> 8406 <span class="w3-text w3-text-theme"> 8407 Chung-Wen Wu, Berlin Chen 8408 </span> 8409 </p> 8410 </a> 8411 <a class="w3-text" href="cheng24b_interspeech.html"> 8412 <p> 8413 Context-Aware Speech Recognition Using Prompts for Language Learners 8414 <br> 8415 <span class="w3-text w3-text-theme"> 8416 Jian Cheng 8417 </span> 8418 </p> 8419 </a> 8420 <a class="w3-text" href="gothi24_interspeech.html"> 8421 <p> 8422 A Dataset and Two-pass System for Reading Miscue Detection 8423 <br> 8424 <span class="w3-text w3-text-theme"> 8425 Raj Gothi, Rahul Kumar, Mildred Pereira, Nagesh Nayak, Preeti Rao 8426 </span> 8427 </p> 8428 </a> 8429 <a class="w3-text" href="lun24_interspeech.html"> 8430 <p> 8431 Oversampling, Augmentation and Curriculum Learning for Speaking Assessment with Limited Training Data 8432 <br> 8433 <span class="w3-text w3-text-theme"> 8434 Tin Mei Lun, Ekaterina Voskoboinik, Ragheb Al-Ghezi, Tamas Grosz, Mikko Kurimo 8435 </span> 8436 </p> 8437 </a> 8438 <a class="w3-text" href="tomita24_interspeech.html"> 8439 <p> 8440 Analysis and Visualization of Directional Diversity in Listening Fluency of World Englishes Speakers in the Framework of Mutual Shadowing 8441 <br>
8442 <span class="w3-text w3-text-theme"> 8443 Yu Tomita, Yingxiang Gao, Nobuaki Minematsu, Noriko Nakanishi, Daisuke Saito 8444 </span> 8445 </p> 8446 </a> 8447 <a class="w3-text" href="robertson24_interspeech.html"> 8448 <p> 8449 Quantifying the Role of Textual Predictability in Automatic Speech Recognition 8450 <br> 8451 <span class="w3-text w3-text-theme"> 8452 Sean Robertson, Gerald Penn, Ewan Dunbar 8453 </span> 8454 </p> 8455 </a> 8456 </div> 8457 </div> 8458 <br> 8459 <div class="w3-content" style="height:10px" id="Question Answering from Speech and Spoken Dialogue Systems"></div> 8460 <div class="w3-card w3-round w3-white w3-padding"> 8461 <div class="w3-container" style="margin-top:40px"> 8462 <h4 class="w3-center">Question Answering from Speech and Spoken Dialogue Systems</h4> 8463 <hr> 8464 <a class="w3-text" href="rajkhowa24_interspeech.html"> 8465 <p> 8466 TM-PATHVQA: 90000+ Textless Multilingual Questions for Medical Visual Question Answering 8467 <br> 8468 <span class="w3-text w3-text-theme"> 8469 Tonmoy Rajkhowa, Amartya Roy Chowdhury, Sankalp Nagaonkar, Achyut Mani Tripathi, Mahadeva Prasanna 8470 </span> 8471 </p> 8472 </a> 8473 <a class="w3-text" href="phukan24_interspeech.html"> 8474 <p> 8475 Towards Multilingual Audio-Visual Question Answering 8476 <br> 8477 <span class="w3-text w3-text-theme"> 8478 Orchid Chetia Phukan, Priyabrata Mallick, Swarup Ranjan Behera, Aalekhya Satya Narayani, Arun Balaji Buduru, Rajesh Sharma 8479 </span> 8480 </p> 8481 </a> 8482 <a class="w3-text" href="nguyen24c_interspeech.html"> 8483 <p> 8484 Reinforcement Learning from Answer Reranking Feedback for Retrieval-Augmented Answer Generation 8485 <br> 8486 <span class="w3-text w3-text-theme"> 8487 Minh Nguyen, Toan Quoc Nguyen, Kishan KC, Zeyu Zhang, Thuy Vu 8488 </span> 8489 </p> 8490 </a> 8491 <a class="w3-text" href="noroozi24_interspeech.html"> 8492 <p> 8493 Instruction Data Generation and Unsupervised Adaptation for Speech Language Models 8494 <br> 8495 <span class="w3-text w3-text-theme"> 8496 Vahid Noroozi, Zhehuai Chen, Somshubra Majumdar, Steve Huang, Jagadeesh Balam, Boris Ginsburg 8497 </span> 8498 </p> 8499 </a> 8500 <a class="w3-text" href="dibratto24_interspeech.html"> 8501 <p> 8502 On the Use of Plausible Arguments in Explainable Conversational AI 8503 <br> 8504 <span class="w3-text w3-text-theme"> 8505 Martina Di Bratto, Maria Di Maro, Antonio Origlia 8506 </span> 8507 </p> 8508 </a> 8509 <a class="w3-text" href="baihaqi24_interspeech.html"> 8510 <p> 8511 Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting 8512 <br>
8513 <span class="w3-text w3-text-theme"> 8514 Muhammad Yeza Baihaqi, Angel Garcia Contreras, Seiya Kawano, Koichiro Yoshino 8515 </span> 8516 </p> 8517 </a> 8518 <a class="w3-text" href="zhou24c_interspeech.html"> 8519 <p> 8520 Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval 8521 <br> 8522 <span class="w3-text w3-text-theme"> 8523 Lifeng Zhou, Yuke Li, Rui Deng, Yuting Yang, Haoqi Zhu 8524 </span> 8525 </p> 8526 </a> 8527 </div> 8528 </div> 8529 <br> 8530 <div class="w3-content" style="height:10px" id="Spoken Dialogue Systems and Conversational Analysis 3"></div> 8531 <div class="w3-card w3-round w3-white w3-padding"> 8532 <div class="w3-container" style="margin-top:40px"> 8533 <h4 class="w3-center">Spoken Dialogue Systems and Conversational Analysis 3</h4> 8534 <hr> 8535 <a class="w3-text" href="huang24b_interspeech.html"> 8536 <p> 8537 MM-NodeFormer: Node Transformer Multimodal Fusion for Emotion Recognition in Conversation 8538 <br> 8539 <span class="w3-text w3-text-theme"> 8540 Zilong Huang, Man-Wai Mak, Kong Aik Lee 8541 </span> 8542 </p> 8543 </a> 8544 <a class="w3-text" href="shi24d_interspeech.html"> 8545 <p> 8546 Emotional Cues Extraction and Fusion for Multi-modal Emotion Prediction and Recognition in Conversation 8547 <br> 8548 <span class="w3-text w3-text-theme"> 8549 Haoxiang Shi, Ziqi Liang, Jun Yu 8550 </span> 8551 </p> 8552 </a> 8553 <a class="w3-text" href="suzuki24_interspeech.html"> 8554 <p> 8555 Participant-Pair-Wise Bottleneck Transformer for Engagement Estimation from Video Conversation 8556 <br> 8557 <span class="w3-text w3-text-theme"> 8558 Keita Suzuki, Nobukatsu Hojo, Kazutoshi Shinoda, Saki Mizuno, Ryo Masumura 8559 </span> 8560 </p> 8561 </a> 8562 <a class="w3-text" href="omahony24_interspeech.html"> 8563 <p> 8564 Well, what can you do with messy data? Exploring the prosody and pragmatic function of the discourse marker "well" with found data and speech synthesis 8565 <br> 8566 <span class="w3-text w3-text-theme"> 8567 Johannah O'Mahony, Catherine Lai, Ãva Székely 8568 </span> 8569 </p> 8570 </a> 8571 <a class="w3-text" href="shinoda24_interspeech.html"> 8572 <p> 8573 Learning from Multiple Annotator Biased Labels in Multimodal Conversation 8574 <br> 8575 <span class="w3-text w3-text-theme"> 8576 Kazutoshi Shinoda, Nobukatsu Hojo, Saki Mizuno, Keita Suzuki, Satoshi Kobashikawa, Ryo Masumura 8577 </span> 8578 </p> 8579 </a> 8580 <a class="w3-text" href="hoscilowicz24_interspeech.html"> 8581 <p> 8582 Non-Linear Inference Time Intervention: Improving LLM Truthfulness 8583 <br>
8584 <span class="w3-text w3-text-theme"> 8585 Jakub Hoscilowicz, Adam Wiacek, Jan Chojnacki, Adam Cieslak, Leszek Michon, Artur Janicki 8586 </span> 8587 </p> 8588 </a> 8589 <a class="w3-text" href="liu24c_interspeech.html"> 8590 <p> 8591 Evaluating Speech Recognition Performance Towards Large Language Model Based Voice Assistants 8592 <br> 8593 <span class="w3-text w3-text-theme"> 8594 Zhe Liu, Suyoun Kim, Ozlem Kalinli 8595 </span> 8596 </p> 8597 </a> 8598 </div> 8599 </div> 8600 <br> 8601 <div class="w3-content" style="height:10px" id="Dysarthric Speech Assessment"></div> 8602 <div class="w3-card w3-round w3-white w3-padding"> 8603 <div class="w3-container" style="margin-top:40px"> 8604 <h4 class="w3-center">Dysarthric Speech Assessment</h4> 8605 <hr> 8606 <a class="w3-text" href="zaheera24_interspeech.html"> 8607 <p> 8608 Automatic Assessment of Dysarthria using Speech and synthetically generated Electroglottograph signal 8609 <br> 8610 <span class="w3-text w3-text-theme"> 8611 Fathima Zaheera, Supritha Shetty, Gayadhar Pradhan, Deepak K T 8612 </span> 8613 </p> 8614 </a> 8615 <a class="w3-text" href="wan24b_interspeech.html"> 8616 <p> 8617 CDSD: Chinese Dysarthria Speech Database 8618 <br> 8619 <span class="w3-text w3-text-theme"> 8620 Yan Wan, Mengyi Sun, Xinchen Kang, Jingting Li, Pengfei Guo, Ming Gao, Su-Jing Wang 8621 </span> 8622 </p> 8623 </a> 8624 <a class="w3-text" href="samptur24_interspeech.html"> 8625 <p> 8626 Exploring Syllable Discriminability during Diadochokinetic Task with Increasing Dysarthria Severity for Patients with Amyotrophic Lateral Sclerosis 8627 <br> 8628 <span class="w3-text w3-text-theme"> 8629 Neelesh Samptur, Tanuka Bhattacharjee, Anirudh Chakravarty K, Seena Vengalil, Yamini Belur, Atchayaram Nalini, Prasanta Kumar Ghosh 8630 </span> 8631 </p> 8632 </a> 8633 <a class="w3-text" href="perez24_interspeech.html"> 8634 <p> 8635 Beyond Binary: Multiclass Paraphasia Detection with Generative Pretrained Transformers and End-to-End Models 8636 <br> 8637 <span class="w3-text w3-text-theme"> 8638 Matthew Perez, Aneesha Sampath, Minxue Niu, Emily Mower Provost 8639 </span> 8640 </p> 8641 </a> 8642 <a class="w3-text" href="daoudi24_interspeech.html"> 8643 <p> 8644 Electroglottography for the assessment of dysphonia in Parkinson's disease and multiple system atrophy 8645 <br> 8646 <span class="w3-text w3-text-theme"> 8647 Khalid Daoudi, Solange Milhé de Saint Victor, Alexandra Foubert-Samier, Margherita Fabbri, Anne Pavy-Le Traon, Olivier Rascol, Virginie Woisard, Wassilios G. Me
8647issner 8648 </span> 8649 </p> 8650 </a> 8651 <a class="w3-text" href="chen24t_interspeech.html"> 8652 <p> 8653 CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction 8654 <br> 8655 <span class="w3-text w3-text-theme"> 8656 Xueyuan Chen, Dongchao Yang, Dingdong Wang, Xixin Wu, Zhiyong Wu, Helen Meng 8657 </span> 8658 </p> 8659 </a> 8660 </div> 8661 </div> 8662 <br> 8663 <div class="w3-content" style="height:10px" id="Spoken Language Models for Universal Speech Processing (Special Session)"></div> 8664 <div class="w3-card w3-round w3-white w3-padding"> 8665 <div class="w3-container" style="margin-top:40px"> 8666 <h4 class="w3-center">Spoken Language Models for Universal Speech Processing (Special Session)</h4> 8667 <hr> 8668 <a class="w3-text" href="li24qa_interspeech.html"> 8669 <p> 8670 On the Effectiveness of Acoustic BPE in Decoder-Only TTS 8671 <br> 8672 <span class="w3-text w3-text-theme"> 8673 Bohan Li, Feiyu Shen, Yiwei Guo, Shuai Wang, Xie Chen, Kai Yu 8674 </span> 8675 </p> 8676 </a> 8677 <a class="w3-text" href="chang24c_interspeech.html"> 8678 <p> 8679 Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks 8680 <br> 8681 <span class="w3-text w3-text-theme"> 8682 Kai-Wei Chang, Ming-Hao Hsu, Shan-Wen Li, Hung-yi Lee 8683 </span> 8684 </p> 8685 </a> 8686 <a class="w3-text" href="kuan24_interspeech.html"> 8687 <p> 8688 Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models 8689 <br> 8690 <span class="w3-text w3-text-theme"> 8691 Chun-Yi Kuan, Wei-Ping Huang, Hung-yi Lee 8692 </span> 8693 </p> 8694 </a> 8695 <a class="w3-text" href="tang24d_interspeech.html"> 8696 <p> 8697 Can Large Language Models Understand Spatial Audio? 8698 <br> 8699 <span class="w3-text w3-text-theme"> 8700 Changli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Jun Zhang, Lu Lu, Zejun Ma, Yuxuan Wang, Chao Zhang 8701 </span> 8702 </p> 8703 </a> 8704 <a class="w3-text" href="shon24_interspeech.html"> 8705 <p> 8706 DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding 8707 <br> 8708 <span class="w3-text w3-text-theme"> 8709 Suwon Shon, Kwangyoun Kim, Yi-Te Hsu, Prashant Sridhar, Shinji Watanabe, Karen Livescu 8710 </span> 8711 </p> 8712 </a> 8713 <a class="w3-text" href="lu24c_interspeech.html"> 8714 <p> 8715 DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment 8716 <br>
8717 <span class="w3-text w3-text-theme"> 8718 Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, He Huang, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee 8719 </span> 8720 </p> 8721 </a> 8722 <a class="w3-text" href="pan24b_interspeech.html"> 8723 <p> 8724 COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning 8725 <br> 8726 <span class="w3-text w3-text-theme"> 8727 Jing Pan, Jian Wu, Yashesh Gaur, Sunit Sivasankaran, Zhuo Chen, Shujie Liu, Jinyu Li 8728 </span> 8729 </p> 8730 </a> 8731 <a class="w3-text" href="messica24_interspeech.html"> 8732 <p> 8733 NAST: Noise Aware Speech Tokenization for Speech Language Models 8734 <br> 8735 <span class="w3-text w3-text-theme"> 8736 Shoval Messica, Yossi Adi 8737 </span> 8738 </p> 8739 </a> 8740 <a class="w3-text" href="shechtman24_interspeech.html"> 8741 <p> 8742 Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer 8743 <br> 8744 <span class="w3-text w3-text-theme"> 8745 Slava Shechtman, Avihu Dekel 8746 </span> 8747 </p> 8748 </a> 8749 </div> 8750 </div> 8751 <br> 8752 <div class="w3-content" style="height:10px" id="Keynote 4"></div> 8753 <div class="w3-card w3-round w3-white w3-padding"> 8754 <div class="w3-container" style="margin-top:40px"> 8755 <h4 class="w3-center">Keynote 4</h4> 8756 <hr> 8757 <a class="w3-text" href="tillmann24_interspeech.html"> 8758 <p> 8759 Perception of music and speech: Focus on rhythm processing 8760 <br> 8761 <span class="w3-text w3-text-theme"> 8762 Barbara Tillmann 8763 </span> 8764 </p> 8765 </a> 8766 </div> 8767 </div> 8768 <br> 8769 <div class="w3-content" style="height:10px" id="L1/L2 Acquisition and Cross-Linguistic Factors"></div> 8770 <div class="w3-card w3-round w3-white w3-padding"> 8771 <div class="w3-container" style="margin-top:40px"> 8772 <h4 class="w3-center">L1/L2 Acquisition and Cross-Linguistic Factors</h4> 8773 <hr> 8774 <a class="w3-text" href="hwang24b_interspeech.html"> 8775 <p> 8776 Acquisition of high vowel devoicing in Japanese: A production experiment with three and four year olds 8777 <br> 8778 <span class="w3-text w3-text-theme"> 8779 Hyun Kyung Hwang, Manami Hirayama 8780 </span> 8781 </p> 8782 </a> 8783 <a class="w3-text" href="li24fa_interspeech.html"> 8784 <p> 8785 The Production of Contrastive Focus by 7 to 13-year-olds Learning Mandarin Chinese 8786 <br>
8787 <span class="w3-text w3-text-theme"> 8788 Zimeng Li, Zhongxuan Mao, Shengting Shen, Ivan Yuen, Ping Tang 8789 </span> 8790 </p> 8791 </a> 8792 <a class="w3-text" href="zaitova24_interspeech.html"> 8793 <p> 8794 Cross-Linguistic Intelligibility of Non-Compositional Expressions in Spoken Context 8795 <br> 8796 <span class="w3-text w3-text-theme"> 8797 Iuliia Zaitova, Irina Stenger, Wei Xue, Tania Avgustinova, Bernd Möbius, Dietrich Klakow 8798 </span> 8799 </p> 8800 </a> 8801 <a class="w3-text" href="demaere24_interspeech.html"> 8802 <p> 8803 On the relationship between speech production and vocabulary size in 3-5 year olds 8804 <br> 8805 <span class="w3-text w3-text-theme"> 8806 Alexis DeMaere, Nicole van Rootselaar, Fangfang Li, Robbin Gibb, Claudia L. R. Gonzalez 8807 </span> 8808 </p> 8809 </a> 8810 <a class="w3-text" href="polzehl24_interspeech.html"> 8811 <p> 8812 Towards Classifying Mother Tongue from Infant Cries - Findings Substantiating Prenatal Learning Theory 8813 <br> 8814 <span class="w3-text w3-text-theme"> 8815 Tim Polzehl, Tim Herzig, Friedrich Wicke, Kathleen Wermke, Razieh Khamsehashari, Michiko Dahlem, Sebastian Möller 8816 </span> 8817 </p> 8818 </a> 8819 <a class="w3-text" href="li24n_interspeech.html"> 8820 <p>
8821 Effect of Complex Boundary Tones on Tone Identification: An Experimental Study with Mandarin-speaking Preschool Children 8822 <br> 8823 <span class="w3-text w3-text-theme"> 8824 Aijun Li, Jun Gao, Zhiwei Wang 8825 </span> 8826 </p> 8827 </a> 8828 <a class="w3-text" href="truong24_interspeech.html"> 8829 <p> 8830 Ethnolinguistic Identification of Vietnamese-German Heritage Speech 8831 <br> 8832 <span class="w3-text w3-text-theme"> 8833 Thanh Lan Truong, Andrea Weber 8834 </span> 8835 </p> 8836 </a> 8837 </div> 8838 </div> 8839 <br> 8840 <div class="w3-content" style="height:10px" id="Speaker Stance, Emotion and Language-External Factors"></div> 8841 <div class="w3-card w3-round w3-white w3-padding"> 8842 <div class="w3-container" style="margin-top:40px"> 8843 <h4 class="w3-center">Speaker Stance, Emotion and Language-External Factors</h4> 8844 <hr> 8845 <a class="w3-text" href="hoffner24_interspeech.html"> 8846 <p> 8847 Joint prediction of subjective listening effort and speech intelligibility based on end-to-end learning 8848 <br> 8849 <span class="w3-text w3-text-theme"> 8850 Dirk Eike Hoffner, Jana RoÃbach, Bernd T. Meyer 8851 </span> 8852 </p> 8853 </a> 8854 <a class="w3-text" href="wu24j_interspeech.html"> 8855 <p> 8856 Depression Enhances Internal Inconsistency between Spoken and Semantic Emotion: Evidence from the Analysis of Emotion Expression in Conversation 8857 <br> 8858 <span class="w3-text w3-text-theme"> 8859 Xinyi Wu, Changqing Xu, Nan Li, Rongfeng Su, Lan Wang, Nan Yan 8860 </span> 8861 </p> 8862 </a> 8863 <a class="w3-text" href="simantiraki24_interspeech.html"> 8864 <p> 8865 Listeners' F0 preferences in quiet and stationary noise 8866 <br> 8867 <span class="w3-text w3-text-theme"> 8868 Olympia Simantiraki, Martin Cooke 8869 </span> 8870 </p> 8871 </a> 8872 <a class="w3-text" href="hodoshima24_interspeech.html"> 8873 <p>
8874 Effects of talker and playback rate of reverberation-induced speech on speech intelligibility of older adults 8875 <br> 8876 <span class="w3-text w3-text-theme"> 8877 Nao Hodoshima 8878 </span> 8879 </p> 8880 </a> 8881 </div> 8882 </div> 8883 <br> 8884 <div class="w3-content" style="height:10px" id="Experimental Phonetics and Laboratory Phonology"></div> 8885 <div class="w3-card w3-round w3-white w3-padding"> 8886 <div class="w3-container" style="margin-top:40px"> 8887 <h4 class="w3-center">Experimental Phonetics and Laboratory Phonology</h4> 8888 <hr> 8889 <a class="w3-text" href="zhao24i_interspeech.html"> 8890 <p> 8891 Age-related Differences in Acoustic Cues for the Perception of Checked Syllables in Shengzhou Wu 8892 <br> 8893 <span class="w3-text w3-text-theme"> 8894 Bingliang Zhao, Jiangping Kong, Xiyu Wu 8895 </span> 8896 </p> 8897 </a> 8898 <a class="w3-text" href="kaland24b_interspeech.html"> 8899 <p> 8900 Quantity-sensitivity affects recall performance of word stress 8901 <br> 8902 <span class="w3-text w3-text-theme"> 8903 Constantijn Kaland, Maria Lialiou 8904 </span> 8905 </p> 8906 </a> 8907 <a class="w3-text" href="tokac24_interspeech.html"> 8908 <p> 8909 Phonological Symmetry Does Not Predict Generalization of Perceptual Adaptation to Vowels 8910 <br> 8911 <span class="w3-text w3-text-theme"> 8912 Zuheyra Tokac, Jennifer Cole 8913 </span> 8914 </p> 8915 </a> 8916 <a class="w3-text" href="reitsema24_interspeech.html"> 8917 <p> 8918 Perceptual Learning in Lexical Tone: Phonetic Similarity vs. Phonological Categories 8919 <br> 8920 <span class="w3-text w3-text-theme"> 8921 Ariëlle Reitsema, Chenxin Li, Leanne van Lambalgen, Laura Preining, Saskia Galindo Jong, Qing Yang, Xinyi Wen, Yiya Chen 8922 </span> 8923 </p> 8924 </a> 8925 <a class="w3-text" href="stein24_interspeech.html"> 8926 <p> 8927 Modeling probabilistic reduction across domains with Naive Discriminative Learning 8928 <br> 8929 <span class="w3-text w3-text-theme"> 8930 Anna Stein, Kevin Tang 8931 </span> 8932 </p> 8933 </a> 8934 <a class="w3-text" href="lee24l_interspeech.html"> 8935 <p> 8936 Do we EXPECT TO find phonetic traces for syntactic traces? 8937 <br> 8938 <span class="w3-text w3-text-theme"> 8939 Jonathan Him Nok Lee, Mark Liberman, Martin Salzmann 8940 </span> 8941 </p> 8942 </a> 8943 </div> 8944 </div> 8945 <br> 8946 <div class="w3-content" style="height:10px" id="Speaker recognition evaluation and resources"></div> 8947 <div class="w3-card w3-round w3-white w3-padding"> 8948 <div class="w3-container" style="margin-top:40px"> 8949 <h4 class="w3-center">Speaker recognition evaluation and resources</h4> 8950 <hr> 8951 <a class="w3-text" href="lin24j_interspeech.html"> 8952 <p> 8953 VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark 8954 <br>
8955 <span class="w3-text w3-text-theme"> 8956 Yuke Lin, Ming Cheng, Fulin Zhang, Yingying Gao, Shilei Zhang, Ming Li 8957 </span> 8958 </p> 8959 </a> 8960 <a class="w3-text" href="hutiri24_interspeech.html"> 8961 <p> 8962 As Biased as You Measure: Methodological Pitfalls of Bias Evaluations in Speaker Verification Research 8963 <br> 8964 <span class="w3-text w3-text-theme"> 8965 Wiebke Hutiri, Tanvina Patel, Aaron Yi Ding, Odette Scharenborg 8966 </span> 8967 </p> 8968 </a> 8969 <a class="w3-text" href="wang24fa_interspeech.html"> 8970 <p> 8971 WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction 8972 <br> 8973 <span class="w3-text w3-text-theme"> 8974 Shuai Wang, Ke Zhang, Shaoxiong Lin, Junjie Li, Xuefei Wang, Meng Ge, Jianwei Yu, Yanmin Qian, Haizhou Li 8975 </span> 8976 </p> 8977 </a> 8978 <a class="w3-text" href="jung24c_interspeech.html"> 8979 <p> 8980 ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models 8981 <br> 8982 <span class="w3-text w3-text-theme"> 8983 Jee-weon Jung, Wangyou Zhang, Jiatong Shi, Zakaria Aldeneh, Takuya Higuchi, Alex Gichamba, Barry-John Theobald, Ahmed Hussen Abdelaziz, Shinji Watanabe 8984 </span> 8985 </p> 8986 </a> 8987 <a class="w3-text" href="huang24g_interspeech.html"> 8988 <p> 8989 Active Speaker Detection in Fisheye Meeting Scenes with Scene Spatial Spectrums 8990 <br> 8991 <span class="w3-text w3-text-theme"> 8992 Xinghao Huang, Weiwei Jiang, Long Rao, Wei Xu, Wenqing Cheng 8993 </span> 8994 </p> 8995 </a> 8996 <a class="w3-text" href="hoang24b_interspeech.html"> 8997 <p> 8998 VSASV: a Vietnamese Dataset for Spoofing-Aware Speaker Verification 8999 <br> 9000 <span class="w3-text w3-text-theme"> 9001 Vu Hoang, Viet Thanh Pham, Hoa Nguyen Xuan, Pham Nhi, Phuong Dat, Thi Thu Trang Nguyen 9002 </span> 9003 </p> 9004 </a> 9005 </div> 9006 </div> 9007 <br> 9008 <div class="w3-content" style="height:10px" id="Speech Type Classification"></div> 9009 <div class="w3-card w3-round w3-white w3-padding"> 9010 <div class="w3-container" style="margin-top:40px"> 9011 <h4 class="w3-center">Speech Type Classification</h4> 9012 <hr> 9013 <a class="w3-text" href="ma24_interspeech.html"> 9014 <p> 9015 E-ODN: An Emotion Open Deep Network for Generalised and Adaptive Speech Emotion Recognition 9016 <br>
9017 <span class="w3-text w3-text-theme"> 9018 Liuxian Ma, Lin Shen, Ruobing Li, Haojie Zhang, Kun Qian, Bin Hu, Björn W. Schuller, Yoshiharu Yamamoto 9019 </span> 9020 </p> 9021 </a> 9022 <a class="w3-text" href="liu24h_interspeech.html"> 9023 <p> 9024 Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment 9025 <br> 9026 <span class="w3-text w3-text-theme"> 9027 Joseph Liu, Mahesh Kumar Nandwana, Janne Pylkkönen, Hannes Heikinheimo, Morgan McGuire 9028 </span> 9029 </p> 9030 </a> 9031 <a class="w3-text" href="nafea24_interspeech.html"> 9032 <p> 9033 AraOffence: Detecting Offensive Speech Across Dialects in Arabic Media 9034 <br> 9035 <span class="w3-text w3-text-theme"> 9036 Youssef Nafea, Shady Shehata, Zeerak Talat, Ahmed Aboeitta, Ahmed Sharshar, Preslav Nakov 9037 </span> 9038 </p> 9039 </a> 9040 <a class="w3-text" href="cheng24c_interspeech.html"> 9041 <p> 9042 CogniVoice: Multimodal and Multilingual Fusion Networks for Mild Cognitive Impairment Assessment from Spontaneous Speech 9043 <br> 9044 <span class="w3-text w3-text-theme"> 9045 Jiali Cheng, Mohamed Elgaar, Nidhi Vakil, Hadi Amiri 9046 </span> 9047 </p> 9048 </a> 9049 <a class="w3-text" href="niu24b_interspeech.html"> 9050 <p> 9051 Speech Topic Classification Based on Multi-Scale and Graph Attention Networks 9052 <br> 9053 <span class="w3-text w3-text-theme"> 9054 Fangjing Niu, Xiaozhe Qi, Xinya Chen, Liang He 9055 </span> 9056 </p> 9057 </a> 9058 <a class="w3-text" href="chen24r_interspeech.html"> 9059 <p> 9060 Enhancing Speech and Music Discrimination Through the Integration of Static and Dynamic Features 9061 <br> 9062 <span class="w3-text w3-text-theme"> 9063 Liangwei Chen, Xiren Zhou, Qiang Tu, Huanhuan Chen 9064 </span> 9065 </p> 9066 </a> 9067 </div> 9068 </div> 9069 <br> 9070 <div class="w3-content" style="height:10px" id="Target Speaker Extraction"></div> 9071 <div class="w3-card w3-round w3-white w3-padding"> 9072 <div class="w3-container" style="margin-top:40px"> 9073 <h4 class="w3-center">Target Speaker Extraction</h4> 9074 <hr> 9075 <a class="w3-text" href="meng24b_interspeech.html"> 9076 <p> 9077 Binaural Selective Attention Model for Target Speaker Extraction 9078 <br> 9079 <span class="w3-text w3-text-theme"> 9080 Hanyu Meng, Qiquan Zhang, Xiangyu Zhang, Vidhyasaharan Sethu, Eliathamby Ambikairajah 9081 </span> 9082 </p> 9083 </a> 9084 <a class="w3-text" href="pandey24_interspeech.html"> 9085 <p> 9086 All Neural Low-latency Directional Speech Extraction 9087 <br>
9088 <span class="w3-text w3-text-theme"> 9089 Ashutosh Pandey, Sanha Lee, Juan Azcarreta, Daniel Wong, Buye Xu 9090 </span> 9091 </p> 9092 </a> 9093 <a class="w3-text" href="heo24_interspeech.html"> 9094 <p> 9095 Centroid Estimation with Transformer-Based Speaker Embedder for Robust Target Speaker Extraction 9096 <br> 9097 <span class="w3-text w3-text-theme"> 9098 Woon-Haeng Heo, Joongyu Maeng, Yoseb Kang, Namhyun Cho 9099 </span> 9100 </p> 9101 </a> 9102 <a class="w3-text" href="srinivas24_interspeech.html"> 9103 <p> 9104 Knowledge boosting during low-latency inference 9105 <br> 9106 <span class="w3-text w3-text-theme"> 9107 Vidya Srinivas, Malek Itani, Tuochao Chen, Emre Sefik Eskimez, Takuya Yoshioka, Shyamnath Gollakota 9108 </span> 9109 </p> 9110 </a> 9111 <a class="w3-text" href="wu24h_interspeech.html"> 9112 <p> 9113 Unified Audio Visual Cues for Target Speaker Extraction 9114 <br> 9115 <span class="w3-text w3-text-theme"> 9116 Tianci Wu, Shulin He, Jiahui Pan, Haifeng Huang, Zhijian Mo, Xueliang Zhang 9117 </span> 9118 </p> 9119 </a> 9120 <a class="w3-text" href="liu24j_interspeech.html"> 9121 <p> 9122 Target Speaker Extraction with Curriculum Learning 9123 <br> 9124 <span class="w3-text w3-text-theme"> 9125 Yun Liu, Xuechen Liu, Xiaoxiao Miao, Junichi Yamagishi 9126 </span> 9127 </p> 9128 </a> 9129 </div> 9130 </div> 9131 <br> 9132 <div class="w3-content" style="height:10px" id="Speech Synthesis: Voice Conversion 3"></div> 9133 <div class="w3-card w3-round w3-white w3-padding"> 9134 <div class="w3-container" style="margin-top:40px"> 9135 <h4 class="w3-center">Speech Synthesis: Voice Conversion 3</h4> 9136 <hr> 9137 <a class="w3-text" href="bai24_interspeech.html"> 9138 <p> 9139 SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion 9140 <br> 9141 <span class="w3-text w3-text-theme"> 9142 Bingsong Bai, Fengping Wang, Yingming Gao, Ya Li 9143 </span> 9144 </p> 9145 </a> 9146 <a class="w3-text" href="salman24_interspeech.html"> 9147 <p> 9148 Towards Naturalistic Voice Conversion: NaturalVoices Dataset with an Automatic Processing Pipeline 9149 <br> 9150 <span class="w3-text w3-text-theme"> 9151 Ali N. Salman, Zongyang Du, Shreeram Suresh Chandra, İsmail Rasim Ãlgen, Carlos Busso, Berrak Sisman 9152 </span> 9153 </p> 9154 </a> 9155 <a class="w3-text" href="tanaka24_interspeech.html"> 9156 <p> 9157 PRVAE-VC2: Non-Parallel Voice Conversion by Distillation of Speech Representations 9158 <br>
9159 <span class="w3-text w3-text-theme"> 9160 Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Yuto Kondo 9161 </span> 9162 </p> 9163 </a> 9164 <a class="w3-text" href="niu24_interspeech.html"> 9165 <p> 9166 HybridVC: Efficient Voice Style Conversion with Text and Audio Prompts 9167 <br> 9168 <span class="w3-text w3-text-theme"> 9169 Xinlei Niu, Jing Zhang, Charles Patrick Martin 9170 </span> 9171 </p> 9172 </a> 9173 <a class="w3-text" href="hai24_interspeech.html"> 9174 <p> 9175 DreamVoice: Text-Guided Voice Conversion 9176 <br> 9177 <span class="w3-text w3-text-theme"> 9178 Jiarui Hai, Karan Thakkar, Helin Wang, Zengyi Qin, Mounya Elhilali 9179 </span> 9180 </p> 9181 </a> 9182 <a class="w3-text" href="lee24d_interspeech.html"> 9183 <p> 9184 Hear Your Face: Face-based voice conversion with F0 estimation 9185 <br> 9186 <span class="w3-text w3-text-theme"> 9187 Jaejun Lee, Yoori Oh, Injune Hwang, Kyogu Lee 9188 </span> 9189 </p> 9190 </a> 9191 <a class="w3-text" href="siriwardena24_interspeech.html"> 9192 <p> 9193 Accent Conversion with Articulatory Representations 9194 <br> 9195 <span class="w3-text w3-text-theme"> 9196 Yashish M. Siriwardena, Nathan Swedlow, Audrey Howard, Evan Gitterman, Dan Darcy, Carol Espy-Wilson, Andrea Fanelli 9197 </span> 9198 </p> 9199 </a> 9200 <a class="w3-text" href="huang24e_interspeech.html"> 9201 <p> 9202 USD-AC: Unsupervised Speech Disentanglement for Accent Conversion 9203 <br> 9204 <span class="w3-text w3-text-theme"> 9205 Jen-Hung Huang, Wei-Tsung Lee, Chung-Hsien Wu 9206 </span> 9207 </p> 9208 </a> 9209 <a class="w3-text" href="kanagawa24b_interspeech.html"> 9210 <p> 9211 Knowledge Distillation from Self-Supervised Representation Learning Model with Discrete Speech Units for Any-to-Any Streaming Voice Conversion 9212 <br> 9213 <span class="w3-text w3-text-theme"> 9214 Hiroki Kanagawa, Yusuke Ijima 9215 </span> 9216 </p> 9217 </a> 9218 </div> 9219 </div> 9220 <br> 9221 <div class="w3-content" style="height:10px" id="Speech Synthesis: Paradigms and Methods 3"></div> 9222 <div class="w3-card w3-round w3-white w3-padding"> 9223 <div class="w3-container" style="margin-top:40px"> 9224 <h4 class="w3-center">Speech Synthesis: Paradigms and Methods 3</h4> 9225 <hr> 9226 <a class="w3-text" href="yang24l_interspeech.html"> 9227 <p> 9228 SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models 9229 <br>
9230 <span class="w3-text w3-text-theme"> 9231 Dongchao Yang, Dingdong Wang, Haohan Guo, Xueyuan Chen, Xixin Wu, Helen Meng 9232 </span> 9233 </p> 9234 </a> 9235 <a class="w3-text" href="lovelace24_interspeech.html"> 9236 <p> 9237 Sample-Efficient Diffusion for Text-To-Speech Synthesis 9238 <br> 9239 <span class="w3-text w3-text-theme"> 9240 Justin Lovelace, Soham Ray, Kwangyoun Kim, Kilian Q. Weinberger, Felix Wu 9241 </span> 9242 </p> 9243 </a> 9244 <a class="w3-text" href="feng24d_interspeech.html"> 9245 <p> 9246 Exploring the Robustness of Text-to-Speech Synthesis Based on Diffusion Probabilistic Models to Heavily Noisy Transcriptions 9247 <br> 9248 <span class="w3-text w3-text-theme"> 9249 Jingyi Feng, Yusuke Yasuda, Tomoki Toda 9250 </span> 9251 </p> 9252 </a> 9253 <a class="w3-text" href="kim24_interspeech.html"> 9254 <p> 9255 VoiceTailor: Lightweight Plug-In Adapter for Diffusion-Based Personalized Text-to-Speech 9256 <br> 9257 <span class="w3-text w3-text-theme"> 9258 Heeseung Kim, Sang-gil Lee, Jiheum Yeom, Che Hyun Lee, Sungwon Kim, Sungroh Yoon 9259 </span> 9260 </p> 9261 </a> 9262 <a class="w3-text" href="sadekova24_interspeech.html"> 9263 <p> 9264 PitchFlow: adding pitch control to a Flow-matching based TTS model 9265 <br> 9266 <span class="w3-text w3-text-theme"> 9267 Tasnima Sadekova, Mikhail Kudinov, Vadim Popov, Assel Yermekova, Artem Khrapov 9268 </span> 9269 </p> 9270 </a> 9271 <a class="w3-text" href="yang24q_interspeech.html"> 9272 <p> 9273 DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance 9274 <br> 9275 <span class="w3-text w3-text-theme"> 9276 Jinhyeok Yang, Junhyeok Lee, Hyeong-Seok Choi, Seunghoon Ji, Hyeongju Kim, Juheon Lee 9277 </span> 9278 </p> 9279 </a> 9280 <a class="w3-text" href="chen24q_interspeech.html"> 9281 <p> 9282 Generating Speakers by Prompting Listener Impressions for Pre-trained Multi-Speaker Text-to-Speech Systems 9283 <br> 9284 <span class="w3-text w3-text-theme"> 9285 Zhengyang Chen, Xuechen Liu, Erica Cooper, Junichi Yamagishi, Yanmin Qian 9286 </span> 9287 </p> 9288 </a> 9289 <a class="w3-text" href="song24b_interspeech.html"> 9290 <p> 9291 TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers 9292 <br>
9293 <span class="w3-text w3-text-theme"> 9294 Yakun Song, Zhuo Chen, Xiaofei Wang, Ziyang Ma, Guanrou Yang, Xie Chen 9295 </span> 9296 </p> 9297 </a> 9298 </div> 9299 </div> 9300 <br> 9301 <div class="w3-content" style="height:10px" id="Privacy and Security in Speech Communication 2"></div> 9302 <div class="w3-card w3-round w3-white w3-padding"> 9303 <div class="w3-container" style="margin-top:40px"> 9304 <h4 class="w3-center">Privacy and Security in Speech Communication 2</h4> 9305 <hr> 9306 <a class="w3-text" href="ghosh24_interspeech.html"> 9307 <p> 9308 Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Example 9309 <br> 9310 <span class="w3-text w3-text-theme"> 9311 Suhita Ghosh, Melanie Jouaiti, Arnab Das, Yamini Sinha, Tim Polzehl, Ingo Siegert, Sebastian Stober 9312 </span> 9313 </p> 9314 </a> 9315 <a class="w3-text" href="wang24ha_interspeech.html"> 9316 <p> 9317 Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding 9318 <br> 9319 <span class="w3-text w3-text-theme"> 9320 Rui Wang, Liping Chen, Kong Aik Lee, Zhen-Hua Ling 9321 </span> 9322 </p> 9323 </a> 9324 <a class="w3-text" href="meyer24_interspeech.html"> 9325 <p> 9326 Probing the Feasibility of Multilingual Speaker Anonymization 9327 <br> 9328 <span class="w3-text w3-text-theme"> 9329 Sarina Meyer, Florian Lux, Ngoc Thang Vu 9330 </span> 9331 </p> 9332 </a> 9333 <a class="w3-text" href="huang24_interspeech.html"> 9334 <p> 9335 DiffVC+: Improving Diffusion-based Voice Conversion for Speaker Anonymization 9336 <br> 9337 <span class="w3-text w3-text-theme"> 9338 Fan Huang, Kun Zeng, Wei Zhu 9339 </span> 9340 </p> 9341 </a> 9342 </div> 9343 </div> 9344 <br> 9345 <div class="w3-content" style="height:10px" id="Streaming ASR"></div> 9346 <div class="w3-card w3-round w3-white w3-padding"> 9347 <div class="w3-container" style="margin-top:40px"> 9348 <h4 class="w3-center">Streaming ASR</h4> 9349 <hr> 9350 <a class="w3-text" href="yang24m_interspeech.html"> 9351 <p> 9352 Learning from Back Chunks: Acquiring More Future Knowledge for Streaming ASR Models via Self Distillation 9353 <br> 9354 <span class="w3-text w3-text-theme"> 9355 Yuting Yang, Guodong Ma, Yuke Li, Binbin Du, Haoqi Zhu, Liang Ruan 9356 </span> 9357 </p> 9358 </a> 9359 <a class="w3-text" href="tsunoo24_interspeech.html"> 9360 <p> 9361 Decoder-only Architecture for Streaming End-to-end Speech Recognition 9362 <br>
9363 <span class="w3-text w3-text-theme"> 9364 Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe 9365 </span> 9366 </p> 9367 </a> 9368 <a class="w3-text" href="chen24u_interspeech.html"> 9369 <p> 9370 Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study 9371 <br> 9372 <span class="w3-text w3-text-theme"> 9373 Peikun Chen, Sining Sun, Changhao Shan, Qing Yang, Lei Xie 9374 </span> 9375 </p> 9376 </a> 9377 <a class="w3-text" href="heitkaemper24_interspeech.html"> 9378 <p> 9379 TfCleanformer: A streaming, array-agnostic, full- and sub-band modeling front-end for robust ASR 9380 <br> 9381 <span class="w3-text w3-text-theme"> 9382 Jens Heitkaemper, Joe Caroselli, Arun Narayanan, Nathan Howard 9383 </span> 9384 </p> 9385 </a> 9386 <a class="w3-text" href="le24_interspeech.html"> 9387 <p> 9388 Improving Streaming Speech Recognition With Time-Shifted Contextual Attention And Dynamic Right Context Masking 9389 <br> 9390 <span class="w3-text w3-text-theme"> 9391 Khanh Le, Duc Chau 9392 </span> 9393 </p> 9394 </a> 9395 <a class="w3-text" href="wang24ea_interspeech.html"> 9396 <p> 9397 Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection 9398 <br> 9399 <span class="w3-text w3-text-theme"> 9400 Haoyu Wang, Guoqiang Hu, Guodong Lin, Wei-Qiang Zhang, Jian Li 9401 </span> 9402 </p> 9403 </a> 9404 </div> 9405 </div> 9406 <br> 9407 <div class="w3-content" style="height:10px" id="Computational Resource Constrained ASR"></div> 9408 <div class="w3-card w3-round w3-white w3-padding"> 9409 <div class="w3-container" style="margin-top:40px"> 9410 <h4 class="w3-center">Computational Resource Constrained ASR</h4> 9411 <hr> 9412 <a class="w3-text" href="xiao24b_interspeech.html"> 9413 <p> 9414 Dynamic Data Pruning for Automatic Speech Recognition 9415 <br> 9416 <span class="w3-text w3-text-theme"> 9417 Qiao Xiao, Pingchuan Ma, Adriana Fernandez-Lopez, Boqian Wu, Lu Yin, Stavros Petridis, Mykola Pechenizkiy, Maja Pantic, Decebal Constantin Mocanu, Shiwei Liu 9418 </span> 9419 </p> 9420 </a> 9421 <a class="w3-text" href="kim24k_interspeech.html"> 9422 <p> 9423 Mitigating Overfitting in Structured Pruning of ASR Models with Gradient-Guided Parameter Regularization 9424 <br> 9425 <span class="w3-text w3-text-theme"> 9426 Dong-Hyun Kim, Joon-Hyuk Chang 9427 </span> 9428 </p> 9429 </a> 9430 <a class="w3-text" href="gu24_interspeech.html"> 9431 <p> 9432 SparseWAV: Fast and Accurate One-Shot Unstructured Pruning for Large Speech Foundation Models 9433 <br>
9434 <span class="w3-text w3-text-theme"> 9435 Tianteng Gu, Bei Liu, Hang Shao, Yanmin Qian 9436 </span> 9437 </p> 9438 </a> 9439 <a class="w3-text" href="li24o_interspeech.html"> 9440 <p> 9441 One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model 9442 <br> 9443 <span class="w3-text w3-text-theme"> 9444 Zhaoqing Li, Haoning Xu, Tianzi Wang, Shoukang Hu, Zengrui Jin, Shujie Hu, Jiajun Deng, Mingyu Cui, Mengzhe Geng, Xunying Liu 9445 </span> 9446 </p> 9447 </a> 9448 <a class="w3-text" href="rybakov24_interspeech.html"> 9449 <p> 9450 USM RNN-T model weights binarization 9451 <br> 9452 <span class="w3-text w3-text-theme"> 9453 Oleg Rybakov, Dmitriy Serdyuk, Chengjian Zheng 9454 </span> 9455 </p> 9456 </a> 9457 <a class="w3-text" href="lin24d_interspeech.html"> 9458 <p> 9459 DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Models 9460 <br> 9461 <span class="w3-text w3-text-theme"> 9462 Tzu-Quan Lin, Hung-yi Lee, Hao Tang 9463 </span> 9464 </p> 9465 </a> 9466 <a class="w3-text" href="park24_interspeech.html"> 9467 <p> 9468 RepTor: Re-parameterizable Temporal Convolution for Keyword Spotting via Differentiable Kernel Search 9469 <br> 9470 <span class="w3-text w3-text-theme"> 9471 Eunik Park, Daehyun Ahn, Hyungjun Kim 9472 </span> 9473 </p> 9474 </a> 9475 <a class="w3-text" href="wang24p_interspeech.html"> 9476 <p> 9477 Global-Local Convolution with Spiking Neural Networks for Energy-efficient Keyword Spotting 9478 <br> 9479 <span class="w3-text w3-text-theme"> 9480 Shuai Wang, Dehao Zhang, Kexin Shi, Yuchen Wang, Wenjie Wei, Jibin Wu, Malu Zhang 9481 </span> 9482 </p> 9483 </a> 9484 <a class="w3-text" href="song24c_interspeech.html"> 9485 <p> 9486 ED-sKWS: Early-Decision Spiking Neural Networks for Rapid, and Energy-Efficient Keyword Spotting 9487 <br> 9488 <span class="w3-text w3-text-theme"> 9489 Zeyang Song, Qianhui Liu, Qu Yang, Yizhou Peng, Haizhou Li 9490 </span> 9491 </p> 9492 </a> 9493 <a class="w3-text" href="ling24_interspeech.html"> 9494 <p> 9495 A Small and Fast BERT for Chinese Medical Punctuation Restoration 9496 <br> 9497 <span class="w3-text w3-text-theme"> 9498 Tongtao Ling, Yutao Lai, Lei Chen, Shilei Huang, Yi Liu 9499 </span> 9500 </p> 9501 </a> 9502 </div> 9503 </div> 9504 <br> 9505 <div class="w3-content" style="height:10px" id="Evaluation of Speech Technology Systems"></div> 9506 <div class="w3-card w3-round w3-white w3-padding"> 9507 <div class="w3-container" style="margin-top:40px"> 9508 <h4 class="w3-center">Evaluation of Speech Technology Systems</h4> 9509 <hr> 9510 <a class="w3-text" href="heuser24_interspeech.html"> 9511 <p> 9512 Quantification of stylistic differences in human- and ASR-produced transcripts of African American English 9513 <br>
9514 <span class="w3-text w3-text-theme"> 9515 Annika Heuser, Tyler Kendall, Miguel del Rio, Quinn McNamara, Nishchal Bhandari, Corey Miller, Migüel Jetté 9516 </span> 9517 </p> 9518 </a> 9519 <a class="w3-text" href="kuhn24_interspeech.html"> 9520 <p> 9521 Beyond Levenshtein: Leveraging Multiple Algorithms for Robust Word Error Rate Computations And Granular Error Classifications 9522 <br> 9523 <span class="w3-text w3-text-theme"> 9524 Korbinian Kuhn, Verena Kersken, Gottfried Zimmermann 9525 </span> 9526 </p> 9527 </a> 9528 <a class="w3-text" href="teleki24_interspeech.html"> 9529 <p> 9530 Comparing ASR Systems in the Context of Speech Disfluencies 9531 <br> 9532 <span class="w3-text w3-text-theme"> 9533 Maria Teleki, Xiangjue Dong, Soohwan Kim, James Caverlee 9534 </span> 9535 </p> 9536 </a> 9537 <a class="w3-text" href="lu24d_interspeech.html"> 9538 <p> 9539 Deep Prosodic Features in Tandem with Perceptual Judgments of Word Reduction for Tone Recognition in Conversed Speech 9540 <br> 9541 <span class="w3-text w3-text-theme"> 9542 Xiang-Li Lu, Yi-Fen Liu 9543 </span> 9544 </p> 9545 </a> 9546 <a class="w3-text" href="sasindran24_interspeech.html"> 9547 <p> 9548 SeMaScore: A new evaluation metric for automatic speech recognition tasks 9549 <br> 9550 <span class="w3-text w3-text-theme"> 9551 Zitha Sasindran, Harsha Yelchuri, T. V. Prabhakar 9552 </span> 9553 </p> 9554 </a> 9555 </div> 9556 </div> 9557 <br> 9558 <div class="w3-content" style="height:10px" id="Neural Network Training for Speech Recognition"></div> 9559 <div class="w3-card w3-round w3-white w3-padding"> 9560 <div class="w3-container" style="margin-top:40px"> 9561 <h4 class="w3-center">Neural Network Training for Speech Recognition</h4> 9562 <hr> 9563 <a class="w3-text" href="xu24_interspeech.html"> 9564 <p> 9565 Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition 9566 <br> 9567 <span class="w3-text w3-text-theme"> 9568 Jingjing Xu, Wei Zhou, Zijian Yang, Eugen Beck, Ralf Schlüter 9569 </span> 9570 </p> 9571 </a> 9572 <a class="w3-text" href="hou24_interspeech.html"> 9573 <p> 9574 Revisiting Convolution-free Transformer for Speech Recognition 9575 <br> 9576 <span class="w3-text w3-text-theme"> 9577 Zejiang Hou, Goeric Huybrechts, Anshu Bhatia, Daniel Garcia-Romero, Kyu J. Han, Katrin Kirchhoff 9578 </span> 9579 </p> 9580 </a> 9581 <a class="w3-text" href="huang24c_interspeech.html"> 9582 <p> 9583 Optimizing Large-Scale Context Retrieval for End-to-End ASR 9584 <br>
9585 <span class="w3-text w3-text-theme"> 9586 Zhiqi Huang, Diamantino Caseiro, Kandarp Joshi, Christopher Li, Pat Rondon, Zelin Wu, Petr Zadrazil, Lillian Zhou 9587 </span> 9588 </p> 9589 </a> 9590 <a class="w3-text" href="choi24b_interspeech.html"> 9591 <p> 9592 Self-Supervised Speech Representations are More Phonetic than Semantic 9593 <br> 9594 <span class="w3-text w3-text-theme"> 9595 Kwanghee Choi, Ankita Pasad, Tomohiko Nakamura, Satoru Fukayama, Karen Livescu, Shinji Watanabe 9596 </span> 9597 </p> 9598 </a> 9599 <a class="w3-text" href="han24_interspeech.html"> 9600 <p> 9601 Enhancing CTC-based speech recognition with diverse modeling units 9602 <br> 9603 <span class="w3-text w3-text-theme"> 9604 Shiyi Han, Mingbin Xu, Zhihong Lei, Zhen Huang, Xingyu Na 9605 </span> 9606 </p> 9607 </a> 9608 <a class="w3-text" href="kim24d_interspeech.html"> 9609 <p> 9610 Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation 9611 <br> 9612 <span class="w3-text w3-text-theme"> 9613 Eungbeom Kim, Hantae Kim, Kyogu Lee 9614 </span> 9615 </p> 9616 </a> 9617 </div> 9618 </div> 9619 <br> 9620 <div class="w3-content" style="height:10px" id="Leveraging Large Language Models and Contextual Features for Phonetic Analysis (Special Session)"></div> 9621 <div class="w3-card w3-round w3-white w3-padding"> 9622 <div class="w3-container" style="margin-top:40px"> 9623 <h4 class="w3-center">Leveraging Large Language Models and Contextual Features for Phonetic Analysis (Special Session)</h4> 9624 <hr> 9625 <a class="w3-text" href="deheerkloots24_interspeech.html"> 9626 <p> 9627 Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0 9628 <br> 9629 <span class="w3-text w3-text-theme"> 9630 Marianne de Heer Kloots, Willem Zuidema 9631 </span> 9632 </p> 9633 </a> 9634 <a class="w3-text" href="lin24e_interspeech.html"> 9635 <p> 9636 Exploring Pre-trained Speech Model for Articulatory Feature Extraction in Dysarthric Speech Using ASR 9637 <br> 9638 <span class="w3-text w3-text-theme"> 9639 Yuqin Lin, Longbiao Wang, Jianwu Dang, Nobuaki Minematsu 9640 </span> 9641 </p> 9642 </a> 9643 <a class="w3-text" href="hao24c_interspeech.html"> 9644 <p> 9645 Exploring Self-Supervised Speech Representations for Cross-lingual Acoustic-to-Articulatory Inversion 9646 <br> 9647 <span class="w3-text w3-text-theme"> 9648 Yun Hao, Reihaneh Amooie, Wietse de Vries, Thomas Tienkamp, Rik van Noord, Martijn Wieling 9649 </span> 9650 </p> 9651 </a> 9652 <a class="w3-text" href="shams24_interspeech.html"> 9653 <p> 9654 Are Articulatory Feature Overlaps Shrouded in Speech Embeddings? 9655 <br>
9656 <span class="w3-text w3-text-theme"> 9657 Erfan A. Shams, Iona Gessinger, Patrick Cormac English, Julie Carson-Berndsen 9658 </span> 9659 </p> 9660 </a> 9661 <a class="w3-text" href="english24_interspeech.html"> 9662 <p> 9663 Searching for Structure: Appraising the Organisation of Speech Features in wav2vec 2.0 Embeddings 9664 <br> 9665 <span class="w3-text w3-text-theme"> 9666 Patrick Cormac English, John D. Kelleher, Julie Carson-Berndsen 9667 </span> 9668 </p> 9669 </a> 9670 </div> 9671 </div> 9672 <br> 9673 <div class="w3-content" style="height:10px" id="Responsible Speech Foundation Models (Special Session)"></div> 9674 <div class="w3-card w3-round w3-white w3-padding"> 9675 <div class="w3-container" style="margin-top:40px"> 9676 <h4 class="w3-center">Responsible Speech Foundation Models (Special Session)</h4> 9677 <hr> 9678 <a class="w3-text" href="wiepert24_interspeech.html"> 9679 <p> 9680 Speech foundation models in healthcare: Effect of layer selection on pathological speech feature prediction 9681 <br> 9682 <span class="w3-text w3-text-theme"> 9683 Daniela A. Wiepert, Rene L. Utianski, Joseph R. Duffy, John L. Stricker, Leland R. Barnard, David T. Jones, Hugo Botha 9684 </span> 9685 </p> 9686 </a> 9687 <a class="w3-text" href="wagner24_interspeech.html"> 9688 <p> 9689 Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models 9690 <br> 9691 <span class="w3-text w3-text-theme"> 9692 Dominik Wagner, Ilja Baumann, Korbinian Riedhammer, Tobias Bocklet 9693 </span> 9694 </p> 9695 </a> 9696 <a class="w3-text" href="kulkarni24_interspeech.html"> 9697 <p> 9698 Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems 9699 <br> 9700 <span class="w3-text w3-text-theme"> 9701 Ajinkya Kulkarni, Atharva Kulkarni, Miguel Couceiro, Isabel Trancoso 9702 </span> 9703 </p> 9704 </a> 9705 <a class="w3-text" href="lin24i_interspeech.html"> 9706 <p> 9707 Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition 9708 <br> 9709 <span class="w3-text w3-text-theme"> 9710 Yi-Cheng Lin, Haibin Wu, Huang-Cheng Chou, Chi-Chun Lee, Hung-yi Lee 9711 </span> 9712 </p> 9713 </a> 9714 <a class="w3-text" href="lin24b_interspeech.html"> 9715 <p> 9716 On the social bias of speech self-supervised models 9717 <br>
9718 <span class="w3-text w3-text-theme"> 9719 Yi-Cheng Lin, Tzu-Quan Lin, Hsi-Che Lin, Andy T. Liu, Hung-yi Lee 9720 </span> 9721 </p> 9722 </a> 9723 <a class="w3-text" href="chang24d_interspeech.html"> 9724 <p> 9725 Self-supervised Speech Representations Still Struggle with African American Vernacular English 9726 <br> 9727 <span class="w3-text w3-text-theme"> 9728 Kalvin Chang, Yi-Hui Chou, Jiatong Shi, Hsuan-Ming Chen, Nicole Holliday, Odette Scharenborg, David R. Mortensen 9729 </span> 9730 </p> 9731 </a> 9732 <a class="w3-text" href="aldeneh24_interspeech.html"> 9733 <p> 9734 Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features? 9735 <br> 9736 <span class="w3-text w3-text-theme"> 9737 Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Skyler Seto, Tatiana Likhomanenko, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Barry-John Theobald 9738 </span> 9739 </p> 9740 </a> 9741 <a class="w3-text" href="meng24c_interspeech.html"> 9742 <p> 9743 Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System 9744 <br> 9745 <span class="w3-text w3-text-theme"> 9746 Lingwei Meng, Jiawen Kang, Yuejiao Wang, Zengrui Jin, Xixin Wu, Xunying Liu, Helen Meng 9747 </span> 9748 </p> 9749 </a> 9750 </div> 9751 </div> 9752 <br> 9753 <div class="w3-content" style="height:10px" id="Multimodal Paralinguistics"></div> 9754 <div class="w3-card w3-round w3-white w3-padding"> 9755 <div class="w3-container" style="margin-top:40px"> 9756 <h4 class="w3-center">Multimodal Paralinguistics</h4> 9757 <hr> 9758 <a class="w3-text" href="cai24b_interspeech.html"> 9759 <p> 9760 LoRA-MER: Low-Rank Adaptation of Pre-Trained Speech Models for Multimodal Emotion Recognition Using Mutual Information 9761 <br> 9762 <span class="w3-text w3-text-theme"> 9763 Yunrui Cai, Zhiyong Wu, Jia Jia, Helen Meng 9764 </span> 9765 </p> 9766 </a> 9767 <a class="w3-text" href="li24z_interspeech.html"> 9768 <p> 9769 Enhancing Modal Fusion by Alignment and Label Matching for Multimodal Emotion Recognition 9770 <br> 9771 <span class="w3-text w3-text-theme"> 9772 Qifei Li, Yingming Gao, Yuhua Wen, Cong Wang, Ya Li 9773 </span> 9774 </p> 9775 </a> 9776 <a class="w3-text" href="zhu24_interspeech.html"> 9777 <p> 9778 Prompt Link Multimodal Fusion in Multimodal Sentiment Analysis 9779 <br> 9780 <span class="w3-text w3-text-theme"> 9781 Kang Zhu, Cunhang Fan, Jianhua Tao, Zhao Lv 9782 </span> 9783 </p> 9784 </a> 9785 <a class="w3-text" href="wang24r_interspeech.html"> 9786 <p> 9787 A multimodal analysis of different types of laughter expression in conversational dialogues 9788 <br>
9789 <span class="w3-text w3-text-theme"> 9790 Kexin Wang, Carlos Ishi, Ryoko Hayashi 9791 </span> 9792 </p> 9793 </a> 9794 <a class="w3-text" href="chochlakis24_interspeech.html"> 9795 <p> 9796 Tackling Missing Modalities in Audio-Visual Representation Learning Using Masked Autoencoders 9797 <br> 9798 <span class="w3-text w3-text-theme"> 9799 Georgios Chochlakis, Chandrashekhar Lavania, Prashant Mathur, Kyu J. Han 9800 </span> 9801 </p> 9802 </a> 9803 <a class="w3-text" href="kyung24_interspeech.html"> 9804 <p> 9805 Enhancing Multimodal Emotion Recognition through ASR Error Compensation and LLM Fine-Tuning 9806 <br> 9807 <span class="w3-text w3-text-theme"> 9808 Jehyun Kyung, Serin Heo, Joon-Hyuk Chang 9809 </span> 9810 </p> 9811 </a> 9812 <a class="w3-text" href="goncalves24_interspeech.html"> 9813 <p> 9814 Bridging Emotions Across Languages: Low Rank Adaptation for Multilingual Speech Emotion Recognition 9815 <br> 9816 <span class="w3-text w3-text-theme"> 9817 Lucas Goncalves, Donita Robinson, Elizabeth Richerson, Carlos Busso 9818 </span> 9819 </p> 9820 </a> 9821 </div> 9822 </div> 9823 <br> 9824 <div class="w3-content" style="height:10px" id="Automatic Emotion Recognition"></div> 9825 <div class="w3-card w3-round w3-white w3-padding"> 9826 <div class="w3-container" style="margin-top:40px"> 9827 <h4 class="w3-center">Automatic Emotion Recognition</h4> 9828 <hr> 9829 <a class="w3-text" href="upadhyay24_interspeech.html"> 9830 <p> 9831 A Layer-Anchoring Strategy for Enhancing Cross-Lingual Speech Emotion Recognition 9832 <br> 9833 <span class="w3-text w3-text-theme"> 9834 Shreya G. Upadhyay, Carlos Busso, Chi-Chun Lee 9835 </span> 9836 </p> 9837 </a> 9838 <a class="w3-text" href="phukan24b_interspeech.html"> 9839 <p> 9840 Are Paralinguistic Representations all that is needed for Speech Emotion Recognition? 9841 <br> 9842 <span class="w3-text w3-text-theme"> 9843 Orchid Chetia Phukan, Gautam Siddharth Kashyap, Arun Balaji Buduru, Rajesh Sharma 9844 </span> 9845 </p> 9846 </a> 9847 <a class="w3-text" href="sun24b_interspeech.html"> 9848 <p> 9849 MFSN: Multi-perspective Fusion Search Network For Pre-training Knowledge in Speech Emotion Recognition 9850 <br> 9851 <span class="w3-text w3-text-theme"> 9852 Haiyang Sun, Fulin Zhang, Yingying Gao, Shilei Zhang, Zheng Lian, Junlan Feng 9853 </span> 9854 </p> 9855 </a> 9856 <a class="w3-text" href="khaertdinov24_interspeech.html"> 9857 <p> 9858 Exploring Self-Supervised Multi-view Contrastive Learning for Speech Emotion Recognition with Limited Annotations 9859 <br>
9860 <span class="w3-text w3-text-theme"> 9861 Bulat Khaertdinov, Pedro Jeruis, Annanda Sousa, Enrique Hortal 9862 </span> 9863 </p> 9864 </a> 9865 </div> 9866 </div> 9867 <br> 9868 <div class="w3-content" style="height:10px" id="Self and Weakly-Labelled Speaker Verification"></div> 9869 <div class="w3-card w3-round w3-white w3-padding"> 9870 <div class="w3-container" style="margin-top:40px"> 9871 <h4 class="w3-center">Self and Weakly-Labelled Speaker Verification</h4> 9872 <hr> 9873 <a class="w3-text" href="wang24z_interspeech.html"> 9874 <p> 9875 Self-Supervised Speaker Verification with Mini-Batch Prediction Correction 9876 <br> 9877 <span class="w3-text w3-text-theme"> 9878 Junxu Wang, Zhihua Fang, Liang He 9879 </span> 9880 </p> 9881 </a> 9882 <a class="w3-text" href="li24q_interspeech.html"> 9883 <p> 9884 SCDNet: Self-supervised Learning Feature based Speaker Change Detection 9885 <br> 9886 <span class="w3-text w3-text-theme"> 9887 Yue Li, Xinsheng Wang, Li Zhang, Lei Xie 9888 </span> 9889 </p> 9890 </a> 9891 <a class="w3-text" href="jin24c_interspeech.html"> 9892 <p> 9893 Self-Supervised Learning with Multi-Head Multi-Mode Knowledge Distillation for Speaker Verification 9894 <br> 9895 <span class="w3-text w3-text-theme"> 9896 Zezhong Jin, Youzhi Tu, Man-Wai Mak 9897 </span> 9898 </p> 9899 </a> 9900 <a class="w3-text" href="selvakumar24_interspeech.html"> 9901 <p> 9902 Getting More for Less: Using Weak Labels and AV-Mixup for Robust Audio-Visual Speaker Verification 9903 <br> 9904 <span class="w3-text w3-text-theme"> 9905 Anith Selvakumar, Homa Fashandi 9906 </span> 9907 </p> 9908 </a> 9909 </div> 9910 </div> 9911 <br> 9912 <div class="w3-content" style="height:10px" id="Acoustic Event Detection, Segmentation and Classification"></div> 9913 <div class="w3-card w3-round w3-white w3-padding"> 9914 <div class="w3-container" style="margin-top:40px"> 9915 <h4 class="w3-center">Acoustic Event Detection, Segmentation and Classification</h4> 9916 <hr> 9917 <a class="w3-text" href="behera24_interspeech.html"> 9918 <p> 9919 FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation 9920 <br> 9921 <span class="w3-text w3-text-theme"> 9922 Swarup Ranjan Behera, Abhishek Dhiman, Karthik Gowda, Aalekhya Satya Narayani 9923 </span> 9924 </p> 9925 </a> 9926 <a class="w3-text" href="xiao24_interspeech.html"> 9927 <p> 9928 LungAdapter: Efficient Adapting Audio Spectrogram Transformer for Lung Sound Classification 9929 <br>
9930 <span class="w3-text w3-text-theme"> 9931 Li Xiao, Lucheng Fang, Yuhong Yang, Weiping Tu 9932 </span> 9933 </p> 9934 </a> 9935 <a class="w3-text" href="feng24c_interspeech.html"> 9936 <p> 9937 ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutions 9938 <br> 9939 <span class="w3-text w3-text-theme"> 9940 Jiu Feng, Mehmet Hamza Erol, Joon Son Chung, Arda Senocak 9941 </span> 9942 </p> 9943 </a> 9944 <a class="w3-text" href="omine24_interspeech.html"> 9945 <p> 9946 Robust Laughter Segmentation with Automatic Diverse Data Synthesis 9947 <br> 9948 <span class="w3-text w3-text-theme"> 9949 Taisei Omine, Kenta Akita, Reiji Tsuruno 9950 </span> 9951 </p> 9952 </a> 9953 <a class="w3-text" href="lebourdais24_interspeech.html"> 9954 <p> 9955 Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing 9956 <br> 9957 <span class="w3-text w3-text-theme"> 9958 Martin Lebourdais, Théo Mariotte, Antonio Almudévar, Marie Tahon, Alfonso Ortega 9959 </span> 9960 </p> 9961 </a> 9962 <a class="w3-text" href="elbanna24_interspeech.html"> 9963 <p> 9964 Predicting Heart Activity from Speech using Data-driven and Knowledge-based features 9965 <br> 9966 <span class="w3-text w3-text-theme"> 9967 Gasser Elbanna, Zohreh Mostaani, Mathew Magimai.-Doss 9968 </span> 9969 </p> 9970 </a> 9971 <a class="w3-text" href="morozova24_interspeech.html"> 9972 <p> 9973 Measuring acoustic dissimilarity of hierarchical markers in task-oriented dialogue with MFCC-based dynamic time warping 9974 <br> 9975 <span class="w3-text w3-text-theme"> 9976 Natalia Morozova, Guanghao You, Sabine Stoll, Adrian Bangerter 9977 </span> 9978 </p> 9979 </a> 9980 <a class="w3-text" href="buddi24_interspeech.html"> 9981 <p> 9982 Comparative Analysis of Personalized Voice Activity Detection Systems: Assessing Real-World Effectiveness 9983 <br> 9984 <span class="w3-text w3-text-theme"> 9985 Sai Srujana Buddi, Satyam Kumar, Utkarsh Sarawgi, Vineet Garg, Shivesh Ranjan, Ognjen Rudovic, Ahmed Hussen Abdelaziz, Saurabh Adya 9986 </span> 9987 </p> 9988 </a> 9989 <a class="w3-text" href="wang24ca_interspeech.html"> 9990 <p> 9991 Generalized Fake Audio Detection via Deep Stable Learning 9992 <br> 9993 <span class="w3-text w3-text-theme"> 9994 Zhiyong Wang, Ruibo Fu, Zhengqi Wen, Yuankun Xie, Yukun Liu, Xiaopeng Wang, Xuefei Liu, Yongwei Li, Jianhua Tao, Xin Qi, Yi Lu, Shuchen Shi 9995 </span> 9996 </p> 9997 </a> 9998 <a class="w3-text" href="palaskar24_interspeech.html"> 9999 <p> 10000 Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection 10001 <br>
10002 <span class="w3-text w3-text-theme"> 10003 Shruti Palaskar, Ognjen Rudovic, Sameer Dharur, Florian Pesce, Gautam Krishna, Aswin Sivaraman, Jack Berkowitz, Ahmed Hussen Abdelaziz, Saurabh Adya, Ahmed Tewfik 10004 </span> 10005 </p> 10006 </a> 10007 <a class="w3-text" href="zang24_interspeech.html"> 10008 <p> 10009 CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection 10010 <br> 10011 <span class="w3-text w3-text-theme"> 10012 Yongyi Zang, Jiatong Shi, You Zhang, Ryuichi Yamamoto, Jionghao Han, Yuxun Tang, Shengyuan Xu, Wenxiao Zhao, Jing Guo, Tomoki Toda, Zhiyao Duan 10013 </span> 10014 </p> 10015 </a> 10016 <a class="w3-text" href="si24_interspeech.html"> 10017 <p> 10018 Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor 10019 <br> 10020 <span class="w3-text w3-text-theme"> 10021 Yongjie Si, Yanxiong Li, Jialong Li, Jiaxin Tan, Qianhua He 10022 </span> 10023 </p> 10024 </a> 10025 <a class="w3-text" href="a24_interspeech.html"> 10026 <p> 10027 Multi-label Bird Species Classification from Field Recordings using Mel_Graph-GCN Framework 10028 <br> 10029 <span class="w3-text w3-text-theme"> 10030 Noumida A, Rajeev Rajan 10031 </span> 10032 </p> 10033 </a> 10034 </div> 10035 </div> 10036 <br> 10037 <div class="w3-content" style="height:10px" id="Speech and Audio Modelling"></div> 10038 <div class="w3-card w3-round w3-white w3-padding"> 10039 <div class="w3-container" style="margin-top:40px"> 10040 <h4 class="w3-center">Speech and Audio Modelling</h4> 10041 <hr> 10042 <a class="w3-text" href="li24ha_interspeech.html"> 10043 <p> 10044 DiveSound: LLM-Assisted Automatic Taxonomy Construction for Diverse Audio Generation 10045 <br> 10046 <span class="w3-text w3-text-theme"> 10047 Baihan Li, Zeyu Xie, Xuenan Xu, Yiwei Guo, Ming Yan, Ji Zhang, Kai Yu, Mengyue Wu 10048 </span> 10049 </p> 10050 </a> 10051 <a class="w3-text" href="wang24d_interspeech.html"> 10052 <p> 10053 Leveraging Language Model Capabilities for Sound Event Detection 10054 <br> 10055 <span class="w3-text w3-text-theme"> 10056 Hualei Wang, Jianguo Mao, Zhifang Guo, Jiarui Wan, Hong Liu, Xiangdong Wang 10057 </span> 10058 </p> 10059 </a> 10060 <a class="w3-text" href="xu24f_interspeech.html"> 10061 <p> 10062 Enhancing Zero-shot Audio Classification using Sound Attribute Knowledge from Large Language Models 10063 <br> 10064 <span class="w3-text w3-text-theme"> 10065 Xuenan Xu, Pingyue Zhang, Ming Yan, Ji Zhang, Mengyue Wu 10066 </span> 10067 </p> 10068 </a> 10069 <a class="w3-text" href="guan24b_interspeech.html"> 10070 <p> 10071 LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation 10072 <br>
10073 <span class="w3-text w3-text-theme"> 10074 Wenhao Guan, Kaidi Wang, Wangjin Zhou, Yang Wang, Feng Deng, Hui Wang, Lin Li, Qingyang Hong, Yong Qin 10075 </span> 10076 </p> 10077 </a> 10078 <a class="w3-text" href="cumlin24_interspeech.html"> 10079 <p> 10080 DNSMOS Pro: A Reduced-Size DNN for Probabilistic MOS of Speech 10081 <br> 10082 <span class="w3-text w3-text-theme"> 10083 Fredrik Cumlin, Xinyu Liang, Victor Ungureanu, Chandan K. A. Reddy, Christian Schüldt, Saikat Chatterjee 10084 </span> 10085 </p> 10086 </a> 10087 <a class="w3-text" href="boukun24_interspeech.html"> 10088 <p> 10089 Blind Zero-Shot Audio Restoration: A Variational Autoencoder Approach for Denoising and Inpainting 10090 <br> 10091 <span class="w3-text w3-text-theme"> 10092 Veranika Boukun, Jakob Drefs, Jörg Lücke 10093 </span> 10094 </p> 10095 </a> 10096 </div> 10097 </div> 10098 <br> 10099 <div class="w3-content" style="height:10px" id="Fake Audio Detection"></div> 10100 <div class="w3-card w3-round w3-white w3-padding"> 10101 <div class="w3-container" style="margin-top:40px"> 10102 <h4 class="w3-center">Fake Audio Detection</h4> 10103 <hr> 10104 <a class="w3-text" href="pascu24_interspeech.html"> 10105 <p> 10106 Towards generalisable and calibrated audio deepfake detection with self-supervised representations 10107 <br> 10108 <span class="w3-text w3-text-theme"> 10109 Octavian Pascu, Adriana Stan, Dan Oneata, Elisabeta Oneata, Horia Cucu 10110 </span> 10111 </p> 10112 </a> 10113 <a class="w3-text" href="xie24_interspeech.html"> 10114 <p> 10115 Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategy 10116 <br> 10117 <span class="w3-text w3-text-theme"> 10118 Yuankun Xie, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Xiaopeng Wang, Haonnan Cheng, Long Ye, Jianhua Tao 10119 </span> 10120 </p> 10121 </a> 10122 <a class="w3-text" href="zhong24_interspeech.html"> 10123 <p> 10124 Enhancing Partially Spoofed Audio Localization with Boundary-aware Attention Mechanism 10125 <br> 10126 <span class="w3-text w3-text-theme"> 10127 Jiafeng Zhong, Bin Li, Jiangyan Yi 10128 </span> 10129 </p> 10130 </a> 10131 <a class="w3-text" href="chen24o_interspeech.html"> 10132 <p> 10133 Singing Voice Graph Modeling for SingFake Detection 10134 <br> 10135 <span class="w3-text w3-text-theme"> 10136 Xuanjun Chen, Haibin Wu, Roger Jang, Hung-yi Lee 10137 </span> 10138 </p> 10139 </a> 10140 <a class="w3-text" href="wang24ga_interspeech.html"> 10141 <p> 10142 Genuine-Focused Learning using Mask AutoEncoder for Generalized Fake Audio Detection 10143 <br>
10144 <span class="w3-text w3-text-theme"> 10145 Xiaopeng Wang, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Yuankun Xie, Yukun Liu, Jianhua Tao, Xuefei Liu, Yongwei Li, Xin Qi, Yi Lu, Shuchen Shi 10146 </span> 10147 </p> 10148 </a> 10149 <a class="w3-text" href="kim24b_interspeech.html"> 10150 <p> 10151 One-class learning with adaptive centroid shift for audio deepfake detection 10152 <br> 10153 <span class="w3-text w3-text-theme"> 10154 Hyun Myung Kim, Kangwook Jang, Hoirin Kim 10155 </span> 10156 </p> 10157 </a> 10158 </div> 10159 </div> 10160 <br> 10161 <div class="w3-content" style="height:10px" id="Deep Learning-Based Speech Enhancement: Approaches, Scalability, and Evaluation"></div> 10162 <div class="w3-card w3-round w3-white w3-padding"> 10163 <div class="w3-container" style="margin-top:40px"> 10164 <h4 class="w3-center">Deep Learning-Based Speech Enhancement: Approaches, Scalability, and Evaluation</h4> 10165 <hr> 10166 <a class="w3-text" href="cao24_interspeech.html"> 10167 <p> 10168 VoiCor: A Residual Iterative Voice Correction Framework for Monaural Speech Enhancement 10169 <br> 10170 <span class="w3-text w3-text-theme"> 10171 Rui Cao, Tianrui Wang, Meng Ge, Andong Li, Longbiao Wang, Jianwu Dang, Yungang Jia 10172 </span> 10173 </p> 10174 </a> 10175 <a class="w3-text" href="parnamaa24_interspeech.html"> 10176 <p> 10177 Personalized Speech Enhancement Without a Separate Speaker Embedding Model 10178 <br> 10179 <span class="w3-text w3-text-theme"> 10180 Tanel Pärnamaa, Ando Saabas 10181 </span> 10182 </p> 10183 </a> 10184 <a class="w3-text" href="zhang24h_interspeech.html"> 10185 <p> 10186 URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement 10187 <br> 10188 <span class="w3-text w3-text-theme"> 10189 Wangyou Zhang, Robin Scheibler, Kohei Saijo, Samuele Cornell, Chenda Li, Zhaoheng Ni, Jan Pirklbauer, Marvin Sach, Shinji Watanabe, Tim Fingscheidt, Yanmin Qian 10190 </span> 10191 </p> 10192 </a> 10193 <a class="w3-text" href="richter24_interspeech.html"> 10194 <p> 10195 EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation 10196 <br> 10197 <span class="w3-text w3-text-theme"> 10198 Julius Richter, Yi-Chiao Wu, Steven Krenn, Simon Welker, Bunlong Lay, Shinji Watanabe, Alexander Richard, Timo Gerkmann 10199 </span> 10200 </p> 10201 </a> 10202 </div> 10203 </div> 10204 <br> 10205 <div class="w3-content" style="height:10px" id="Speech Synthesis: Other Topics 1"></div> 10206 <div class="w3-card w3-round w3-white w3-padding"> 10207 <div class="w3-container" style="margin-top:40px"> 10208 <h4 class="w3-center">Speech Synthesis: Other Topics 1</h4> 10209 <hr> 10210 <a class="w3-text" href="tan24c_interspeech.html"> 10211 <p> 10212 LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis 10213 <br>
10214 <span class="w3-text w3-text-theme"> 10215 Zhenxiong Tan, Xinyin Ma, Gongfan Fang, Xinchao Wang 10216 </span> 10217 </p> 10218 </a> 10219 <a class="w3-text" href="kim24e_interspeech.html"> 10220 <p> 10221 Speak in the Scene: Diffusion-based Acoustic Scene Transfer toward Immersive Speech Generation 10222 <br> 10223 <span class="w3-text w3-text-theme"> 10224 Miseul Kim, Soo-Whan Chung, Youna Ji, Hong-Goo Kang, Min-Seok Choi 10225 </span> 10226 </p> 10227 </a> 10228 <a class="w3-text" href="li24y_interspeech.html"> 10229 <p> 10230 PL-TTS: A Generalizable Prompt-based Diffusion TTS Augmented by Large Language Model 10231 <br> 10232 <span class="w3-text w3-text-theme"> 10233 Shuhua Li, Qirong Mao, Jiatong Shi 10234 </span> 10235 </p> 10236 </a> 10237 <a class="w3-text" href="abel24_interspeech.html"> 10238 <p> 10239 Towards realtime co-speech gestures synthesis using STARGATE 10240 <br> 10241 <span class="w3-text w3-text-theme"> 10242 Louis Abel, Vincent Colotte, Slim Ouni 10243 </span> 10244 </p> 10245 </a> 10246 <a class="w3-text" href="shi24f_interspeech.html"> 10247 <p> 10248 PPPR: Portable Plug-in Prompt Refiner for Text to Audio Generation 10249 <br> 10250 <span class="w3-text w3-text-theme"> 10251 Shuchen Shi, Ruibo Fu, Zhengqi Wen, Jianhua Tao, Tao Wang, Chunyu Qiang, Yi Lu, Xin Qi, Xuefei Liu, Yukun Liu, Yongwei Li, Zhiyong Wang, Xiaopeng Wang 10252 </span> 10253 </p> 10254 </a> 10255 <a class="w3-text" href="lee24m_interspeech.html"> 10256 <p> 10257 Neural ATSM: Fully Neural Network-based Adaptive Time-Scale Modification Using Sentence-Specific Dynamic Control 10258 <br> 10259 <span class="w3-text w3-text-theme"> 10260 Jaeuk Lee, Sohee Jang, Joon-Hyuk Chang 10261 </span> 10262 </p> 10263 </a> 10264 <a class="w3-text" href="guo24c_interspeech.html"> 10265 <p> 10266 FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis 10267 <br> 10268 <span class="w3-text w3-text-theme"> 10269 Yinlin Guo, Yening Lv, Jinqiao Dou, Yan Zhang, Yuehai Wang 10270 </span> 10271 </p> 10272 </a> 10273 <a class="w3-text" href="kunesova24_interspeech.html"> 10274 <p> 10275 Zero-shot Out-of-domain is No Joke: Lessons Learned in the VoiceMOS 2023 MOS Prediction Challenge 10276 <br> 10277 <span class="w3-text w3-text-theme"> 10278 Marie KuneÅ¡ová, Jan LeheÄka, Josef Michálek, Jindrich Matousek, Jan Å vec 10279 </span> 10280 </p> 10281 </a> 10282 <a class="w3-text" href="ward24_interspeech.html"> 10283 <p> 10284 Towards a General-Purpose Model of Perceived Pragmatic Similarity 10285 <br>
10286 <span class="w3-text w3-text-theme"> 10287 Nigel G. Ward, Andres Segura, Alejandro Ceballos, Divette Marco 10288 </span> 10289 </p> 10290 </a> 10291 </div> 10292 </div> 10293 <br> 10294 <div class="w3-content" style="height:10px" id="Speech Synthesis: Other Topics 2"></div> 10295 <div class="w3-card w3-round w3-white w3-padding"> 10296 <div class="w3-container" style="margin-top:40px"> 10297 <h4 class="w3-center">Speech Synthesis: Other Topics 2</h4> 10298 <hr> 10299 <a class="w3-text" href="ratsep24_interspeech.html"> 10300 <p> 10301 Enabling Conversational Speech Synthesis using Noisy Spontaneous Data 10302 <br> 10303 <span class="w3-text w3-text-theme"> 10304 Liisa Rätsep, Rasmus Lellep, Mark Fishel 10305 </span> 10306 </p> 10307 </a> 10308 <a class="w3-text" href="yang24c_interspeech.html"> 10309 <p> 10310 Frame-Wise Breath Detection with Self-Training: An Exploration of Enhancing Breath Naturalness in Text-to-Speech 10311 <br> 10312 <span class="w3-text w3-text-theme"> 10313 Dong Yang, Tomoki Koriyama, Yuki Saito 10314 </span> 10315 </p> 10316 </a> 10317 <a class="w3-text" href="seong24_interspeech.html"> 10318 <p> 10319 H4C-TTS: Leveraging Multi-Modal Historical Context for Conversational Text-to-Speech 10320 <br> 10321 <span class="w3-text w3-text-theme"> 10322 Donghyun Seong, Joon-Hyuk Chang 10323 </span> 10324 </p> 10325 </a> 10326 <a class="w3-text" href="yang24i_interspeech.html"> 10327 <p> 10328 Bilingual and Code-switching TTS Enhanced with Denoising Diffusion Model and GAN 10329 <br> 10330 <span class="w3-text w3-text-theme"> 10331 Huai-Zhe Yang, Chia-Ping Chen, Shan-Yun He, Cheng-Ruei Li 10332 </span> 10333 </p> 10334 </a> 10335 <a class="w3-text" href="saeki24_interspeech.html"> 10336 <p> 10337 SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics 10338 <br> 10339 <span class="w3-text w3-text-theme"> 10340 Takaaki Saeki, Soumi Maiti, Shinnosuke Takamichi, Shinji Watanabe, Hiroshi Saruwatari 10341 </span> 10342 </p> 10343 </a> 10344 <a class="w3-text" href="yoon24b_interspeech.html"> 10345 <p> 10346 UNIQUE : Unsupervised Network for Integrated Speech Quality Evaluation 10347 <br> 10348 <span class="w3-text w3-text-theme"> 10349 Juhwan Yoon, WooSeok Ko, Seyun Um, Sungwoong Hwang, Soojoong Hwang, Changhwan Kim, Hong-Goo Kang 10350 </span> 10351 </p> 10352 </a> 10353 <a class="w3-text" href="lee24_interspeech.html"> 10354 <p> 10355 FVTTS : Face Based Voice Synthesis for Text-to-Speech 10356 <br>
10357 <span class="w3-text w3-text-theme"> 10358 Minyoung Lee, Eunil Park, Sungeun Hong 10359 </span> 10360 </p> 10361 </a> 10362 </div> 10363 </div> 10364 <br> 10365 <div class="w3-content" style="height:10px" id="Speech synthesis: Cross-lingual and multilingual aspects"></div> 10366 <div class="w3-card w3-round w3-white w3-padding"> 10367 <div class="w3-container" style="margin-top:40px"> 10368 <h4 class="w3-center">Speech synthesis: Cross-lingual and multilingual aspects</h4> 10369 <hr> 10370 <a class="w3-text" href="lux24_interspeech.html"> 10371 <p> 10372 Meta Learning Text-to-Speech Synthesis in over 7000 Languages 10373 <br> 10374 <span class="w3-text w3-text-theme"> 10375 Florian Lux, Sarina Meyer, Lyonel Behringer, Frank Zalkow, Phat Do, Matt Coler, Emanuël A. P. Habets, Ngoc Thang Vu 10376 </span> 10377 </p> 10378 </a> 10379 <a class="w3-text" href="gong24c_interspeech.html"> 10380 <p> 10381 An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios 10382 <br> 10383 <span class="w3-text w3-text-theme"> 10384 Cheng Gong, Erica Cooper, Xin Wang, Chunyu Qiang, Mengzhe Geng, Dan Wells, Longbiao Wang, Jianwu Dang, Marc Tessier, Aidan Pine, Korin Richmond, Junichi Yamagishi 10385 </span> 10386 </p> 10387 </a> 10388 <a class="w3-text" href="wu24f_interspeech.html"> 10389 <p> 10390 Improving Multilingual Text-to-Speech with Mixture-of-Language-Experts and Accent Disentanglement 10391 <br> 10392 <span class="w3-text w3-text-theme"> 10393 Jing Wu, Ting Chen, Minchuan Chen, Wei Hu, Shaojun Wang, Jing Xiao 10394 </span> 10395 </p> 10396 </a> 10397 <a class="w3-text" href="xu24g_interspeech.html"> 10398 <p> 10399 Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models 10400 <br> 10401 <span class="w3-text w3-text-theme"> 10402 Jing Xu, Minglin Wu, Xixin Wu, Helen Meng 10403 </span> 10404 </p> 10405 </a> 10406 <a class="w3-text" href="casanova24_interspeech.html"> 10407 <p> 10408 XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model 10409 <br> 10410 <span class="w3-text w3-text-theme"> 10411 Edresson Casanova, Kelly Davis, Eren Gölge, Görkem Göknar, Iulian Gulea, Logan Hart, Aya Aljafari, Joshua Meyer, Reuben Morais, Samuel Olayemi, Julian Weber 10412 </span> 10413 </p> 10414 </a> 10415 <a class="w3-text" href="guo24b_interspeech.html"> 10416 <p> 10417 X-E-Speech: Joint Training Framework of Non-Autoregressive Cross-lingual Emotional Text-to-Speech and Voice Conversion 10418 <br>
10419 <span class="w3-text w3-text-theme"> 10420 Houjian Guo, Chaoran Liu, Carlos Toshinori Ishi, Hiroshi Ishiguro 10421 </span> 10422 </p> 10423 </a> 10424 </div> 10425 </div> 10426 <br> 10427 <div class="w3-content" style="height:10px" id="Noise, Far-Field, Multi-Talker, Enhancement, Audio Classification"></div> 10428 <div class="w3-card w3-round w3-white w3-padding"> 10429 <div class="w3-container" style="margin-top:40px"> 10430 <h4 class="w3-center">Noise, Far-Field, Multi-Talker, Enhancement, Audio Classification</h4> 10431 <hr> 10432 <a class="w3-text" href="shao24_interspeech.html"> 10433 <p> 10434 RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios 10435 <br> 10436 <span class="w3-text w3-text-theme"> 10437 Yiwen Shao, Shi-Xiong Zhang, Dong Yu 10438 </span> 10439 </p> 10440 </a> 10441 <a class="w3-text" href="shao24b_interspeech.html"> 10442 <p> 10443 Multi-Channel Multi-Speaker ASR Using Target Speakerâs Solo Segment 10444 <br> 10445 <span class="w3-text w3-text-theme"> 10446 Yiwen Shao, Shi-Xiong Zhang, Yong Xu, Meng Yu, Dong Yu, Daniel Povey, Sanjeev Khudanpur 10447 </span> 10448 </p> 10449 </a> 10450 <a class="w3-text" href="ravenscroft24_interspeech.html"> 10451 <p> 10452 Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition 10453 <br> 10454 <span class="w3-text w3-text-theme"> 10455 William Ravenscroft, George Close, Stefan Goetze, Thomas Hain, Mohammad Soleymanpour, Anurag Chowdhur
10455y, Mark C. Fuhs 10456 </span> 10457 </p> 10458 </a> 10459 <a class="w3-text" href="vinnikov24_interspeech.html"> 10460 <p> 10461 NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription 10462 <br> 10463 <span class="w3-text w3-text-theme"> 10464 Alon Vinnikov, Amir Ivry, Aviv Hurvitz, Igor Abramovski, Sharon Koubi, Ilya Gurvich, Shai Peer, Xiong Xiao, Benjamin Martinez Elizalde, Naoyuki Kanda, Xiaofei Wang, Shalev Shaer, Stav Yagev, Yossi Asher, Sunit Sivasankaran, Yifan Gong, Min Tang, Huaming Wang, Eyal Krupka 10465 </span> 10466 </p> 10467 </a> 10468 <a class="w3-text" href="dissen24_interspeech.html"> 10469 <p> 10470 Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network 10471 <br> 10472 <span class="w3-text w3-text-theme"> 10473 Yehoshua Dissen, Shiry Yonash, Israel Cohen, Joseph Keshet 10474 </span> 10475 </p> 10476 </a> 10477 <a class="w3-text" href="haider24_interspeech.html"> 10478 <p> 10479 Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement 10480 <br> 10481 <span class="w3-text w3-text-theme"> 10482 Daniel Haider, Felix Perfler, Vincent Lostanlen, Martin Ehler, Peter Balazs 10483 </span> 10484 </p> 10485 </a> 10486 <a class="w3-text" href="wang24da_interspeech.html"> 10487 <p> 10488 DGSRN: Noise-Robust Speech Recognition Method with Dual-Path Gated Spectral Refinement Network 10489 <br> 10490 <span class="w3-text w3-text-theme"> 10491 Wenjun Wang, Shangbin Mo, Ling Dong, Zhengtao Yu, Junjun Guo, Yuxin Huang 10492 </span> 10493 </p> 10494 </a> 10495 <a class="w3-text" href="singh24b_interspeech.html"> 10496 <p> 10497 Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation 10498 <br> 10499 <span class="w3-text w3-text-theme"> 10500 Riyansha Singh, Parinita Nema, Vinod K Kurmi 10501 </span> 10502 </p> 10503 </a> 10504 <a class="w3-text" href="sheikh24_interspeech.html"> 10505 <p> 10506 Bird Whisperer: Leveraging Large Pre-trained Acoustic Model for Bird Call Classification 10507 <br> 10508 <span class="w3-text w3-text-theme"> 10509 Muhammad Umer Sheikh, Hassan Abid, Bhuiyan Sanjid Shafique, Asif Hanif, Muhammad Haris Khan 10510 </span> 10511 </p> 10512 </a> 10513 <a class="w3-text" href="sato24_interspeech.html"> 10514 <p> 10515 SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling 10516 <br>
10517 <span class="w3-text w3-text-theme"> 10518 Hiroshi Sato, Takafumi Moriya, Masato Mimura, Shota Horiguchi, Tsubasa Ochiai, Takanori Ashihara, Atsushi Ando, Kentaro Shinayama, Marc Delcroix 10519 </span> 10520 </p> 10521 </a> 10522 <a class="w3-text" href="borsdorf24_interspeech.html"> 10523 <p> 10524 wTIMIT2mix: A Cocktail Party Mixtures Database to Study Target Speaker Extraction for Normal and Whispered Speech 10525 <br> 10526 <span class="w3-text w3-text-theme"> 10527 Marvin Borsdorf, Zexu Pan, Haizhou Li, Tanja Schultz 10528 </span> 10529 </p> 10530 </a> 10531 </div> 10532 </div> 10533 <br> 10534 <div class="w3-content" style="height:10px" id="Self-Supervised Learning for ASR"></div> 10535 <div class="w3-card w3-round w3-white w3-padding"> 10536 <div class="w3-container" style="margin-top:40px"> 10537 <h4 class="w3-center">Self-Supervised Learning for ASR</h4> 10538 <hr> 10539 <a class="w3-text" href="getman24_interspeech.html"> 10540 <p> 10541 What happens in continued pre-training? Analysis of self-supervised speech models with continued pre-training for colloquial Finnish ASR 10542 <br> 10543 <span class="w3-text w3-text-theme"> 10544 Yaroslav Getman, Tamas Grosz, Mikko Kurimo 10545 </span> 10546 </p> 10547 </a> 10548 <a class="w3-text" href="kato24_interspeech.html"> 10549 <p> 10550 Self-Supervised Learning for ASR Pre-Training with Uniquely Determined Target Labels and Controlling Cepstrum Truncation for Speech Augmentation 10551 <br> 10552 <span class="w3-text w3-text-theme"> 10553 Akihiro Kato, Hiroyuki Nagano, Kohei Chike, Masaki Nose 10554 </span> 10555 </p> 10556 </a> 10557 <a class="w3-text" href="yadav24b_interspeech.html"> 10558 <p> 10559 MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations 10560 <br> 10561 <span class="w3-text w3-text-theme"> 10562 Hemant Yadav, Sunayana Sitaram, Rajiv Ratn Shah 10563 </span> 10564 </p> 10565 </a> 10566 <a class="w3-text" href="lee24k_interspeech.html"> 10567 <p> 10568 Balanced-Wav2Vec: Enhancing Stability and Robustness of Representation Learning Through Sample Reweighting Techniques 10569 <br> 10570 <span class="w3-text w3-text-theme"> 10571 Mun-Hak Lee, Jae-Hong Lee, DoHee Kim, Ye-Eun Ko, Joon-Hyuk Chang 10572 </span> 10573 </p> 10574 </a> 10575 </div> 10576 </div> 10577 <br> 10578 <div class="w3-content" style="height:10px" id="Spoken Term Detection and Speech Retrieval"></div> 10579 <div class="w3-card w3-round w3-white w3-padding"> 10580 <div class="w3-container" style="margin-top:40px"> 10581 <h4 class="w3-center">Spoken Term Detection and Speech Retrieval</h4> 10582 <hr> 10583 <a class="w3-text" href="yuan24b_interspeech.html"> 10584 <p> 10585 Few-Shot Keyword Spotting from Mixed Speech 10586 <br>
10587 <span class="w3-text w3-text-theme"> 10588 Junming Yuan, Ying Shi, LanTian Li, Dong Wang, Askar Hamdulla 10589 </span> 10590 </p> 10591 </a> 10592 <a class="w3-text" href="yusuf24b_interspeech.html"> 10593 <p> 10594 Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units 10595 <br> 10596 <span class="w3-text w3-text-theme"> 10597 Bolaji Yusuf, Jan Honza Cernocky, Murat Saraçlar 10598 </span> 10599 </p> 10600 </a> 10601 <a class="w3-text" href="he24_interspeech.html"> 10602 <p> 10603 2DP-2MRC: 2-Dimensional Pointer-based Machine Reading Comprehension Method for Multimodal Moment Retrieval 10604 <br> 10605 <span class="w3-text w3-text-theme"> 10606 Jiajun He, Tomoki Toda 10607 </span> 10608 </p> 10609 </a> 10610 <a class="w3-text" href="xie24c_interspeech.html"> 10611 <p> 10612 GPA: Global and Prototype Alignment for Audio-Text Retrieval 10613 <br> 10614 <span class="w3-text w3-text-theme"> 10615 Yuxin Xie, Zhihong Zhu, Xianwei Zhuang, Liming Liang, Zhichang Wang, Yuexian Zou 10616 </span> 10617 </p> 10618 </a> 10619 <a class="w3-text" href="kim24r_interspeech.html"> 10620 <p> 10621 Few-Shot Keyword-Incremental Learning with Total Calibration 10622 <br> 10623 <span class="w3-text w3-text-theme"> 10624 Ilseok Kim, Ju-Seok Seong, Joon-Hyuk Chang 10625 </span> 10626 </p> 10627 </a> 10628 <a class="w3-text" href="tapo24_interspeech.html"> 10629 <p> 10630 Leveraging Speech Data Diversity to Document Indigenous Heritage and Culture 10631 <br> 10632 <span class="w3-text w3-text-theme"> 10633 Allahsera Tapo, Ãric Le Ferrand, Zoey Liu, Christopher Homan, Emily Prud'hommeaux 10634 </span> 10635 </p> 10636 </a> 10637 </div> 10638 </div> 10639 <br> 10640 <div class="w3-content" style="height:10px" id="Speech Disorders 1"></div> 10641 <div class="w3-card w3-round w3-white w3-padding"> 10642 <div class="w3-container" style="margin-top:40px"> 10643 <h4 class="w3-center">Speech Disorders 1</h4> 10644 <hr> 10645 <a class="w3-text" href="mohapatra24_interspeech.html"> 10646 <p> 10647 Missingness-resilient Video-enhanced Multimodal Disfluency Detection 10648 <br> 10649 <span class="w3-text w3-text-theme"> 10650 Payal Mohapatra, Shamika Likhite, Subrata Biswas, Bashima Islam, Qi Zhu 10651 </span> 10652 </p> 10653 </a> 10654 <a class="w3-text" href="gong24_interspeech.html"> 10655 <p> 10656 AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection 10657 <br>
10658 <span class="w3-text w3-text-theme"> 10659 Rong Gong, Hongfei Xue, Lezhi Wang, Xin Xu, Qisheng Li, Lei Xie, Hui Bu, Shaomei Wu, Jiaming Zhou, Yong Qin, Binbin Zhang, Jun Du, Jia Bin, Ming Li 10660 </span> 10661 </p> 10662 </a> 10663 <a class="w3-text" href="zulfikar24_interspeech.html"> 10664 <p> 10665 Analyzing Speech Motor Movement using Surface Electromyography in Minimally Verbal Adults with Autism Spectrum Disorder 10666 <br> 10667 <span class="w3-text w3-text-theme"> 10668 Wazeer Zulfikar, Nishat Protyasha, Camila Canales, Heli Patel, James Williamson, Laura Sarnie, Lisa Nowinski, Nataliya Kosmyna, Paige Townsend, Sophia Yuditskaya, Tanya Talkar, Utkarsh Oggy Sarawgi, Christopher McDougle, Thomas Quatieri, Pattie Maes, Maria Mody 10669 </span> 10670 </p> 10671 </a> 10672 <a class="w3-text" href="zhang24f_interspeech.html"> 10673 <p> 10674 Prosody of speech production in latent post-stroke aphasia 10675 <br> 10676 <span class="w3-text w3-text-theme"> 10677 Cong Zhang, Tong Li, Gayle DeDe, Christos Salis 10678 </span> 10679 </p> 10680 </a> 10681 <a class="w3-text" href="nie24_interspeech.html"> 10682 <p> 10683 MMSD-Net: Towards Multi-modal Stuttering Detection 10684 <br> 10685 <span class="w3-text w3-text-theme"> 10686 Liangyu Nie, Sudarsana Reddy Kadiri, Ruchit Agrawal 10687 </span> 10688 </p> 10689 </a> 10690 <a class="w3-text" href="wagner24b_interspeech.html"> 10691 <p> 10692 Large Language Models for Dysfluency Detection in Stuttered Speech 10693 <br> 10694 <span class="w3-text w3-text-theme"> 10695 Dominik Wagner, Sebastian P. Bayerl, Ilja Baumann, Elmar Noeth, Korbinian Riedhammer, Tobias Bocklet 10696 </span> 10697 </p> 10698 </a> 10699 </div> 10700 </div> 10701 <br> 10702 <div class="w3-content" style="height:10px" id="Connecting Speech-science and Speech-technology for Childrenâs Speech (Special Session)"></div> 10703 <div class="w3-card w3-round w3-white w3-padding"> 10704 <div class="w3-container" style="margin-top:40px"> 10705 <h4 class="w3-center">Connecting Speech-science and Speech-technology for Childrenâs Speech (Special Session)</h4> 10706 <hr> 10707 <a class="w3-text" href="demopoulos24_interspeech.html"> 10708 <p> 10709 Preliminary Investigation of Psychometric Properties of a Novel Multimodal Dialog Based Affect Production Task in Children and Adolescents with Autism 10710 <br> 10711 <span class="w3-text w3-text-theme"> 10712 Carly Demopoulos, Linnea Lampinen, Cristian Preciado, Hardik Kothare, Vikram Ramanarayanan 10713 </span> 10714 </p> 10715 </a> 10716 <a class="w3-text" href="charuau24_interspeech.html"> 10717 <p> 10718 Training speech-breathing coordination in computer-assisted reading 10719 <br>
10720 <span class="w3-text w3-text-theme"> 10721 Delphine Charuau, Andrea Briglia, Erika Godde, Gérard Bailly 10722 </span> 10723 </p> 10724 </a> 10725 <a class="w3-text" href="kadambi24_interspeech.html"> 10726 <p> 10727 How Does Alignment Error Affect Automated Pronunciation Scoring in Children's Speech? 10728 <br> 10729 <span class="w3-text w3-text-theme"> 10730 Prad Kadambi, Tristan Mahr, Lucas Annear, Henry Nomeland, Julie Liss, Katherine Hustad, Visar Berisha 10731 </span> 10732 </p> 10733 </a> 10734 <a class="w3-text" href="benway24_interspeech.html"> 10735 <p> 10736 Examining Vocal Tract Coordination in Childhood Apraxia of Speech with Acoustic-to-Articulatory Speech Inversion Feature Sets 10737 <br> 10738 <span class="w3-text w3-text-theme"> 10739 Nina R. Benway, Jonathan L. Preston, Carol Espy-Wilson 10740 </span> 10741 </p> 10742 </a> 10743 <a class="w3-text" href="sukhadia24_interspeech.html"> 10744 <p> 10745 Childrenâs Speech Recognition through Discrete Token Enhancement 10746 <br> 10747 <span class="w3-text w3-text-theme"> 10748 Vrunda N. Sukhadia, Shammur Absar Chowdhury 10749 </span> 10750 </p> 10751 </a> 10752 <a class="w3-text" href="wang24f_interspeech.html"> 10753 <p> 10754 Bridging Child-Centered Speech Language Identification and Language Diarization via Phonetics 10755 <br> 10756 <span class="w3-text w3-text-theme"> 10757 Yujia Wang, Hexin Liu, Leibny Paola Garcia 10758 </span> 10759 </p> 10760 </a> 10761 <a class="w3-text" href="gao24d_interspeech.html"> 10762 <p> 10763 Reading Miscue Detection in Primary School through Automatic Speech Recognition 10764 <br> 10765 <span class="w3-text w3-text-theme"> 10766 Lingyun Gao, Cristian Tejedor-Garcia, Helmer Strik, Catia Cucchiarini 10767 </span> 10768 </p> 10769 </a> 10770 <a class="w3-text" href="baumann24_interspeech.html"> 10771 <p> 10772 Automatic Evaluation of a Sentence Memory Test for Preschool Children 10773 <br> 10774 <span class="w3-text w3-text-theme"> 10775 Ilja Baumann, Nicole Unger, Dominik Wagner, Korbinian Riedhammer, Tobias Bocklet 10776 </span> 10777 </p> 10778 </a> 10779 <a class="w3-text" href="li24j_interspeech.html"> 10780 <p> 10781 Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis 10782 <br> 10783 <span class="w3-text w3-text-theme"> 10784 Jialu Li, Mark Hasegawa-Johnson, Karrie Karahalios 10785 </span> 10786 </p> 10787 </a> 10788 <a class="w3-text" href="blockmedin24_interspeech.html"> 10789 <p> 10790 Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning 10791 <br>
10792 <span class="w3-text w3-text-theme"> 10793 Lucas Block Medin, Thomas Pellegrini, Lucile Gelin 10794 </span> 10795 </p> 10796 </a> 10797 <a class="w3-text" href="fan24b_interspeech.html"> 10798 <p> 10799 Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models 10800 <br> 10801 <span class="w3-text w3-text-theme"> 10802 Ruchao Fan, Natarajan Balaji Shankar, Abeer Alwan 10803 </span> 10804 </p> 10805 </a> 10806 <a class="w3-text" href="rolland24_interspeech.html"> 10807 <p> 10808 Introduction To Partial Fine-tuning: A Comprehensive Evaluation Of End-to-end Childrenâs Automatic Speech Recognition Adaptation 10809 <br> 10810 <span class="w3-text w3-text-theme"> 10811 Thomas Rolland, Alberto Abad 10812 </span> 10813 </p> 10814 </a> 10815 <a class="w3-text" href="zhang24d_interspeech.html"> 10816 <p> 10817 Improving child speech recognition with augmented child-like speech 10818 <br> 10819 <span class="w3-text w3-text-theme"> 10820 Yuanyuan Zhang, Zhengjun Yue, Tanvina Patel, Odette Scharenborg 10821 </span> 10822 </p> 10823 </a> 10824 <a class="w3-text" href="graave24_interspeech.html"> 10825 <p> 10826 Mixed Children/Adult/Childrenized Fine-Tuning for Childrenâs ASR: How to Reduce Age Mismatch and Speaking Style Mismatch 10827 <br> 10828 <span class="w3-text w3-text-theme"> 10829 Thomas Graave, Zhengyang Li, Timo Lohrenz, Tim Fingscheidt 10830 </span> 10831 </p> 10832 </a> 10833 <a class="w3-text" href="xu24c_interspeech.html"> 10834 <p> 10835 Exploring Speech Foundation Models for Speaker Diarization in Child-Adult Dyadic Interactions 10836 <br> 10837 <span class="w3-text w3-text-theme"> 10838 Anfeng Xu, Kevin Huang, Tiantian Feng, Lue Shen, Helen Tager-Flusberg, Shrikanth Narayanan 10839 </span> 10840 </p> 10841 </a> 10842 </div> 10843 </div> 10844 <br> 10845 <div class="w3-content" style="height:10px" id="Show and Tell 4"></div> 10846 <div class="w3-card w3-round w3-white w3-padding"> 10847 <div class="w3-container" style="margin-top:40px"> 10848 <h4 class="w3-center">Show and Tell 4</h4> 10849 <hr> 10850 <a class="w3-text" href="sirigiraju24_interspeech.html"> 10851 <p> 10852 IIITH Ucchar e-Sudharak: an automatic English pronunciation corrector for school-going children with a teacher in the loop 10853 <br> 10854 <span class="w3-text w3-text-theme"> 10855 Meenakshi Sirigiraju, Arjun Rajasekar, Abhishikth Meejuri, Chiranjeevi Yarra 10856 </span> 10857 </p> 10858 </a> 10859 <a class="w3-text" href="yap24_interspeech.html"> 10860 <p> 10861 Speech enabled visual acuity test 10862 <br>
10863 <span class="w3-text w3-text-theme"> 10864 Boon Peng Yap, Kok Liang Tan, Zhenghao Li, Rong Tong 10865 </span> 10866 </p> 10867 </a> 10868 <a class="w3-text" href="aiba24_interspeech.html"> 10869 <p> 10870 A ChatGPT-based oral Q&A practice system for first-time student participants in international conferences 10871 <br> 10872 <span class="w3-text w3-text-theme"> 10873 Mayuko Aiba, Daisuke Saito, Nobuaki Minematsu 10874 </span> 10875 </p> 10876 </a> 10877 <a class="w3-text" href="sridaran24_interspeech.html"> 10878 <p> 10879 Visual scene display application for augmentative and alternative communication 10880 <br> 10881 <span class="w3-text w3-text-theme"> 10882 Karthik Venkat Sridaran, Raja Praveen, Reuben T Varghese, Ajish K Abraham, Shankar R, Winnie Rachel Cherian 10883 </span> 10884 </p> 10885 </a> 10886 <a class="w3-text" href="masudakatsuse24_interspeech.html"> 10887 <p> 10888 CALL system using pitch-accent feature representations reflecting listenersâ subjective adequacy 10889 <br> 10890 <span class="w3-text w3-text-theme"> 10891 Ikuyo Masuda-Katsuse, Ayako Shirose 10892 </span> 10893 </p> 10894 </a> 10895 <a class="w3-text" href="preston24_interspeech.html"> 10896 <p> 10897 The speech motor chaining web app for speech motor learning 10898 <br> 10899 <span class="w3-text w3-text-theme"> 10900 Jonathan L Preston, Nina R Benway, Nathan Prestopnik, Nathan Preston 10901 </span> 10902 </p> 10903 </a> 10904 <a class="w3-text" href="yoder24_interspeech.html"> 10905 <p> 10906 Visualization for improving foreign language pronunciation 10907 <br> 10908 <span class="w3-text w3-text-theme"> 10909 Charlotte Yoder, Karrie Karahalios, Mark Hasegawa-Johnson, Shreyansh Agrawal 10910 </span> 10911 </p> 10912 </a> 10913 <a class="w3-text" href="phan24b_interspeech.html"> 10914 <p> 10915 CaptainA self-study mobile app for practising speaking: task completion assessment and feedback with generative AI 10916 <br> 10917 <span class="w3-text w3-text-theme"> 10918 Nhan Phan, Anna von Zansen, Maria Kautonen, Tamás Grósz, Mikko Kurimo 10919 </span> 10920 </p> 10921 </a> 10922 </div> 10923 </div> 10924 <br> 10925 </div> 10926 </div> 10927 10928 10929 10930 <!-- Paper search table --> 10931 <div class="w3-container" id="bypaper"> 10932 <div class="w3-content" style="max-width:1200px;margin-top:60px">
10933 <div class="w3-container w3-card w3-padding w3-white"> 10934 <div class="w3-text w3-center"> 10935 <span class='w3-large'> 10936 <b>Search papers</b> 10937 </span> 10938 <button class='w3-text w3-button w3-right' 10939 onclick="document.getElementById('help_papers').style.display='block'"> 10940 <i class='icon-question-circle'></i> 10941 </button> 10942 </div> 10943 <table id="paper_table" class="display" style="width:95%"> 10944 <thead> 10945 <tr> 10946 <th width="100%">Article</th> 10947 <th width="0%"></th> 10948 <th width="0%"></th> 10949 <th width="0%"></th> 10950 </tr> 10951 </thead> 10952 </table> 10953 </div> 10954 <!-- <p class="w3-small" style="margin-bottom: 50px"></p> --> 10955 </div> 10956 </div> 10957 </div> 10958 10959 <!-- Session chooser --> 10960 <div id="sessionchooser" class="w3-modal" > 10961 <div class="w3-modal-content w3-card-4 w3-greyscale w3-theme-d4 w3-padding w3-bordered" onclick="document.getElementById('sessionchooser').style.display='none'"> 10962 <span onclick="document.getElementById('sessionchooser').style.display='none'" 10963 class="w3-button w3-display-topright">×</span> 10964 <p><a class="w3-text" href="#Keynote 1 ISCA Medallist">Keynote 1 ISCA Medallist</a></p> 10965 <p><a class="w3-text" href="#L2 Speech, Bilingualism and Code-Switching">L2 Speech, Bilingualism and Code-Switching</a></p> 10966 <p><a class="w3-text" href="#Speaker Diarization 1">Speaker Diarization 1</a></p> 10967 <p><a class="w3-text" href="#Speech and Audio Analysis and Representations">Speech and Audio Analysis and Representations</a></p> 10968 <p><a class="w3-text" href="#Acoustic Event Detection and Classification 2">Acoustic Event Detection and Classification 2</a></p> 10969 <p><a class="w3-text" href="#Detection and Classification of Bioacoustic Signals">Detection and Classification of Bioacoustic Signals</a></p> 10970 <p><a class="w3-text" href="#Acoustic Echo Cancellation">Acoustic Echo Cancellation</a></p> 10971 <p><a class="w3-text" href="#Speech Synthesis: Voice Conversion 1">Speech Synthesis: Voice Conversion 1</a></p> 10972 <p><a class="w3-text" href="#Neural Network Architectures for ASR 2">Neural Network Architectures for ASR 2</a></p> 10973 <p><a class="w3-text" href="#Decoding Algorithms">Decoding Algorithms</a></p> 10974 <p><a class="w3-text" href="#Pronunciation Assessment">Pronunciation Assessment</a></p> 10975 <p><a class="w3-text" href="#Spoken Language Processing">Spoken Language Processing</a></p> 10976 <p><a class="w3-text" href="#Spoken Machine Translation 2">Spoken Machine Translation 2</a></p> 10977 <p><a class="w3-text" href="#Biosignal-enabled Spoken Communication">Biosignal-enabled Spoken Communication</a></p> 10978 <p><a class="w3-text" href="#Individual and Social Factors in Phonetics">Individual and Social Factors in Phonetics</a></p> 10979 <p><a class="w3-text" href="#Paralinguistics">Paralinguistics</a></p> 10980 <p><a class="w3-text" href="#Speaker Recognition: Adversarial and Spoofing Attacks">Speaker Recognition: Adversarial and Spoofing Attacks</a></p> 10981 <p><a class="w3-text" href="#Audio Event Detection and Classification 1">Audio Event Detection and Classification 1</a></p> 10982 <p><a class="w3-text" href="#Source Separation 2">Source Separation 2</a></p> 10983 <p><a class="w3-text" href="#Noise Reduction, Dereverberation, and Echo Cancellation">Noise Reduction, Dereverberation, and Echo Cancellation</a></p> 10984 <p><a class="w3-text" href="#Computationally-Efficient Speech Enhancement">Computationally-Efficient Speech Enhancement</a></p> 10985 <p><a class="w3-text" href="#Zero-shot TTS">Zero-shot TTS</a></p> 10986 <p><a class="w3-text" href="#Noise Robustness, Far-Field, and Multi-Talker ASR">Noise Robustness, Far-Field, and Multi-Talker ASR</a></p> 10987 <p><a class="w3-text" href="#Contextual Biasing and Adaptation">Contextual Biasing and Adaptation</a></p> 10988 <p><a class="w3-text" href="#Spoken Language Understanding">Spoken Language Understanding</a></p> 10989 <p><a class="w3-text" href="#Spoken Machine Translation 1">Spoken Machine Translation 1</a></p> 10990 <p><a class="w3-text" href="#Hearing Disorders">Hearing Disorders</a></p> 10991 <p><a class="w3-text" href="#Speech Disorders 2">Speech Disorders 2</a></p> 10992 <p><a class="w3-text" href="#TAUKADIAL Challenge: Speech-Based Cognitive Assessment in Chinese and English (Special Session)">TAUKADIAL Challenge: Speech-Based Cognitive Assessment in Chinese and English (Special Session)</a></p> 10993 <p><a class="w3-text" href="#Show and Tell 1">Show and Tell 1</a></p> 10994 <p><a class="w3-text" href="#Keynote 2">Keynote 2</a></p> 10995 <p><a class="w3-text" href="#Phonetics and Phonology of Second Language Acquisition">Phonetics and Phonology of Second Language Acquisition</a></p> 10996 <p><a class="w3-text" href="#Corpora-based Approaches in Automatic Emotion Recognition">Corpora-based Approaches in Automatic Emotion Recognition</a></p> 10997 <p><a class="w3-text" href="#Analysis of Speakers States and Traits">Analysis of Speakers States and Traits</a></p> 10998 <p><a class="w3-text" href="#Spoofing and Deepfake Detection">Spoofing and Deepfake Detection</a></p> 10999 <p><a class="w3-text" href="#Audio Captioning, Tagging, and Audio-Text Retrieval">Audio Captioning, Tagging, and Audio-Text Retrieval</a></p> 11000 <p><a class="w3-text" href="#Generative Speech Enhancement">Generative Speech Enhancement</a></p> 11001 <p><a class="w3-text" href="#Speech Synthesis: Evaluation">Speech Synthesis: Evaluation</a></p> 11002 <p><a class="w3-text" href="#Multilingual ASR">Multilingual ASR</a></p> 11003 <p><a class="w3-text" href="#General Topics in ASR">General Topics in ASR</a></p> 11004 <p><a class="w3-text" href="#Spoken Language Understanding">Spoken Language Understanding</a></p> 11005 <p><a class="w3-text" href="#Speech and Multimodal Resources">Speech and Multimodal Resources</a></p> 11006 <p><a class="w3-text" href="#Pathological Speech Analysis 1">Pathological Speech Analysis 1</a></p> 11007 <p><a class="w3-text" href="#Speech and Language in Health: from Remote Monitoring to Medical Conversations - 1 (Special Session)">Speech and Language in Health: from Remote Monitoring to Medical Conversations - 1 (Special Session)</a></p> 11008 <p><a class="w3-text" href="#Speech and Brain">Speech and Brain</a></p> 11009 <p><a class="w3-text" href="#Innovative Methods in Phonetics and Phonology">Innovative Methods in Phonetics and Phonology</a></p> 11010 <p><a class="w3-text" href="#Voice, Tones and F0">Voice, Tones and F0</a></p> 11011 <p><a class="w3-text" href="#Emotion Recognition: Resources and Benchmarks">Emotion Recognition: Resources and Benchmarks</a></p> 11012 <p><a class="w3-text" href="#Speaker and Language Identification and Diarization">Speaker and Language Identification and Diarization</a></p> 11013 <p><a class="w3-text" href="#Audio-Text Retrieval">Audio-Text Retrieval</a></p> 11014 <p><a class="w3-text" href="#Speech Enhancement">Speech Enhancement</a></p> 11015 <p><a class="w3-text" href="#Speech Coding">Speech Coding</a></p> 11016 <p><a class="w3-text" href="#Speech Synthesis: Expressivity and Emotion">Speech Synthesis: Expressivity and Emotion</a></p> 11017 <p><a class="w3-text" href="#Speech Synthesis: Tools and Data">Speech Synthesis: Tools and Data</a></p> 11018 <p><a class="w3-text" href="#Speech Synthesis: Singing Voice Synthesis">Speech Synthesis: Singing Voice Synthesis</a></p> 11019 <p><a class="w3-text" href="#LLM in ASR">LLM in ASR</a></p> 11020 <p><a class="w3-text" href="#Vision and Speech">Vision and Speech</a></p> 11021 <p><a class="w3-text" href="#Spoken Document Summarization">Spoken Document Summarization</a></p> 11022 <p><a class="w3-text" href="#Speech and Language in Health: from Remote Monitoring to Medical Conversations - 2 (Special Sessions)">Speech and Language in Health: from Remote Monitoring to Medical Conversations - 2 (Special Sessions)</a></p> 11023 <p><a class="w3-text" href="#Show and Tell 2">Show and Tell 2</a></p> 11024 <p><a class="w3-text" href="#Prosody">Prosody</a></p> 11025 <p><a class="w3-text" href="#Foundational Models for Deepfake and Spoofed Speech Detection">Foundational Models for Deepfake and Spoofed Speech Detection</a></p> 11026 <p><a class="w3-text" href="#Speaker Recognition 1">Speaker Recognition 1</a></p> 11027 <p>
11027<a class="w3-text" href="#Source Separation 1">Source Separation 1</a></p> 11028 <p><a class="w3-text" href="#Audio-Visual and Generative Speech Enhancement">Audio-Visual and Generative Speech Enhancement</a></p> 11029 <p><a class="w3-text" href="#Speech Privacy and Bandwidth Expansion">Speech Privacy and Bandwidth Expansion</a></p> 11030 <p><a class="w3-text" href="#Speech Synthesis: Prosody">Speech Synthesis: Prosody</a></p> 11031 <p><a class="w3-text" href="#Accented Speech, Prosodic Features, Dialect, Emotion, Sound Classification">Accented Speech, Prosodic Features, Dialect, Emotion, Sound Classification</a></p> 11032 <p><a class="w3-text" href="#Neural Network Adaptation">Neural Network Adaptation</a></p> 11033 <p><a class="w3-text" href="#ASR and LLMs">ASR and LLMs</a></p> 11034 <p><a class="w3-text" href="#Pathological Speech Analysis 3">Pathological Speech Analysis 3</a></p> 11035 <p><a class="w3-text" href="#Speech Disorders 3">Speech Disorders 3</a></p> 11036 <p><a class="w3-text" href="#Speech Recognition with Large Pretrained Speech Models for Under-represented Languages (Special Session)">Speech Recognition with Large Pretrained Speech Models for Under-represented Languages (Special Session)</a></p> 11037 <p><a class="w3-text" href="#Speech Processing Using Discrete Speech Units (Special Session)">Speech Processing Using Discrete Speech Units (Special Session)</a></p> 11038 <p><a class="w3-text" href="#Keynote 3">Keynote 3</a></p> 11039 <p><a class="w3-text" href="#Databases and Progress in Methodology">Databases and Progress in Methodology</a></p> 11040 <p><a class="w3-text" href="#Articulation, Convergence and Perception">Articulation, Convergence and Perception</a></p> 11041 <p><a class="w3-text" href="#Speech Emotion Recognition">Speech Emotion Recognition</a></p> 11042 <p><a class="w3-text" href="#Self-Supervised Models in Speaker Recognition">Self-Supervised Models in Speaker Recognition</a></p> 11043 <p><a class="w3-text" href="#Speech Quality Assessment">Speech Quality Assessment</a></p> 11044 <p><a class="w3-text" href="#Privacy and Security in Speech Communication 1">Privacy and Security in Speech Communication 1</a></p> 11045 <p><a class="w3-text" href="#Speech Synthesis: Voice Conversion 2">Speech Synthesis: Voice Conversion 2</a></p> 11046 <p><a class="w3-text" href="#Speech Synthesis: Text Processing">Speech Synthesis: Text Processing</a></p> 11047 <p><a class="w3-text" href="#Training Methods, Self-Supervised Learning, Adaptation">Training Methods, Self-Supervised Learning, Adaptation</a></p> 11048 <p><a class="w3-text" href="#Novel Architectures for ASR">Novel Architectures for ASR</a></p> 11049 <p><a class="w3-text" href="#Multimodality and Foundation Models">Multimodality and Foundation Models</a></p> 11050 <p><a class="w3-text" href="#Spoken Dialogue Systems and Conversational Analysis 1">Spoken Dialogue Systems and Conversational Analysis 1</a></p> 11051 <p><a class="w3-text" href="#Speech Technology">Speech Technology</a></p> 11052 <p><a class="w3-text" href="#Pathological Speech Analysis 2">Pathological Speech Analysis 2</a></p> 11053 <p><a class="w3-text" href="#Speech Science, Speech Technology, and Gender (Special Session)">Speech Science, Speech Technology, and Gender (Special Session)</a></p> 11054 <p><a class="w3-text" href="#Speech Production and Perception">Speech Production and Perception</a></p> 11055 <p><a class="w3-text" href="#Phonetics and Phonology: Segmentals and Suprasegmentals">Phonetics and Phonology: Segmentals and Suprasegmentals</a></p> 11056 <p><a class="w3-text" href="#Topics in Paralinguistics">Topics in Paralinguistics</a></p> 11057 <p><a class="w3-text" href="#Emotion Recognition: Fairness, Variability, Uncertainty">Emotion Recognition: Fairness, Variability, Uncertainty</a></p> 11058 <p><a class="w3-text" href="#Speaker Verification">Speaker Verification</a></p> 11059 <p><a class="w3-text" href="#Spatial Audio and Acoustics">Spatial Audio and Acoustics</a></p> 11060 <p><a class="w3-text" href="#Generative Models for Speech and Audio">Generative Models for Speech and Audio</a></p> 11061 <p><a class="w3-text" href="#Speech and Audio Modelling">Speech and Audio Modelling</a></p> 11062 <p><a class="w3-text" href="#Multi-Channel Speech Enhancement">Multi-Channel Speech Enhancement</a></p> 11063 <p><a class="w3-text" href="#Speech Synthesis: Paradigms and Methods 1">Speech Synthesis: Paradigms and Methods 1</a></p> 11064 <p><a class="w3-text" href="#Speech Synthesis: Paradigms and Methods 2">Speech Synthesis: Paradigms and Methods 2</a></p> 11065 <p><a class="w3-text" href="#Neural Network Architectures for ASR 1">Neural Network Architectures for ASR 1</a></p> 11066 <p><a class="w3-text" href="#Error Correction and Rescoring">Error Correction and Rescoring</a></p> 11067 <p><a class="w3-text" href="#Spoken Language Understanding">Spoken Language Understanding</a></p> 11068 <p><a class="w3-text" href="#Spoken Dialogue Systems and Conversational Analysis 2">Spoken Dialogue Systems and Conversational Analysis 2</a></p> 11069 <p><a class="w3-text" href="#Computational Models of Human Language Acquisition, Perception, and Production (Special Session)">Computational Models of Human Language Acquisition, Perception, and Production (Special Session)</a></p> 11070 <p><a class="w3-text" href="#Show and Tell 3">Show and Tell 3</a></p> 11071 <p><a class="w3-text" href="#Phonetics, Phonology and Prosody">Phonetics, Phonology and Prosody</a></p> 11072 <p><a class="w3-text" href="#Segmentals">Segmentals</a></p> 11073 <p><a class="w3-text" href="#New Avenues in Emotion Recognition">New Avenues in Emotion Recognition</a></p> 11074 <p><a class="w3-text" href="#Speaker Diarization 2">Speaker Diarization 2</a></p> 11075 <p><a class="w3-text" href="#Speaker Recognition 2">Speaker Recognition 2</a></p> 11076 <p><a class="w3-text" href="#Speech and Audio Analysis">Speech and Audio Analysis</a></p> 11077 <p><a class="w3-text" href="#Speech Quality and Intelligibility: Prediction and Enhancement">Speech Quality and Intelligibility: Prediction and Enhancement</a></p> 11078 <p><a class="w3-text" href="#Speech Synthesis: Vocoders">Speech Synthesis: Vocoders</a></p> 11079 <p><a class="w3-text" href="#ASR Model Training Methods">ASR Model Training Methods</a></p> 11080 <p><a class="w3-text" href="#Cross-Lingual and Multilingual Processing">Cross-Lingual and Multilingual Processing</a></p> 11081 <p><a class="w3-text" href="#Speech Assessment">Speech Assessment</a></p> 11082 <p><a class="w3-text" href="#Question Answering from Speech and Spoken Dialogue Systems">Question Answering from Speech and Spoken Dialogue Systems</a></p> 11083 <p><a class="w3-text" href="#Spoken Dialogue Systems and Conversational Analysis 3">Spoken Dialogue Systems and Conversational Analysis 3</a></p> 11084 <p><a class="w3-text" href="#Dysarthric Speech Assessment">Dysarthric Speech Assessment</a></p> 11085 <p><a class="w3-text" href="#Spoken Language Models for Universal Speech Processing (Special Session)">Spoken Language Models for Universal Speech Processing (Special Session)</a></p> 11086 <p><a class="w3-text" href="#Keynote 4">Keynote 4</a></p> 11087 <p><a class="w3-text" href="#L1/L2 Acquisition and Cross-Linguistic Factors">L1/L2 Acquisition and Cross-Linguistic Factors</a></p> 11088 <p><a class="w3-text" href="#Speaker Stance, Emotion and Language-External Factors">Speaker Stance, Emotion and Language-External Factors</a></p> 11089 <p><a class="w3-text" href="#Experimental Phonetics and Laboratory Phonology">Experimental Phonetics and Laboratory Phonology</a></p> 11090 <p><a class="w3-text" href="#Speaker recognition evaluation and resources">Speaker recognition evaluation and resources</a></p> 11091 <p><a class="w3-text" href="#Speech Type Classification">Speech Type Classification</a></p> 11092 <p><a class="w3-text" href="#Target Speaker Extraction">Target Speaker Extraction</a></p> 11093 <p><a class="w3-text" href="#Speech Synthesis: Voice Conversion 3">Speech Synthesis: Voice Conversion 3</a></p> 11094 <p><a class="w3-text" href="#Speech Synthesis: Paradigms and Methods 3">Speech Synthesis: Paradigms and Methods 3</a></p> 11095 <p><a class="w3-text" href="#Privacy and Security in Speech Communication 2">Privacy and Security in Speech Communication 2</a></p> 11096 <p><a class="w3-text" href="#Streaming ASR">Streaming ASR</a></p> 11097 <p><a class="w3-text" href="#Computational Resource Constrained ASR">Computational Resource Constrained ASR</a></p> 11098 <p><a class="w3-text" href="#Evaluation of Speech Technology Systems">Evaluation of Speech Technology Systems</a></p> 11099 <p><a class="w3-text" href="#Neural Network Training for Speech Recognition">Neural Network Training for Speech Recognition</a></p> 11100 <p><a class="w3-text" href="#Leveraging Large Language Models and Contextual Features for Phonetic Analysis (Special Session)">Leveraging Large Language Models and Contextual Features for Phonetic Analysis (Special Session)</a></p> 11101 <p><a class="w3-text" href="#Responsible Speech Foundation Models (Special Session)">Responsible Speech Foundation Models (Special Session)</a></p> 11102 <p><a class="w3-text" href="#Multimodal Paralinguistics">Multimodal Paralinguistics</a></p> 11103 <p><a class="w3-text" href="#Automatic Emotion Recognition">Automatic Emotion Recognition</a></p> 11104 <p><a class="w3-text" href="#Self and Weakly-Labelled Speaker Verification">Self and Weakly-Labelled Speaker Verification</a></p> 11105 <p><a class="w3-text" href="#Acoustic Event Detection, Segmentation and Classification">Acoustic Event Detection, Segmentation and Classification</a></p> 11106 <p><a class="w3-text" href="#Speech and Audio Modelling">Speech and Audio Modelling</a></p> 11107 <p><a class="w3-text" href="#Fake Audio Detection">Fake Audio Detection</a></p> 11108 <p><a class="w3-text" href="#Deep Learning-Based Speech Enhancement: Approaches, Scalability, and Evaluation">Deep Learning-Based Speech Enhancement: Approaches, Scalability, and Evaluation</a></p> 11109 <p><a class="w3-text" href="#Speech Synthesis: Other Topics 1">Speech Synthesis: Other Topics 1</a></p> 11110 <p><a class="w3-text" href="#Speech Synthesis: Other Topics 2">Speech Synthesis: Other Topics 2</a></p> 11111 <p><a class="w3-text" href="#Speech synthesis: Cross-lingual and multilingual aspects">Speech synthesis: Cross-lingual and multilingual aspects</a></p> 11112 <p><a class="w3-text" href="#Noise, Far-Field, Multi-Talker, Enhancement, Audio Classification">Noise, Far-Field, Multi-Talker, Enhancement, Audio Classification</a></p> 11113 <p><a class="w3-text" href="#Self-Supervised Learning for ASR">Self-Supervised Learning for ASR</a></p> 11114 <p><a class="w3-text" href="#Spoken Term Detection and Speech Retrieval">Spoken Term Detection and Speech Retrieval</a></p> 11115 <p><a class="w3-text" href="#Speech Disorders 1">Speech Disorders 1</a></p> 11116 <p><a class="w3-text" href="#Connecting Speech-science and Speech-technology for Childrenâs Speech (Special Session)">Connecting Speech-science and Speech-technology for Childrenâs Speech (Special Session)</a></p> 11117 <p><a class="w3-text" href="#Show and Tell 4">Show and Tell 4</a></p> 11118 </div> 11119 </div> 11120 11121 11122
11122<script> 11123 function myFunction() { 11124 var x = document.getElementById("smallnav"); 11125 if (x.className.indexOf("w3-show") == -1) { 11126 x.className += " w3-show"; 11127 } else { 11128 x.className = x.className.replace(" w3-show", ""); 11129 } 11130 } 11131 11132 // Get the modal 11133 var modal = document.getElementById('sessionchooser'); 11134 11135 // When the user clicks anywhere outside of the modal, close it 11136 window.onclick = function(event) { 11137 if (event.target == modal) { 11138 modal.style.display = "none"; 11139 } 11140 } 11141 11142 11143 $(document).ready(function() { 11144 11145 $('#paper_table').DataTable( { 11146 data: [['Zhiqi Ai, Zhiyong Chen, Shugong Xu', 'MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting', 'ai24_interspeech', 'text embeddings libriphrase speech mining confusable enrollment applicability distinguishing solely'], ['Ye-Xin Lu, Yang Ai, Zheng-Yan Sheng, Zhen-Hua Ling', 'MultiStage Speech Bandwidth Extension with Flexible Sampling Rate Control', 'lu24_interspeech', 'ms-bwe bwe block generation stage sixty one-stage featuring source multi-stage'], ['Olympia Simantiraki, Martin Cooke', "Listeners' F0 preferences in quiet and stationary noise", 'simantiraki24_interspeech', 'alter mean intelligibility impact original inexperienced maximise comprehensibility variation masker'], ['Jennifer Williams, Eike Schneiders, Henry Card, Tina Seabrooke, Beatrice Pakenham-Walsh, Tayyaba Azim, Lucy Valls-Reed, Ganesh Vigneswaran, John Robert Bautista, Rohan Chandra, Arya Farahi', 'Predicting Acute Pain Levels Implicitly from Vocal Features', 'williams24_interspeech', 'clinical triage high-stakes three-class communication explainable cold stroke support emergency'], ['Xingxing Yang', 'G2PA: G2P with Aligned Audio for Mandarin Chinese', 'yang24_interspeech', 'pronunciation github solely ambiguity phoneme text disregarding preprocess polyphone repository'], ['Sizhou Chen, Yibo Bai, Jiadi Yao, Xiao-Lei Zhang, Xuelong Li', 'Textual-Driven Adversarial Purification for Speaker Verification', 'chen24_interspeech', 'diffusion audio defense attack textual neglecting diffusion-based model causing mistake'], ['Thien-Phuc Doan, Long Nguyen-Vu, Kihun Hong, Souhwan Jung', 'Balance, Multiple Augmentation, and Re-synthesis: A Triad Training Strategy for Enhanced Audio Deepfake Detection', 'doan24_interspeech', 'assembling surpassed set sample mini-batch in-the-wild re-synthesized benchmarking balancing achievable'], ['Mohan Li, Simon Keizer, Rama Doddipatla', 'Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language Understanding', 'li24_interspeech', 'slu slurp question-answering system optimising comprehend model cross-corpus excessive comparably'], ['Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Noboru Harada, Masahiro Yasuda, Shunsuke Tsubaki, Keisuke Imoto', 'M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation', 'niizumi24_interspeech', 'learns audio transfer performs gtzan versatile aligns classification zero-shot pre-training'], ['Nicolas M. Müller, Piotr Kawa, Shen Hu, Matthias Neu, Jennifer Williams, Philip Sperl, Konstantin Böttinger', 'A New Approach to Voice Authenticity', 'muller24_interspeech', 'edits fake editing binary maliciously ethically pinpointing nancy longstanding delineate'], ['Korbinian Kuhn, Verena Kersken, Gottfried Zimmermann', 'Beyond Levenshtein: Leveraging Multiple Algorithms for Robust Word Error Rate Computations And Granular Error Classifications', 'kuhn24_interspeech', 'punctuation wer non-semantic token-based exemplary common pre-processed visualisation substituting equivalence'], ['Jiatong Shi, Yueqian Lin, Xinyi Bai, Keyi Zhang, Yuning Wu, Yuxun Tang, Yifeng Yu, Qin Jin, Shinji Watanabe', 'Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing', 'shi24_interspeech', 'svs espnet datasets synthesis expansive multi-singer curation complemented supplementary thorough'], ['Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti', 'Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters', 'cappellazzo24_interspeech', 'moe expert burgeoning computational parameter-efficient underexplored affordable adapter dense ablation'], ['Titouan Parcollet, Rogier van Dalen, Shucong Zhang, Sourav Bhattacharya', 'SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding', 'parcollet24_interspeech', 'quot inference memory cheaper summarises slowing asr exceed quadratic consumption'], ['Soham Deshmukh, Rita Singh, Bhiksha Raj', 'Domain Adaptation for Contrastive Audio-Language Models', 'deshmukh24_interspeech', 'alm zero-shot alms prompt generalization access require performance test-time enforcing'], ['Jan Pešán, VojtÄch JuÅÃk, Martin Karafiát, Jan Äernocký', 'BESST Dataset: A Multimodal Resource for Speech-based Stress Detection and Analysis', 'pesan24_interspeech', 'comprises speech physiological collection electrocardiogram data electrodermal clean temperature immersion'], ['Martijn Bentum, Louis ten Bosch, Tom Lentz', 'The Processing of Stress in End-to-End Automatic Speech Recognition Models', 'bentum24_interspeech', 'classifier correlate denominator layer acoustic mere vowel asr reflection representation'], ['Zhouyuan Huo, Dongseong Hwang, Gan Song, Khe Chai Sim, Weiran Wang', 'AdaRA: Adaptive Rank Allocation of Residual Adapters for Speech Foundation Model', 'huo24_interspeech', 'parameter additive adaptation bottleneck dimension o
11146ptimal allocating layer possessing efficient'], ['Xinlei Niu, Jing Zhang, Charles Patrick Martin', 'HybridVC: Efficient Voice Style Conversion with Text and Audio Prompts', 'niu24_interspeech', 'contrastive latent embeddings cvae optimises user-defined personalised validates speaker underscore'], ['Oleg Rybakov, Dmitriy Serdyuk, Chengjian Zheng', 'USM RNN-T model weights binarization', 'rybakov24_interspeech', 'size grows serving cost float reduction dominated attractive transducer quantization'], ['Ji-Sang Hwang, Hyeongrae Noh, Yoonseok Hong, Insoo Oh', 'X-Singer: Code-Mixed Singing Voice Synthesis via Cross-Lingual Learning', 'hwang24_interspeech', 'svs lyric annotation phoneme synthesize encoder mixture ability code-switching intra'], ['Yingying Gao, Shilei Zhang, Chao Deng, Junlan Feng', 'GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model', 'gao24_interspeech', 'superb wavlm teacher autoregressively resource layer-by-layer hidden hinder hubert distillation'], ['Rui Cao, Tianrui Wang, Meng Ge, Andong Li, Longbiao Wang, Jianwu Dang, Yungang Jia', 'VoiCor: A Residual Iterative Voice Correction Framework for Monaural Speech Enhancement', 'cao24_interspeech', 'dns-challenge solution non-linearly concretely issue structure continue chain refine pesq'], ['Heeseung Kim, Sang-gil Lee, Jiheum Yeom, Che Hyun Lee, Sungwon Kim, Sungroh Yoon', 'VoiceTailor: Lightweight Plug-In Adapter for Diffusion-Based Personalized Text-to-Speech', 'kim24_interspeech', 'adaptation parameter-efficient pivotal tt speaker pre-trained equipping module lora speaker-adaptive'], ['Jizhong Liu, Gang Li, Junbo Zhang, Heinrich Dinkel, Yongqing Wang, Zhiyong Yan, Yujun Wang, Bin Wang', 'Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding', 'liu24_interspeech', 'aac llm token pre-trained encoder decoder effectivity ced llama querying'], ['Siqi Sun, Korin Richmond', 'Learning Pronunciation from Other Accents via Pronunciation Knowledge Transfer', 'sun24_interspeech', 'seq word target bootstrapping frontend annotating transferred accent coverage type'], ['Masaya Ohagi, Tomoya Mizumoto, Katsumasa Yoshikawa', 'Investigation of look-ahead techniques to improve response time in spoken dialogue system', 'ohagi24_interspeech', 'user speed utterance chatbot bot finish returned delayed task-oriented say'], ['Si Chen, Bruce Xiao Wang, Yitian Hong, Fang Zhou, Angel Chan, Po-yi Tang, Bin Li, Chunyi Wen, James Cheung, Yan Liu, Zhuoming Chen', 'Acoustic changes in speech prosody produced by children with autism after robot-assisted speech training', 'chen24b_interspeech', 'autistic marking focus typically-developing variability monotone post-training designed mixed-effects signalling'], ['Wenbin Wang, Yang Song, Sanjay Jha', 'GLOBE: A High-quality English Corpus with Global Accents for Zero-shot Speaker Adaptive Text-to-Speech', 'wang24b_interspeech', 'worldwide metadata populating tt libritts curated rigorous vctk generalizability trained'], ['Jaden Pieper, Stephen Voran', 'AlignNet: Learning dataset score alignment functions to enable better training of speech quality estimators', 'pieper24_interspeech', 'mdf datasets aligner estimator us intermediate successful larger pretrains no-reference'], ['Ji Won Yoon, Beom Jun Woo, Nam Soo Kim', 'HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition', 'yoon24_interspeech', 'exit inference branch intermediate stop model hidden-unit returned slowing confident'], ['Hideyuki Oiso, Yuto Matsunaga, Kazuya Kakizaki, Taiki Miyagawa', 'Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset', 'oiso24_interspeech', 'add computational gap challenge extra iii countering cost source-target plug-in'], ['Bunlong Lay, Timo Gerkmann', 'An Analysis of the Variance of Diffusion-based Speech Enhancement', 'lay24_interspeech', 'diffusion attenuation noise equation differential environmental stochastic adding gaussian concretely'], ['Lukas Christ, Shahin Amiriparian, Friederike Hawighorst, Ann-Kathrin Schill, Angelo Boutalikakis, Lorenz Graf-Vlachy, Andreas König, Björn Schuller', 'This Paper Had the Smartest Reviewers
11146- Flattery Detection Utilising an Audio-Textual Transformer-Based Approach', 'christ24_interspeech', 'whisper textual multimodal modality praise compliment bonding build roberta ast'], ['Zengrui Jin, Yifan Yang, Mohan Shi, Wei Kang, Xiaoyu Yang, Zengwei Yao, Fangjun Kuang, Liyong Guo, Lingwei Meng, Long Lin, Yong Xu, Shi-Xiong Zhang, Daniel Povey', 'LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization', 'jin24_interspeech', 'far-field daunting multitalker landscape foundational crafted convenience generality encompassing challenge'], ['Andreas Triantafyllopoulos, Anton Batliner, Wolfgang Mayr, Markus Fendler, Florian Pokorny, Maurice Gerczuk, Shahin Amiriparian, Thomas Berghaus, Björn Schuller', 'Sustained Vowels for Pre- vs Post-Treatment COPD Classification', 'triantafyllopoulos24_interspeech', 'lung disease patient exacerbation obstructed hospitalisation pulmonary read acute obstructive'], ['Andreas Triantafyllopoulos, Anton Batliner, Simon Rampp, Manuel Milling, Björn Schuller', 'INTERSPEECH 2009 Emotion Challenge Revisited: Benchmarking 15 Years of Progress in Speech Emotion Recognition', 'triantafyllopoulos24b_interspeech', 'ser official outperform corollary -the set winner newer hyperparameter model'], ['Andreas Triantafyllopoulos, Björn Schuller', 'Enrolment-based personalisation for improving individual-level fairness in speech emotion recognition', 'triantafyllopoulos24c_interspeech', 'aggregated evaluation ser one-size-fits-all individualistic failing uncovered enrolment speaker across'], ['Zhenyu Wang, Shuyu Kong, Li Wan, Biqiao Zhang, Yiteng Huang, Mumin Jin, Ming Sun, Xin Lei, Zhaojun Yang', 'Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning', 'wang24c_interspeech', 'liconet qbye kw conformer framework fa tailoring speaker-invariant frr customized'], ['Daniela A. Wiepert, Rene L. Utianski, Joseph R. Duffy, John L. Stricker, Leland R. Barnard, David T. Jones, Hugo Botha', 'Speech foundation models in healthcare: Effect of layer selection on pathological speech feature prediction', 'wiepert24_interspeech', 'diagnosis treatment clinical best out-of-distribution lower average increase worst neurological'], ['Yuang Li, Jiawei Yu, Min Zhang, Mengxin Ren, Yanqing Zhao, Xiaofeng Zhao, Shimin Tao, Jinsong Su, Hao Yang', 'Using Large Language Model for End-to-End Chinese ASR and NER', 'li24b_interspeech', 'decoder-only llm encoder-decoder token long-form speech infers connect taxonomy cross-attention'], ['Yuang Li, Min Zhang, Chang Su, Yinglu Li, Xiaosong Qiao, Mengxin Ren, Miaomiao Ma, Daimeng Wei, Shimin Tao, Hao Yang', 'A Multitask Training Approach to Enhance Whisper with Open-Vocabulary Keyword Spotting', 'li24c_interspeech', 'ov-kws entity asr named aishell plug-and-play user-defined terminology model hot'], ['Li Xiao, Lucheng Fang, Yuhong Yang, Weiping Tu', 'LungAdapter: Efficient Adapting Audio Spectrogram Transformer for Lung Sound Classification', 'xiao24_interspeech', 'fine-tuning large-scale pre-trained model full parameter adapter predominant frozen entail'], ['Yi Gao, Xiang Su', 'Low Complexity Echo Delay Estimator Based on Binarized Feature Matching', 'gao24b_interspeech', 'bfm method aec webrtc dearth nn-based traditional encompassing canceller serf'], ['Yang Ai, Ye-Xin Lu, Xiao-Hang Jiang, Zheng-Yan Sheng, Rui-Chen Zheng, Zhen-Hua Ling', 'A Low-Bitrate Neural Audio Codec Framework with Bandwidth Reduction and Recovery for High-Sampling-Rate Waveforms', 'ai24b_interspeech', 'bitrate waveform quantizer sampling encoder decoder outputted bitrates decodes recovers'], ['Toshio Irino, Shintaro Doan, Minami Ishikawa', 'Signal processing algorithm effective for sound quality of hearing loss simulators ', 'irino24_interspeech', 'whis perceptible simulator distortion less filterbank version listener synthesis cambridge'], ['Hualei Wang, Jianguo Mao, Zhifang Guo, Jiarui Wan, Hong Liu, Xiangdong Wang', 'Leveraging Language Model Capabilities for Sound Event Detection', 'wang24d_interspeech', 'multi-modality audio generation timestamps sed feature showcase abundant classification flexibly'], ['Mohammad Hassan Vali, Tom Bäckström', 'Privacy PORCUPINE: Anonymization of Speaker Attributes Using Occurrence Normalization for Space-Filling Vector Quantization', 'vali24_interspeech', 'information bottleneck private thus disclosure quantifiable privacy-preserving uneven protecting quantizing'], ['Jingyao Wu, Ting Dang, Vidhyasaharan Sethu, Eliathamby Ambikairajah', 'Dual-Constrained Dynamical Neural ODEs for Ambiguity-aware Continuous Emotion Prediction', 'wu24_interspeech', 'distribution ambiguity recola parameterised dynamic range evolve restrict smoothly less'], ['Suhas BN, Amanda Rebar, Saeed Abdullah', 'Speaking of Health: Leveraging Large Language Models to assess Exercise Motivation and Behavior of Rehabilitation Patients', 'bn24_interspeech', 'session establish outcome wellbeing compliance decision-making thematic sentiment ground-truth augmenting'], ['Yu-Wen Chen, Zhou Yu, Julia Hirschberg', 'MultiPA: A Multi-task Speech Pronunciation Assessment Model for Open Response Scenarios', 'chen24c_interspeech', 'sentence-level open-response accuracy multitask offering predominantly real-life out-of-domain reached fluency'], ['Candy Olivia Mawalim, Shogo Okada, Masashi Unoki', 'Are Recent Deep Learning-Based Speech Enhancement Methods Ready to Confront Real-World Noisy Environments?', 'mawalim24_interspeech', 'fullsubnet denoiser scenario datasets hallucination nuanced assess asr-based emphasizes struggle'], ['Jihyun Mun, Sunhee Kim, Minhwa Chung', 'Developing an End-to-End Framework for Predicting the Social Communication Severity Scores of Children with Autism Spectrum Disorder', 'mun24_interspeech', 'asd diagnostic fine-tuned human-rated lifelong tool necessitate foundational profound objective'], ['Mewlude Nijat, Chen Chen, Dong Wang, Askar Hamdulla', 'UY/CH-CHILD -- A Public Chinese L2 Speech Database of Uyghur Children', 'nijat24_interspeech', 'kindergarten pronunciation school primary intriguing mature downloaded avenue showcase org'], ['Steven Vander Eeckt, Hugo Van hamme', 'Unsupervised Online Continual Learning for Automatic Speech Recognition', 'vandereeckt24_interspeech', 'ocl uocl forgetting continually leveraging asr domain supervised adaptation realm'], ['Robin Scheibler, Yusuke Fujita, Yuma Shirahata, Tatsuya Komatsu', 'Universal Score-based Speech Enhancement with High Content Preservation', 'scheibler24_interspeech', 'universe diffusion adversarial three-fold loss low-rank favorably fidelity promote stability'], ['Minyoung Lee, Eunil Park, Sungeun Hong', 'FVTTS : Face Based Voice Synthesis for Text-to-Speech', 'lee24_interspeech', 'face-based personalized expressive identity image tt sample individual voice-based personalization'], ['Liang Tao, Maoshen Jia, Yonggang Hu, Changchun Bao', 'Spatial Acoustic Enhancement Using Unbiased Relative Harmonic Coefficients', 'tao24_interspeech', 'n
11146oisy source entire spherical multiplying compactly denoted environment domain clue'], ['Xin Jing, Luyang Zhang, Jiangjian Xie, Alexander Gebhard, Alice Baird, Björn Schuller', 'DB3V: A Dialect Dominated Dataset of Bird Vocalisation for Cross-corpus Bird Species Recognition', 'jing24_interspeech', 'publicly call zenodo region impedes contiguous mitigation benchmarking across acknowledged'], ['Da Mu, Zhicheng Zhang, Haobo Yue', 'MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection', 'mu24_interspeech', 'mff seld spatial module temporal spectral subnetworks localizing three-stage challenge'], ['Hao Yang, Min Zhang, Minghan Wang, Jiaxin Guo', 'RASU: Retrieval Augmented Speech Understanding through Generative Modeling', 'yang24b_interspeech', 'slu prompt retrieved rag language intent transcript spoken capability retrieval-based'], ['Julius Richter, Yi-Chiao Wu, Steven Krenn, Simon Welker, Bunlong Lay, Shinji Watanabe, Alexander Richard, Timo Gerkmann', 'EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation', 'richter24_interspeech', 'online freeform totalling style uploaded download non-verbal instrumental server blind'], ['Vladimir Despotovic, Abir Elbéji, Petr V. Nazarov, Guy Fagherazzi', 'Multimodal Fusion for Vocal Biomarkers Using Vector Cross-Attention', 'despotovic24_interspeech', 'modality voice standardized sustained phonation person reading biomarker single vowel'], ['Liming Wang, Yuan Gong, Nauman Dawalatabad, Marco Vilela, Katerina Placek, Brian Tracey, Yishu Gong, Alan Premasiri, Fernando Vieira, James Glass', 'Automatic Prediction of Amyotrophic Lateral Sclerosis Progression using Longitudinal Speech Transformer', 'wang24e_interspeech', 'al disease recording best auc interpretable network-based careful fine-grained pretrained'], ['Yujia Wang, Hexin Liu, Leibny Paola Garcia', 'Bridging Child-Centered Speech Language Identification and Language Diarization via Phonetics', 'wang24f_interspeech', 'lid fine-tuning back-end scoring pre-trained merlion slicing enriching inspiration needing'], ['Erfan Loweimi, Mengjie Qian, Kate Knill, Mark Gales', 'On the Usefulness of Speaker Embeddings for Speaker Retrieval in the Wild: A Comparative Study of x-vector and ECAPA-TDNN Models', 'loweimi24_interspeech', 'synopsis speechbrain develop nemo bbc archival posing assess toolkits encompasses'], ['Zhengxiao Li, Nakamasa Inoue', 'Locally Aligned Rectified Flow Model for Speech Enhancement Towards Single-Step Diffusion', 'li24d_interspeech', 'larf transport equation differential wsj mapping voicebank-demand clean si-sdr noisy'], ['Jeehye Lee, Hyeji Seo', 'Online Knowledge Distillation of Decoder-Only Large Language Models for Efficient Speech Recognition', 'lee24b_interspeech', 'llm cer inference decoder reduction relative cost aed dataset task'], ['Yixuan Zhang, Hao Zhang, Meng Yu, Dong Yu', 'Neural Network Augmented Kalman Filter for Robust Acoustic Howling Suppression', 'zhang24_interspeech', 'ahs refining standalone adaptability performance method covariance validate thereby obtaining'], ['Dong Yang, Tomoki Koriyama, Yuki Saito', 'Frame-Wise Breath Detection with Self-Training: An Exploration of Enhancing Breath Naturalness in Text-to-Speech', 'yang24c_interspeech', 'annotation model mark up-sampling tt pseudo-labeling position synthesizes human-like conformer'], ['Hitoshi Suda, Aya Watanabe, Shinnosuke Takamichi', 'Who Finds This Voice Attractive? A Large-Scale Experiment Using In-the-Wild Data', 'suda24_interspeech', 'likability gender regarding age favorite corpus speech announcement listener speaker'], ['Mayank Kumar Singh, Naoya Takahashi, Weihsiang Liao, Yuki Mitsufuji', 'SilentCipher: Deep Audio Watermarking', 'singh24_interspeech', 'message imperceptible robustness introduce learning-based encode capacity enhancing enabling watermark'], ['Hyun Myung Kim, Kangwook Jang, Hoirin Kim', 'One-class learning with adaptive centroid shift for audio deepfake detection', 'kim24b_interspeech', 'bonafide ac representation unseen embeddings cluster well-separated t-sne disentangles system'], ['Constantijn Kaland, Jeremy Steffman, Jennifer Cole', 'K-means and hierarchical clustering of f0 contours', 'kaland24_interspeech', 'cluster intonation outcome difference popular research decision analysis time-series imitated'], ['Constantijn Kaland, Maria Lialiou', 'Quantity-sensitivity affects recall performance of word stress', 'kaland24b_interspeech', 'var pattern listener greek language segmental memorizing german variable hypothesizes'], ['Loukas Ilias, Dimitris Askounis', 'A Cross-Attention Layer coupled with Multimodal Fusion Methods for Recognizing Depression from Spontaneous Speech', 'ilias24_interspeech', 'perform lifeless activity people biomarker existing diagnosing feel depressed productivity'], ['Francesco Paissan, Elisabetta Farella', 'tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models', 'paissan24_interspeech', 'clap contrastive event complexity text-to-audio detection employment sound less distillation'], ['Yiwen Wang, Xihong Wu', 'TSE-PI: Target Sound Extraction under Reverberant Environments with Pitch Information', 'wang24g_interspeech', 'tse gammatone filterbank fsd feature-wise provided asa model learnable clue'], ['Chin Yuen Kwok, Jia Qi Yip, Eng Siong Chng', 'Continual Learning Optimizations for Auto-regressive Decoder of Multilingual ASR systems', 'kwok24_interspeech', 'masr token pre-trained re-scaling unused freezing hypothesise surgery language sub-optimal'], ['Nicolas Gengembre, Olivier Le Blouch, Cédric Gendrot', 'Disentangling prosody and timbre embeddings via voice conversion', 'gengembre24_interspeech', 'converted anonymization architecture speaker perfectly expressivity source prosodic disentangle preservation'], ['Masato Murata, Koichi Miyazaki, Tomoki Koriyama', 'An Attribute Interpolation Method in Speech Synthesis by Model Merging', 'murata24_interspeech', 'base merged task intensity emotion generation module control specific creates'], ['Quan Wang, Yiling Huang, Guanlong Zhao, Evan Clark, Wei Xia, Hank Liao', 'DiarizationLM: Speaker Diarization Post-Processing with Large Language Models', 'wang24h_interspeech', 'llm rel finetuned output framework wder post-process optionally dataset off-the-shelf'], ['Pawel Bujnowski, Bartlomiej Kuzma, Bartlomiej Paziewski, Jacek Rutkowski, Joanna Marhula, Zuzanna Bordzicka, Piotr Andruszkiewicz', 'SAMSEMO: New dataset for multilingual and multimodal emotion recognition', 'bujnowski24_interspeech', 'scene video cmu-mosei datasets class imbalanced audio metadata popularity heterogeneous'], ['Hyeonuk Nam, Seong-Hu Kim, Deokki Min, Junhyeok Lee, Yong-Hwa Park', 'Diversifying and Expanding Frequency-Adaptive Convolution Kernels for Sound Event Detection', 'nam24_interspeech', 'conv basis dilation dilated size frequency dfd diversify class-wise psds'], ['Jihwan Lee, Aditya Kommineni, Tiantian Feng, Kleanthis Avramidis, Xuan Shi, Sudarsana Reddy Kadiri, Shrikanth Narayanan', 'Toward Fully-End-to-End Listened Speech Decoding from EEG Signals', 'lee24c_interspeech', 'connector module learns waveform single-step unveil characteristic framework bridge com'], ['Tuochao Chen, Qirui Wang, Bohan Wu, Malek Itani, Emre Sef
11146ik Eskimez, Takuya Yoshioka, Shyamnath Gollakota', 'Target conversation extraction: Source separation using turn-taking dynamics', 'chen24d_interspeech', 'interfering -speaker speaker amidst participant uniquely accomplish engaged noise feasibility'], ['Youngmoon Jung, Seungjin Lee, Joon-Young Yang, Jaeyoung Roh, Chang Woo Han, Hoon-Young Cho', 'Relational Proxy Loss for Audio-Text based Keyword Spotting', 'jung24_interspeech', 'embeddings text kw enrollment within proxy-based point-to-point acoustic convenience focus'], ['Jaejun Lee, Yoori Oh, Injune Hwang, Kyogu Lee', 'Hear Your Face: Face-based voice conversion with F0 estimation', 'lee24d_interspeech', 'facial delf fundamental characteristic target framework frequency emerging align solely'], ['Eunik Park, Daehyun Ahn, Hyungjun Kim', 'RepTor: Re-parameterizable Temporal Convolution for Keyword Spotting via Differentiable Kernel Search', 'park24_interspeech', 'kw device mobile model re-parameterized galaxy top- plain smart feed-forward'], ['Seonwoo Lee, Sunhee Kim, Minhwa Chung', 'Automatic Assessment of Speech Production Skills for Children with Cochlear Implants Using Wav2Vec2.0 Acoustic Embeddings', 'lee24e_interspeech', 'ci adult model korean-speaking multi-head pearson therapy trait assessing self-supervised'], ['Hokuto Munakata, Ryo Terashima, Yusuke Fujita', 'Song Data Cleansing for End-to-End Neural Singer Diarization Using Neural Analysis and Synthesis Framework', 'munakata24_interspeech', 'singing choral eend non-overlapped solo convert popular duet mitigates model'], ['Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang, Bin Wang', 'Streaming Audio Transformers for Online Audio Tagging', 'dinkel24_interspeech', 'sat sota usage delay memory vit benchmarked audioset widely-used long-range'], ['Qinglin Meng, Min Liu, Kaixun Huang, Kun Wei, Lei Xie, Zongfeng Quan, Weihong Deng, Quan Lu, Ning Jiang, Guoqing Zhao', 'SEQ-former: A context-enhanced and efficient automatic speech recognition framework', 'meng24_interspeech', 'contextual efficiency ctc asr decoder spike reduce prediction information private'], ['Yusuke Fujita, Tatsuya Komatsu', 'Audio Fingerprinting with Holographic Reduced Representations', 'fujita24_interspeech', 'fingerprint resolution time decimation method combined original circular summation aggregation'], ['Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang, Bin Wang', 'Scaling up masked audio encoder learning for general audio classification', 'dinkel24b_interspeech', 'music environmental ssl voxlingua competes nearest-neighbor crema-d ssl-based speech billion'], ['Nicolas M. Müller, Nicholas Evans, Hemlata Tak, Philip Sperl, Konstantin Böttinger', 'Harder or Different? Understanding Generalization of Audio Deepfake Detection', 'muller24b_interspeech', 'deepfakes hardness component gap model newer question generated fundamentally decomposing'], ['Shihao Chen, Yu Gu, Jie Zhang, Na Li, Rilin Chen, Liping Chen, Lirong Dai', 'LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance', 'chen24e_interspeech', 'svc timbre ldm classifier-free pretrain original vits leakage inevitable editing'], ['Haochen Wu, Wu Guo, Zhentao Zhang, Wenting Zhao, Shengyu Peng, Jie Zhang', 'Spoofing Speech Detection by Modeling Local Spectro-Temporal and Long-term Dependency', 'wu24b_interspeech', 'ssd branch artifact temporal bilstm-based exploit global dual-branch attention reside'], ['Haochen Wu, Wu Guo, Shengyu Peng, Zhuhai Li, Jie Zhang', 'Adapter Learning from Pre-trained Model for Robust Spoof Speech Detection', 'wu24c_interspeech', 'backbone wav vec local-global freezing appended task-dependent catastrophic over-fitting wavlm'], ['Yuankun Xie, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Xiaopeng Wang, Haonnan Cheng, Long Ye, Jianhua Tao', 'Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategy', 'xie24_interspeech', 'ood identifying nsd post-hoc showcasing logits sample urgent proliferation detection'], ['Hui-Peng Du, Ye-Xin Lu, Yang Ai, Zhen-Hua Ling', 'BiVocoder: A Bidirectional Neural Vocoder Integrating Feature Extraction and Waveform Generation', 'du24_interspeech', 'stft amplitude phase tt restores spectrum comprehensively symmetric analysis-synthesis reverse'], ['Tomoki Honda, Shinsuke Sakai, Tatsuya Kawahara', 'Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer', 'honda24_interspeech', 'mhsa hungry layer self-attention computation state-space csj multi-head deterioration unreliable'], ['Shuaishuai Ye, Shunfei Chen, Xinhui Hu, Xinkang Xu', 'SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR', 'ye24_interspeech', 'moe router layer encoder decoder blank language equipped lid ctc'], ['Shengyu Peng, Wu Guo, Haochen Wu, Zuoliang Li, Jie Zhang', 'Fine-tune Pre-Trained Models with Multi-Level Feature Fusion for Speaker Verification', 'peng24_interspeech', 'ptm afm dual-branch merge back-end front-end ptms layer fbank aggregated'], ['Tongtao Ling, Yutao Lai, Lei Chen, Shilei Huang, Yi Liu', 'A Small and Fast BERT for Chinese Medical Punctuation Restoration', 'ling24_interspeech', 'pre-training apr fine-tuning mark clinical pre-trained model roberta reformulate distilled'], ['Qian Yang, Jialong Zuo, Zhe Su, Ziyue Jiang, Mingze Li, Zhou Zhao, Feiyang Chen, Zhefeng Wang, Baoxing Huai', 'MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis', 'yang24d_interspeech', 'open style scenario user-specific prosody prompting multiple source entail audio'], ['Malo Maisonneuve, Corinne Fredouille, Muriel Lalain, Alain Ghio, Virginie Woisard', 'Towards objective and interpretable speech disorder assessment: a comparative analysis of CNN and transformer-based models', 'maisonneuve24_interspeech', 'hnc pathological wav vec patient impact datasets neck unbiased pave'], ['Ryo
11146Setoguchi, Yoshiko Arimoto', 'Acoustical analysis of the initial phones in speech-laugh', 'setoguchi24_interspeech', 'anova speech vowel glmms th-order lower-order variable coefficient explanatory elucidate'], ['Hao Shi, Tatsuya Kawahara', 'Dual-path Adaptation of Pretrained Feature Extraction Module for Robust Automatic Speech Recognition', 'shi24b_interspeech', 'adapter finetuning path encoder noisy effective transformer achieving data freezing'], ['Thanh Lan Truong, Andrea Weber', 'Ethnolinguistic Identification of Vietnamese-German Heritage Speech', 'truong24_interspeech', 'asian german vietnamese listener speaker background identify chance accurately monotonized'], ['Oliver Niebuhr, Nafiseh Taghva', 'How rhythm metrics are linked to produced and perceived speaker charisma', 'niebuhr24_interspeech', 'presentation investor rhythmic element charismatic medium-sized duration-based committed recorded pvi'], ['Shahin Amiriparian, Filip PackaÅ, Maurice Gerczuk, Björn W. Schuller', 'ExHuBERT: Enhancing HuBERT Through Block Extension and Fine-Tuning on 37 Emotion Datasets', 'amiriparian24_interspeech', 'ser duplicate freeze huggingface layer skip gather adaptability twofold backbone'], ['Jie Lin, Xiuping Yang, Li Xiao, Xinhong Li, Weiyan Yi, Yuhong Yang, Weiping Tu, Xiong Chen', 'SimuSOE: A Simulated Snoring Dataset for Obstructive Sleep Apnea-Hypopnea Syndrome Evaluation during Wakefulness', 'lin24_interspeech', 'osahs snore obstruction airway upper signal datasets intentionally emitted chronic'], ['Shoval Messica, Yossi Adi', 'NAST: Noise Aware Speech Tokenization for Speech Language Models', 'messica24_interspeech', 'setup task disentanglement lastly representation com github serf iii signal'], ['Chiara Riegger, Tina Bögel, George Walkden', 'The prosody of the verbal prefix ge-: historical and experimental evidence', 'riegger24_interspeech', 'old negation preceding trochaic foot closure rhythmic auxiliary principle word'], ['Kexu Liu, Yuanxin Wang, Shengchen Li, Xi Shao', 'Speech Formants Integration for Generalized Detection of Synthetic Speech Spoofing Attacks', 'liu24b_interspeech', 'multi-view xls-r unseen variance feature one-class compactly dynamic gating struggle'], ['Zhe Li, Man-wai Mak, Hung-yi Lee, Helen Meng', 'Parameter-efficient Fine-tuning of Speaker-Aware Dynamic Prompts for Speaker Verification', 'li24e_interspeech', 'pool prompt transformer pre-trained tuning tunable resulting overfit plasticity learnable'], ['Bolaji Yusuf, Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran', 'Speculative Speech Recognition by Audio-Prefixed Low-Rank Adaptation of Language Models', 'yusuf24_interspeech', 'ssr asr speculates empower speculation transcribes ahead prefix audio feed'], ['Louis Abel, Vincent Colotte, Slim Ouni', 'Towards realtime co-speech gestures synthesis using STARGATE', 'abel24_interspeech', 'graph fast ecas autoregression field credibility resource-intensive audio-text spatio-temporal architecture'], ['Chenyu Li, Jalal Al-Tamimi', 'Impact of the tonal factor on diphthong realizations in Standard Mandarin with Generalized Additive Mixed Models', 'li24f_interspeech', 'tone falling tend realization gamms universality monophthongs vowel negatively dynamical'], ['Yehoshua Dissen, Shiry Yonash, Israel Cohen, Joseph Keshet', 'Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network', 'dissen24_interspeech', 'whisper model packet-loss criterion practicality underscoring foundational noisy realm environment'], ['Nicolas Audibert, Cecile Fougeron, Christine Meunier', 'Do Speaker-dependent Vowel Characteristics depend on Speech Style?', 'audibert24_interspeech', 'speaker intra-speaker nasal distinction style-dependent read category variability spontaneous property'], ['Riyansha Singh, Parinita Nema, Vinod K Kurmi', 'Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation', 'singh24b_interspeech', 'session base esc danger post-training analytics seamless address catastrophic forgetting'], ['Amit Roth, Arnon Turetzky, Yossi Adi', 'A Language Modeling Approach to Diacritic-Free Hebrew TTS', 'roth24_interspeech', 'diacritic modern word-piece text-to-speech tokenizer dictate in-the-wild imposes weakly pronounce'], ['Veranika Boukun, Jakob Drefs, Jörg Lücke', 'Blind Zero-Shot Audio Restoration: A V
11146ariational Autoencoder Approach for Denoising and Inpainting', 'boukun24_interspeech', 'optimization signal posterior probabilistic setting challenging truncated available grounded theoretically'], ['Austin Jones, Margaret E. L. Renwick', 'Evaluating Italian Vowel Variation with the Recurrent Neural Network Phonet', 'jones24_interspeech', 'posterior phonological lexicon close label phone correlation sociophonetic class marginally'], ['Harsha Veena Tadavarthy, Austin Jones, Margaret E. L. Renwick', 'Phonological Feature Detection for US English using the Phonet Library', 'tadavarthy24_interspeech', 'probability class distinctive posterior relationship patterned timestamps bridging designated broader'], ['Andrew Rouditchenko, Yuan Gong, Samuel Thomas, Leonid Karlinsky, Hilde Kuehne, Rogerio Feris, James Glass', 'Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation', 'rouditchenko24_interspeech', 'video avsr thousand model hour language versatile data gated harder'], ['Soham Deshmukh, Dareen Alharthi, Benjamin Elizalde, Hannes Gamper, Mahmoud Al Ismail, Rita Singh, Bhiksha Raj, Huaming Wang', 'PAM: Prompting Audio-Language Models for Audio Quality Assessment', 'deshmukh24b_interspeech', 'alm metric reference-free score listening human prompt computing ttm tta'], ['Yi-Jen Shih, David Harwath', 'Interface Design for Self-Supervised Speech Models', 'shih24_interspeech', 'ssl downstream upstream depth sum many weighted layerwise logarithmically combining'], ['Helin Wang, Jesús Villalba, Laureano Moro-Velazquez, Jiarui Hai, Thomas Thebaud, Najim Dehak', 'Noise-robust Speech Separation with Fast Generative Correction', 'wang24i_interspeech', 'diffusion reverse process corrector rectify streamline sepformer si-snr libri isolating'], ['Suhita Ghosh, Melanie Jouaiti, Arnab Das, Yamini Sinha, Tim Polzehl, Ingo Siegert, Sebastian Stober', 'Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Example', 'ghosh24_interspeech', 'domain preservation anonymity anonymisation uncommon prosody clinically disentangling pertinent differentiable'], ['Kunal Dhawan, Nithin Rao Koluguri, Ante JukiÄ, Ryan Langman, Jagadeesh Balam, Boris Ginsburg', 'Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations', 'dhawan24_interspeech', 'asr c
11146odec ml-superb encodec garnered foundational speech-text speech-related bit-rate less'], ['Vidya Srinivas, Malek Itani, Tuochao Chen, Emre Sefik Eskimez, Takuya Yoshioka, Shyamnath Gollakota', 'Knowledge boosting during low-latency inference', 'srinivas24_interspeech', 'model chunk streaming operate small running delay large larger time-delayed'], ['Kyuhong Shim, Jinkyu Lee, Hyunjae Kim', 'Leveraging Adapter for Parameter-Efficient ASR Encoder', 'shim24_interspeech', 'parameter parameter-sharing reduces reuses module adjusts conformer-based architecture insert balancing'], ['Paarth Neekhara, Shehzeen Hussain, Subhankar Ghosh, Jason Li, Boris Ginsburg', 'Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment', 'neekhara24_interspeech', 'cross-attention token text tt attention model hallucination robust repeating learnable'], ['Hongmei Guo, Yijiang Chen, Xiao-Lei Zhang, Xuelong Li', 'Graph Attention Based Multi-Channel U-Net for Speech Dereverberation With Ad-Hoc Microphone Arrays', 'guo24_interspeech', 'channel module reverberation model fusion integrated studied selection layer train'], ['Jia Qi Yip, Shengkui Zhao, Dianwen Ng, Eng Siong Chng, Bin Ma', 'Towards Audio Codec-based Speech Separation', 'yip24_interspeech', 'nac compression task sepformer mac chart cloud impractical codecs adopting'], ['Nigel G. Ward, Andres Segura, Alejandro Ceballos, Divette Marco', 'Towards a General-Purpose Model of Perceived Pragmatic Similarity', 'ward24_interspeech', 'human inter-annotator generality hubert utterance fairly thousand judge sometimes judgment'], ['Yuma Shirahata, Byeongseon Park, Ryuichi Yamamoto, Kentaro Tachibana', 'Audio-conditioned phonemic and prosodic annotation for building text-to-speech models from unlabeled speech data', 'shirahata24_interspeech', 'label-speech tt paired dataset model trained sample existing shortage text-only'], ['Jingjing Xu, Wei Zhou, Zijian Yang, Eugen Beck, Ralf Schlüter', 'Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition', 'xu24_interspeech', 'supernet subnets performant on-par full-size effort score-based resource-intensive enjoy model'], ['Zhuhai Li, Jie Zhang, Wu Guo, Haochen Wu', 'Boosting the Transferability of Adversarial Examples with Gradient-Aligned Ensemble Attack for Speaker Recognition', 'li24g_interspeech', 'substitute gradient update model victim black-box spoof randomly calculate voxceleb'], ['Run Chen, Haozhe Chen, Anushka Kulkarni, Eleanor Lin, Linda Pang, Divya Tadimeti, Jun Shin, Julia Hirschberg', 'Detecting Empathy in Speech', 'chen24f_interspeech', 'feeling acoustic-prosodic done empathetic likability trust benchmarking interpretable creating identifying'], ['Yerbolat Khassanov, Zhipeng Chen, Tianfeng Chen, Tze Yuang Chong, Wei Li, Jun Zhang, Lu Lu, Yuxuan Wang', 'Dual-Pipeline with Low-Rank Adaptation for New Language Integration in Multilingual ASR', 'khassanov24_interspeech', 'masr pipeline lora pre-trained existing flow decoder fleurs language-agnostic unavailable'], ['Kohei Matsuura, Takanori Ashihara, Takafumi Moriya, Masato Mimura, Takatomo Kano, Atsunori Ogawa, Marc Delcroix', 'Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation', 'matsuura24_interspeech', 'cascade model summary text sentence-by-sentence combine appealing asr transformer-based evaluates'], ['Zezhong Jin, Youzhi Tu, Man-Wai Mak', 'W-GVKT: Within-Global-View Knowledge Transfer for Speaker Verification', 'jin24b_interspeech', 'dino student view global teacher eer diversification non-contrastive diversified negligible'], ['Michael Lambropoulos, Frantz Clermont, Shunichi Ishihara', 'The sub-band cepstrum as a tool for locating local spectral regions of phonetic sensitivity: A first attempt with multi-speaker vowel data', 'lambropoulos24_interspeech', 'blccs sub-bands flexible cc spectrum band-limited implying full-band classification gaining'], ['Kun Zhou, Shengkui Zhao, Yukun Ma, Chong Zhang, Hao Wang, Dianwen Ng, Chongjia Ni, Trung Hieu Nguyen, Jia Qi Yip, Bin Ma', 'Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis', 'zhou24_interspeech', 'autoregressive non-autoregressive tt in-context training accumulation model scalability codecs propagation'], ['Zezhong Jin, Youzhi Tu, Man-Wai Mak', 'Self-Supervised Learning with Multi-Head Multi-Mode Knowledge Distillation for Speaker Verification', 'jin24c_interspeech', 'memo self architecture teacher contrastive head mode student dino supportive'], ['Ju-ho Kim, Hee-Soo Heo, Bong-Jin Lee, Youngki Kwon, Minjae Lee, Ha-Jin Yu', 'Self-supervised speaker verification with relational mask prediction', 'kim24c_interspeech', 'ssl-based overlooking inter-frame comprehensively mitigating encourages aggregation enrich bridge emerged'], ['Eungbeom Kim, Hantae Kim, Kyogu Lee', 'Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation', 'kim24d_interspeech', 'disagreement student alignment encoder introduces sub-model method spike model teacher-student'], ['Yao Shen, Yingying Gao, Yaqian Hao, Chenguang Hu, Fulin Zhang, Junlan Feng, Shilei Zhang', 'CEC: A Noisy Label Detection Method for Speaker Recognition', 'shen24_interspeech', 'counting inconsistent sample hard cic overfitted metric excels preventing categorize'], ['En-Lun Yu, Kuan-Hsun Ho, Jeih-weih Hung, Shih-Chieh Huang, Berlin Chen', 'Speaker Conditional Sinc-Extractor for Personal VAD', 'yu24_interspeech', 'pvad vanilla feature sinc d-vectors wearable cutoff acoustic accepting function'], ['Seyun Um, Doyeon Kim, Hong-Goo Kang', 'PARAN: Variational Autoencoder-based End-to-End Articulation-to-Speech System for Speech Intelligibility', 'um24_interspeech', 'ema latent signal adjusts distribution researched vae high-fidelity normalizing clarity'], ['Jingze Lu, Yuxiang Zhang, Zhuo Li, Zengqiang Shang, Wenchao Wang, Pengyuan Zhang', 'Improving Copy-Synthesis Anti-Spoofing Training Method with Rhythm and Speaker Perturbation', 'lu24b_interspeech', 'artifact algorithm tt introduced neglecting acoustic model facing locate vocoders'], ['Sheng Li, Chen Chen, Chin Yuen Kwok, Chenhui Chu, Eng Siong Chng, Hisashi Kawai', 'Investigating ASR Error Correction with Large Language Model and Multilingual 1-best Hypotheses', 'li24h_interspeech', 'llm n-best effectively correct llm-based low-resourced feeding noticed output let'], ['Yip Keng Kan, Ke Xu, Hao Li, Jie Shi', 'VoiceDefense: Protecting Automatic Speaker Verification Models Against Black-box Adversarial Attacks', 'kan24_interspeech', 'asv sample trustworthiness formidable counteract slice detection proving compromised distinctly'], ['HyunJung Choi, Muyeol Choi, Yohan Lim, Minkyu Lee, Seonhui Kim, Seung Yun, Donghyun Kim, SangHun Kim', 'Spoken-to-written text conversion with Large Language Model', 'choi24_interspeech', 'itn readability notation korean written making standardize pronunciation err form'], ['Jiwon Suh, Injae Na, Woohwan Jung', 'Improving Domain-Specific ASR with LLM-Generated Contextual Descriptions', 'suh24_interspeech', 'datasets terminology specific domain struggle metadata unavailable llm method whisper'], ['Rubing Shen, Yanzhen Ren, Zongkun Sun', 'FA-GAN: Artifacts-free and Phase-aware High-fidelity GAN-based Vocoder', 'shen24b_interspeech', 'artifact spectral quality non-ideal blurring twin alleviating aliasing upsampling deconvolution'], ['Sheng Feng, Heyang Liu, Yu Wang, Yanfeng Wang', 'Towards an End-to-End Framework for Invasive Brain Signal Decoding with Large Language Models', 'feng24_interspeech', 'llm groundbreaking bcis bci brain-computer immense underscoring evolve underscore showcase'], ['Yi-Wei Wang, Ke-Han Lu, Kuan-Yu Chen', 'HypR: A comprehensive study for ASR hypothesis revising with a reference corpus', 'wang24j_interspeech', 'recognition error progress research checkpoint reranking ted-lium speech dataset modeling'], ['Yuki Saito, Takuto Igarashi, Kentaro Seki, Shinnosuke Takamichi, Ryuichi Yamamoto, Kentaro Tachibana, Hiroshi Saruwatari', 'SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark', 'saito24_interspeech', 'sample low-quality smartphones multi-speaker high-quality speech speaker-wise utterance-wise any-to-any recorded'], ['Jonathan Svirsky, Uri Shaham, Ofir Lindenbaum', 'Sparse Binarization for Fast Keyword Spotting', 'svirsky24_interspeech', 'device kw edge model efficiency keyword-spotting voice-activated necessitates convenience smartphones'], ['Aviv Shamsian, Aviv Navon, Neta Glazer, Gill Hetz, Joseph Keshet', 'Keyword-Guided Adaptation of Automatic Speech Recognition', 'shamsian24_interspeech', 'whisper prompt decoder whisper-based steer transcription biasing prefix guiding significant'], ['Guillem Bonafos, Clara Bourot, Pierre Pudlo, Jean-Marc Freyermuth, Laurence Reboul, Samuel Tronçon, Arnaud Rey', 'Dirichlet process mixture model based on topologically augmented signal representation for clustering infant vocalizations', 'bonafos24_interspeech', 'month diagram vocalization life persistence persistent non-parametric categorization mfccs mel-frequency'], ['Asad Ullah, Alessandro Ragano, Andrew Hines', 'Reduce, Reuse, Recycle: Is Perturbed Data Better than Other Language Augmentation for Low Resource Self
11146-Supervised Speech Models', 'ullah24_interspeech', 'pre-training combined resource-constrained phoneme pre-train pitch target noise viable option'], ['Deok-Hyeon Cho, Hyung-Seok Oh, Seung-Bin Kim, Sang-Hoon Lee, Seong-Whan Lee', 'EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech', 'cho24_interspeech', 'ability expressive speech multi-aspect control pseudo-labels nuanced mimicking synthesizes compromising'], ['Chenyuan Zhang, Linkai Luo, Hong Peng, Wei Wen', 'Variable Segment Length and Domain-Adapted Feature Optimization for Speaker Diarization', 'zhang24b_interspeech', 'msr mixed embeddings still multiple alternation distinguishes surpasses unreliable reaching'], ['Marie KuneÅ¡ová, Jan LeheÄka, Josef Michálek, Jindrich Matousek, Jan Å vec', 'Zero-shot Out-of-domain is No Joke: Lessons Learned in the VoiceMOS 2023 MOS Prediction Challenge', 'kunesova24_interspeech', 'track ensemble win surpassed centered singing degrade wav team vec'], ['Eros Rosello, Angel M. Gomez, Iván López-Espejo, Antonio M. Peinado, Juan M. MartÃn-Doñas', 'Anti-spoofing Ensembling Model: Dynamic Weight Allocation in Ensemble Models for Improved Voice Biometrics Security', 'rosello24_interspeech', 'countermeasure showcasing still neglecting malicious adjusts susceptible spoofed neural prof'], ['Tianzi Wang, Xurong Xie, Zhaoqing Li, Shoukang Hu, Zengrui Jin, Jiajun Deng, Mingyu Cui, Shujie Hu, Mengzhe Geng, Guinan Li, Helen Meng, Xunying Liu', 'Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask', 'wang24k_interspeech', 'amd ctc nar decoder block statistically librispeech- concealed wer tripartite'], ['Yifei Xin, Xuxin Cheng, Zhihong Zhu, Xusheng Yang, Yuexian Zou', 'DiffATR: Diffusion-based Generative Modeling for Audio-Text Retrieval', 'xin24_interspeech', 'atr query candidate methodology joint discriminative clotho audiocaps loss discerning'], ['Hiroshi Sato, Takafumi Moriya, Masato Mimura, Shota Horiguchi, Tsubasa Ochiai, Takanori Ashihara, Atsushi Ando, Kentaro Shinayama, Marc Delcroix', 'SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling', 'sato24_interspeech', 'tse ssm frontend depen
11146dency convolutional encoder tasnet complexity computational enlarge'], ['Jessica Monaghan, Arun Sebastian, Nicky Chong-White, Vicky Zhang, Vijayalakshmi Easwar, Padraig Kitterick', "Automatic Detection of Hearing Loss from Children's Speech using wav2vec 2.0 Features", 'monaghan24_interspeech', 'early scalable developmental xgboost acknowledging preschool proof-of-concept non-intrusive screening toward'], ['Iuliia Zaitova, Irina Stenger, Wei Xue, Tania Avgustinova, Bernd Möbius, Dietrich Klakow', 'Cross-Linguistic Intelligibility of Non-Compositional Expressions in Spoken Context', 'zaitova24_interspeech', 'russian surprisal ukrainian distance phonological multiple-choice slavic bulgarian polish score'], ['Arnon Turetzky, Or Tal, Yael Segal, Yehoshua Dissen, Ella Zeldes, Amit Roth, Eyal Cohen, Yosi Shrem, Bronya R. Chernyak, Olga Seleznova, Joseph Keshet, Yossi Adi', 'HebDB: a Weakly Supervised Dataset for Hebrew Speech Processing', 'turetzky24_interspeech', 'language pre-processed model recording asr provide multi-lingual spoken page baseline'], ['Wei Xue, Ivan Yuen, Bernd Möbius', 'Towards a better understanding of receptive multilingualism: listening conditions and priming effects', 'xue24_interspeech', 'awr similarity affected comprehend word null less prime language-dependent without'], ['Zhiyong Yan, Heinrich Dinkel, Yongqing Wang, Jizhong Liu, Junbo Zhang, Yujun Wang, Bin Wang', 'Bridging Language Gaps in Audio-Text Retrieval', 'yan24_interspeech', 'text encoder ced clotho audiocaps excels content abundance disparity non-english'], ['Xin Wang, Tomi Kinnunen, Kong Aik Lee, Paul-Gauthier Noé, Junichi Yamagishi', 'Revisiting and Improving Scoring Fusion for Spoofing-aware Speaker Verification Using Compositional Data Analysis', 'wang24l_interspeech', 'asv score-level calibration spoofing non-linear finding score zero-effort decision summing'], ['Miseul Kim, Soo-Whan Chung, Youna Ji, Hong-Goo Kang, Min-Seok Choi', 'Speak in the Scene: Diffusion-based Acoustic Scene Transfer toward Immersive Speech Generation', 'kim24e_interspeech', 'ast environment target clap signal task diffusion audio emphasize accompanied'], ['Haiyang Sun, Fulin Zhang, Yingying Gao, Shilei Zhang, Zheng Lian, Junlan Feng', 'MFSN: Multi-perspective Fusion Search Network For Pre-training Knowledge in Speech Emotion Recognition', 'sun24b_interspeech', 'comprehensiveness emotional appropriateness sec ser capturing overlooking content cue verifies'], ['Hyun Kyung Hwang, Manami Hirayama', 'Acquisition of high vowel devoicing in Japanese: A production experiment with three and four year olds', 'hwang24b_interspeech', 'hvd developmental word-medial position advancement old rate pattern distinct age'], ['Rotem Rousso, Eyal Cohen, Joseph Keshet, Eleanor Chodroff', 'Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment', 'rousso24_interspeech', 'whisperx mm mfa gmm-hmm speech dominantly kaldi-based montreal massively buckeye'], ['Young Jin Ahn, Jungwoo Park, Sangha Park, Jonghyun Choi, Kee-Eung Kim', 'SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization', 'ahn24_interspeech', 'vsr synchronizes fell versatility intersection visemes non-autoregressive sought stand aligning'], ['Fengrun Zhang, Wangjin Zhou, Yiming Liu, Wang Geng, Yahui Shan, Chen Zhang', 'Disentangling Age and Identity with a Mutual Information Minimization for Cross-Age Speaker Verification', 'zhang24c_interspeech', 'embeddings backbone gap vox-ca identity-related disentangled age-related aging disentangle method'], ['Naoki Makishima, Naotaka Kawata, Mana Ihori, Tomohiro Tanaka, Shota Orihashi, Atsushi Ando, Ryo Masumura', 'SOMSRED: Sequential Output Modeling for Joint Multi-talker Overlapped Speech Recognition and Speaker Diarization', 'makishima24_interspeech', 'identifier asr unknown jointly fully separate timestamps clustering-based recursively sub-optimal'], ['Xihang Qiu, Lixian Zhu, Zikai Song, Zeyu Chen, Haojie Zhang, Kun Qian, Ye Zhang, Bin Hu, Yoshiharu Yamamoto, Björn W. Schuller', 'Study Selectively: An Adaptive Knowledge Distillation based on a Voting Network for Heart Sound Classification', 'qiu24_interspeech', 'excellent teacher student impart complexity sizeable computational strategy tell nowadays'], ['Takafumi Moriya, Takanori Ashihara, Masato Mimura, Hiroshi Sato, Kohei Matsuura, Ryo Masumura, Taichi Asami', 'Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding', 'moriya24_interspeech', 'hat iam non-blank decoding transducer joint emit synchronously speed-up skip'], ['I-Ting Hsieh,
11146Chung-Hsien Wu', 'Dysarthric Speech Recognition Using Curriculum Learning and Articulatory Feature Embedding', 'hsieh24_interspeech', 'characteristic recognizing disorder diverse incorporate patient speaker commonly efficiency additionally'], ['Matthijs Van keirsbilck, Alexander Keller', 'Conformer without Convolutions', 'vankeirsbilck24_interspeech', 'learnable temporal surprising speech-to-text averaging discover replace completely remove shift'], ['Yi-Cheng Lin, Tzu-Quan Lin, Hsi-Che Lin, Andy T. Liu, Hung-yi Lee', 'On the social bias of speech self-supervised models', 'lin24b_interspeech', 'ssl biased debiasing inadvertently marginalized reinforcing amplify disparate training shallower'], ['Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, He Huang, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee', 'DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment', 'lu24c_interspeech', 'slms instruction-following capability reshape generalizing captioning non-linguistic caption zero-shot facilitating'], ['Ching-Yu Yang, Shreya G. Upadhyay, Ya-Tse Wu, Bo-Hao Su, Chi-Chun Lee', 'RW-VoiceShield: Raw Waveform-based Adversarial Attack on One-shot Voice Conversion', 'yang24e_interspeech', 'protected speaker utterance attacking imperceptible white-box recognizable generated undergoes disparity'], ['Xinwei Cao, Zijian Fan, Torbjørn Svendsen, Giampiero Salvi', 'A Framework for Phoneme-Level Pronunciation Assessment Using CTC', 'cao24b_interspeech', 'gop alignment method prone traditional deletion insertion error child alignment-based'], ['Woan-Shiuan Chien, Chi-Chun Lee', 'An Investigation of Group versus Individual Fairness in Perceptually Fair Speech Emotion Recognition', 'chien24_interspeech', 'ser raters gender label standpoint diminished persist issue biased arising'], ['Martin Lenglet, Olivier Perrotin, Gerard Bailly', 'FastLips: an End-to-End Audiovisual Text-to-Speech System with Lip Features Prediction for Virtual Avatars', 'lenglet24_interspeech', 'fastspeech avatar facial explicit co-verbal encoder model movement generation visual'], ['Yin-Tse Lin, Shreya G. Upadhyay, Bo-Hao Su, Chi-Chun Lee', 'SWiBE: A Parameterized Stochastic Diffusion Process for Noise-Robust Bandwidth Expansion', 'lin24c_interspeech', 'score-based bwe parameterizations stepwise gan-based hyperparameters current including manifest encounter'], ['Joun Yeop Lee, Myeonghun Jeong, Minchan Kim, Ji-Hyun Lee, Hoon-Young Cho, Nam Soo Kim', 'High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model', 'lee24f_interspeech', 'interpreting semantic speech speaking stage module enriching conformer-based high-fidelity text'], ['Shreya G. Upadhyay, Carlos Busso, Chi-Chun Lee', 'A Layer-Anchoring Strategy for Enhancing Cross-Lingual Speech Emotion Recognition', 'upadhyay24_interspeech', 'ser layer pretrained transformer hierarchical uncovers encapsulates msp-podcast podcast model'], ['Wei-Tung Hsu, Chin-Po Chen, Yun-Shao Lin, Chi-Chun Lee', 'A Cluster-based Personalized Federated Learning Strategy for End-to-End ASR of Dementia Patients', 'hsu24_interspeech', 'heterogeneity usage pause asr-related wer privacy-preserving adress distribution alzheimer challenge'], ['Hsing-Hang Chou, Woan-Shiuan Chien, Ya-Tse Wu, Chi-Chun Lee', 'An Inter-Speaker Fairness-Aware Speech Emotion Regression Framework', 'chou24_interspeech', 'ser fairness id fair knowing speaker cluster upfront speaker-level individual'], ['Jan LeheÄka, Josef V. Psutka, Lubos Smidl, Pavel Ircing, Josef Psutka', 'A Comparative Analysis of Bilingual and Trilingual Wav2Vec Models for Automatic Speech Recognition in Multilingual Oral History Archives', 'lehecka24_interspeech', 'mixed-language archive monolingual unique public commonvoice heritage releasing dataset push'], ['Dirk Eike Hoffner, Jana RoÃbach, Bernd T. Meyer', 'Joint prediction of subjective listening effort and speech intelligibility based on end-to-end learning', 'hoffner24_interspeech', 'non-intrusive character root-mean-square entropy-based model intrusive hearing-impaired normal-hearing quantified real-life'], ['Yaroslav Getman, Tamas Grosz, Mikko Kurimo', 'What happens in continued pre-training? Analysis of self
11146-supervised speech models with continued pre-training for colloquial Finnish ASR', 'getman24_interspeech', 'multilingual specialize less-resourced high-resourced codeword language discovered quantized foundation purely'], ['Fredrik Cumlin, Xinyu Liang, Victor Ungureanu, Chandan K. A. Reddy, Christian Schüldt, Saikat Chatterjee', 'DNSMOS Pro: A Reduced-Size DNN for Probabilistic MOS of Speech', 'cumlin24_interspeech', 'non-intrusive subjectively datasets rated quality method training design voip architecture'], ['Yaroslav Getman, Tamas Grosz, Katri Hiovain-Asikainen, Mikko Kurimo', 'Exploring adaptation techniques of large speech foundation models for low-resource ASR: a case study on Northern Sámi', 'getman24b_interspeech', 'fine-tuning pre-training already extended include augments low-resourced new preparing continued'], ['Hoan My Tran, David Guennec, Philippe Martin, Aghilas Sini, Damien Lolive, Arnaud Delhay, Pierre-François Marteau', 'Spoofed Speech Detection with a Focus on Speaker Embedding', 'tran24_interspeech', 'deepfakes contrastive excel loss layer-wise deepfake finetuned spoof attentive wavlm'], ['Ya-Tse Wu, Jingyao Wu, Vidhyasaharan Sethu, Chi-Chun Lee', 'Can Modelling Inter-Rater Ambiguity Lead To Noise-Robust Continuous Emotion Predictions?', 'wu24d_interspeech', 'noise cer insufficiently ccc recola robustness concordance regularize broadly arousal'], ['Yuanyuan Zhang, Zhengjun Yue, Tanvina Patel, Odette Scharenborg', 'Improving child speech recognition with augmented child-like speech', 'zhang24d_interspeech', 'child-to-child cross-lingual augmentation model absolute asrs two-fold asr csr suboptimal'], ['Victor Miara, Theo Lepage, Reda Dehak', 'Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models', 'miara24_interspeech', 'ssl pseudo-labels fine-tuning eer narrowing wavlm representation establishing iteratively refined'], ['Guanrou Yang, Ziyang Ma, Fan Yu, Zhifu Gao, Shiliang Zhang, Xie Chen', 'MaLa-ASR: Multimedia-Assisted LLM-Based ASR', 'yang24f_interspeech', 'llm auxiliary audio integrate sparked keywords ingest information-rich surge fresh'], ['Cécile Macaire, Chloé Dion, Didier Schwab, Benjamin Lecouteux, Emmanuelle Esperança-Rodier', 'Towards Speech-to-Pictograms Translation', 'macaire24_interspeech', 'cascade end-to-end tailor speech state-of-the-art in-depth nlp specially everyday released'], ['June-Woo Kim, Miika Toikkanen, Yera Choi, Seoung-Eun Moon, Ho-Young Jung', 'BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification', 'kim24f_interspeech', 'rsc metadata text-audio patient recording multimodal icbhi sample surpassing validates'], ['Alexander Kathan, Martin Bürger, Andreas Triantafyllopoulos, Sabrina Milkus, Jonas Hohmann, Pauline Muderlak, Jürgen Schottdorf, Richard Musil, Björn Schuller, Shahin Amiriparian', 'Real-world PTSD Recognition: A Cross-corpus and Cross-linguistic Evaluation', 'kathan24_interspeech', 'mental analyse early disaster post-traumatic abuse wellbeing sexual cross-cultural combat'], ['Pu Wang, Junhui Li, Jialu Li, Liangdong Guo, Youshan Zhang', 'Diffusion Gaussian Mixture Audio Denoise', 'wang24m_interspeech', 'model reverse noise distribution signal clean comply subtracted noisy estimate'], ['Thomas Graave, Zhengyang Li, Timo Lohrenz, Tim Fingscheidt', 'Mixed Children/Adult/Childrenized Fine-Tuning for Childrenâs ASR: How to Reduce Age Mismatch and Speaking Style Mismatch', 'graave24_interspeech', 'speech read partially matched pre-trained child absolute datasets individual deteriorate'], ['Shucong Zhang, Titouan Parcollet, Rogier van Dalen, Sourav Bhattacharya', 'Linear-Complexity Self-Supervised Learning for Speech Processing', 'zhang24e_interspeech', 'mhsa pre-training ssl gpus week wav vec encoder model multi-headed'], ['Fan Huang, Kun Zeng, Wei Zhu', 'DiffVC+: Improving Diffusion-based Voice Conversion for Speaker Anonymization', 'huang24_interspeech', 'privacy converted speech encoder embedding server-side content suppresses decoupled leakage'], ['Zhengyang Li, Patrick Blumenberg, Jing Liu, Thomas Graave, Timo Lohrenz, Siegfried Kunzmann, Tim Fingscheidt', 'Interleaved Audio/Audiovisual Transfer Learning for AV-ASR in Low-Resourced Languages', 'li24i_interspeech', '-stage target stage language german excels cross-modality catastrophic forgetting english'], ['Arnav Kundu, Prateeth Nayak, Priyanka Padmanabhan, Devang Naik', 'RepCNN: Micro-sized, Mighty Models for Wakeword Detection', 'kundu24_interspeech', 'always-on runtime memory footprint compute inference convolutional model re-parameterized parameter'], ['Théodor Lemerle, Nicolas Obin, Axel Roebel', 'Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis', 'lemerle24_interspeech', 'transformer cloning zero-shot architecture showcased decoder-only powered impeding tt skipping'], ['Ji-Hun Kang, Jae-Hong Lee, Mun-Hak Lee, Joon-Hyuk Chang', 'Whisper Multilingual Downstream Task Tuning Using Task Vectors', 'kang24_interspeech', 'model vector direction weight orient summing simple space arithmetic effective'], ['Luis Felipe Parra-Gallego, Tilak Purohit, Bogdan Vlasenko, Juan Rafael Orozco-Arroyave, Mathew Magimai.-Doss', 'Cross-transfer Knowledge between Speech and Text Encoders to Evaluate Customer Satisfaction', 'parragallego24_interspeech', 'bert reputation distilling enriching cost-effective asr wavlm learning company whisper'], ['Honglie Chen, Rodrigo Mira, Stavros Petridis, Maja Pantic', 'RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement', 'chen24g_interspeech', 'frame causal latency stream emformer devising non-causal state-of-the-art audio frame-by-frame'], ['Mara Barberis, Pieter De Clercq, Bastiaan Tamm, Hugo Van hamme, Maaike Vandermosten', 'Automatic recognition and detection of aphasic natural speech', 'barberis24_interspeech', 'aphasia asr svm feature detect stroke semi-automatically administered semi-automatic consuming'], ['Moreno La Quatra, Maria Francesca Turco, Torbjørn Svendsen, Giampiero Salvi, Juan Rafael Orozco-Arroyave, Sabato Marco Siniscalchi', "Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions", 'laquatra24_interspeech', 'pc-gita base performance devising foundational assess off-the-shelf wavlm hubert fine-tune'], ['Cong Zhang, Tong Li, Gayle DeDe, Christos Salis', 'Prosody of speech production in latent post-stroke aphasia', 'zhang24f_interspeech', 'neurotypical mild forest prosodic random left-hemisphere utterance-initial reinfor
11146ced stroke control'], ['Lorenzo Maselli, Véronique Delvaux', 'Aerodynamics of Sakata labial-velar oral stops', 'maselli24_interspeech', 'bilabial airflow plain pressure congo delineated variable université southwestern mon'], ['Jongsuk Kim, Jiwon Shin, Junmo Kim', 'AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning', 'kim24g_interspeech', 'advancement extensibility human-level pivotal scalability exploration com github model applicable'], ['Hassan Taherian, Vahid Ahmadi Kalkhorani, Ashutosh Pandey, Daniel Wong, Buye Xu, DeLiang Wang', 'Towards Explainable Monaural Speaker Separation with Auditory-based Training', 'taherian24_interspeech', 'pit permutation onset criterion cue ambiguity pitch hybrid talker-independent same-gender'], ['Anith Selvakumar, Homa Fashandi', 'Getting More for Less: Using Weak Labels and AV-Mixup for Robust Audio-Visual Speaker Verification', 'selvakumar24_interspeech', 'dml voxceleb multimodal overfit space multitask reporting owing dominated learning'], ['Avihu Dekel, Raul Fernandez', 'Exploring the Benefits of Tokenization of Discrete Acoustic Units', 'dekel24_interspeech', 'variable-rate vocabulary audio-based overlooked showcase task merge playing grapheme-to-phoneme explanation'], ['Junzuo Zhou, Jiangyan Yi, Tao Wang, Jianhua Tao, Ye Bai, Chu Yuan Zhang, Yong Ren, Zhengqi Wen', 'TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking', 'zhou24b_interspeech', 'watermark imperceptibility speech attack flexibility quality watermarked vall-e tt resilience'], ['Georgios Chochlakis, Chandrashekhar Lavania, Prashant Mathur, Kyu J. Han', 'Tackling Missing Modalities in Audio-Visual Representation Learning Using Masked Autoencoders', 'chochlakis24_interspeech', 'imputed pristine robust curriculum make lombard retraining trained autoencoder necessarily'], ['Lun Wang, Om Thakkar, Zhong Meng, Nicole Rafidi, Rohit Prabhavalkar, Arun Narayanan', 'Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping', 'wang24n_interspeech', 'pcc gradient memorization unintended mitigate apcc minibatch streamlined multifaceted training'], ['Zilong Huang, Man-Wai Mak, Kong Aik Lee', 'MM-NodeFormer: Node Transformer Multimodal Fusion for Emotion Recognition in Conversation', 'huang24b_interspeech', 'modality erc richness emotional auxiliary text consultation visual meld main'], ['Ji Sub Um, Hoirin Kim', 'Utilizing Adaptive Global Response Normalization and Cluster-Based Pseudo Labels for Zero-Shot Voice Conversion', 'um24b_interspeech', 'content information conduct speaker convnext layer dynamic transmit conveying transmitted'], ['Jialu Li, Mark Hasegawa-Johnson, Karrie Karahalios', 'Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis', 'li24j_interspeech', 'clinician old auxiliary behavior build year reproducible labor helping audio'], ['Alexander Johnson, Peter Plantinga, Pheobe Sun, Swaroop Gadiyaram, Abenezer Girma, Ahmad Emami', 'Efficient SQA from Long Audio Contexts: A Policy-driven Approach', 'johnson24_interspeech', 'file compute safely skipping infeasible podcasts recording skip retrieving less'], ['Li-Fang Lai, Nicole Holliday', 'Voice Quality Variation in AAE: An Additional Challenge for Addressing Bias in ASR Models?', 'lai24_interspeech', 'creaky mae creak american men woman young phonation creakier non-modal'], ['Shiran Aziz, Yossi Adi, Shmuel Peleg', 'Audio Enhancement from Multiple Crowdsourced Recordings: A Simple and Effective Baseline', 'aziz24_interspeech', 'event local noise location device signal cleaned uncorrelated cellular unrelated'], ['Wen Wu, Chao Zhang, Philip C. Woodland', 'Confidence Estimation for Automatic Detection of Depression and Alzheimerâs Disease Based on Clinical Interviews', 'wu24e_interspeech', 'daic-woz informs adress distribution second-order dirichlet clinician attracted speech-based risk'], ['Vikentii Pankov, Valeria Pronina, Alexander Kuzmin, Maksim Borisov, Nikita Usoltsev, Xingshan Zeng, Alexander Golubkov, Nikolai Ermolenko, Aleksandra Shirshova, Yulia Matveeva', 'DINO-VITS: Data-Efficient Zero-Shot TTS with Self-Supervised Speaker Verification Loss for Noise Robustness', 'pankov24_interspeech', 'dino noisy training encoder clean noise-robustness speech objective cloning discriminability'], ['Jie Chi, Electra Wallington, Peter Bell', 'Characterizing code-switching: Applying Linguistic Principles for Metric Assessment and Development', 'chi24_interspeech', 'leverage data-sets hindi-english capture mandarin-english code-switched assess ric
11146hness intuition participating'], ['Sean Robertson, Gerald Penn, Ewan Dunbar', 'Quantifying the Role of Textual Predictability in Automatic Speech Recognition', 'robertson24_interspeech', 'model asr straightforwardly ability long-standing diagnosing use higher-order spite context'], ['Shiyi Han, Mingbin Xu, Zhihong Lei, Zhen Huang, Xingyu Na', 'Enhancing CTC-based speech recognition with diverse modeling units', 'han24_interspeech', 'model synergistic grapheme-based asr phoneme-based heterogeneous driving evolution align accuracy'], ['Zhiqi Huang, Diamantino Caseiro, Kandarp Joshi, Christopher Li, Pat Rondon, Zelin Wu, Petr Zadrazil, Lillian Zhou', 'Optimizing Large-Scale Context Retrieval for End-to-End ASR', 'huang24c_interspeech', 'entity scalable comparative recall scoring contextual accurate outstanding segment-level method'], ['Yiling Huang, Weiran Wang, Guanlong Zhao, Hank Liao, Wei Xia, Quan Wang', 'On the Success and Limitations of Auxiliary Network Based Word-Level End-to-End Neural Speaker Diarization', 'huang24d_interspeech', 'quot spoke asr turn-based capability modularized logits eend blank -speaker'], ['Chung-Ming Chien, Andros Tjandra, Apoorv Vyas, Matt Le, Bowen Shi, Wei-Ning Hsu', 'Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning', 'chien24b_interspeech', 'voicebox adapter pre-trained module lora grow reuse across compromising follow-up'], ['Ankit Gupta, George Saon, Brian Kingsbury', 'Exploring the limits of decoder-only models trained on public speech recognition corpora', 'gupta24_interspeech', 'whisper asr transformer competitive open hour owsm permissive large-v checkpoint'], ['Woo Hyun Kang, Srikanth Vishnubhotla, Rudolf Braun, Yogesh Virkar, Raghuveer Peri, Kyu J. Han', 'SWAN: SubWord Alignment Network for HMM-free word timing estimation in end-to-end automatic speech recognition', 'kang24b_interspeech', 'wte hmm asr multilingual method label fleurs inability accumulated due'], ['Frank Seide, Yangyang Shi, Morrie Doulaty, Yashesh Gaur, Junteng Jia, Chunyang Wu', 'Speech ReaLLM â Real-time Speech Recognition with Multimodal Language Models by Teaching the Flow of Time', 'seide24_interspeech', 'llm decoder-only architecture rnn-t asr end-pointing empty real reasonably without'], ['Tuan Vu Ho, Kota Dohi, Yohei Kawaguchi', 'Stream-based Active Learning for Anomalous Sound Detection in Machine Condition Monitoring', 'ho24_interspeech', 'asd sample budget unexplored dcase updating framework receiver backend retraining'], ['Virat Shejwalkar, Om Thakkar, Arun Narayanan', 'Quantifying Unintended Memorization in BEST-RQ ASR Encoders', 'shejwalkar24_interspeech', 'auditing downstream real-world unintentionally memorize sample clipping impacting conformer-based mitigating'], ['Ke Chen, Jiaqi Su, Taylor Berg-Kirkpatrick, Shlomo Dubnov, Zeyu Jin', 'Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation', 'chen24h_interspeech', 'pipeline training diverse content acoustic separator pit objective across environment'], ['Tien-Ju Yang, Andrew Rosenberg, Bhuvana Ramabhadran', 'Contemplative Mechanism for Speech Recognition: Speech Encoders can Think', 'yang24g_interspeech', 'quot token size encoder strategically interleaving doubling model inserting encourages'], ['Pan-Pan Jiang, Jimmy Tobin, Katrin Tomanek, Robert MacDonald, Katie Seaver, Richard Cave, Marilyn Ladewig, Rus Heywood, Jordan Green', 'Learnings from curating a trustworthy, well-annotated, and useful dataset of disordered English speech', 'jiang24_interspeech', 'metadata project correction transcript annotation inter-rater report machine-learning gathering rationale'], ['Ante JukiÄ, Roman Korostik, Jagadeesh Balam, Boris Ginsburg', 'Schrödinger Bridge for Generative Speech Enhancement', 'jukic24_interspeech', 'model dereverberation denoising clean loss complex-valued diffusion-based distribution tractable baseline'], ['Naijun Zheng, Xucheng Wan, Kai Liu, Ziqing Du, Zhou Huan', 'An efficient text augmentation approach for contextualized Mandarin speech recognition', 'zheng24_interspeech', 'contextualize speech-text text-only asr codebook embeddings pre-trained uncommon top-performing hindered'], ['Jiafeng Zhong, Bin Li, Jiangyan Yi', 'Enhancing Parti
11146ally Spoofed Audio Localization with Boundary-aware Attention Mechanism', 'zhong24_interspeech', 'boundary bam authenticity frame partialspoof intra-frame inter-frame fake unexplored frame-wise'], ['Zejiang Hou, Goeric Huybrechts, Anshu Bhatia, Daniel Garcia-Romero, Kyu J. Han, Katrin Kirchhoff', 'Revisiting Convolution-free Transformer for Speech Recognition', 'hou24_interspeech', 'conformer convolution wer architecture training scale state-ofthe-art module catch inductive'], ['Houjian Guo, Chaoran Liu, Carlos Toshinori Ishi, Hiroshi Ishiguro', 'X-E-Speech: Joint Training Framework of Non-Autoregressive Cross-lingual Emotional Text-to-Speech and Voice Conversion', 'guo24b_interspeech', 'tt speech model style-related content-related freeze similarity content nar synthesis'], ['Haici Yang, Jiaqi Su, Minje Kim, Zeyu Jin', 'Genhancer: High-Fidelity Speech Enhancement via Generative Modeling on Discrete Codec Tokens', 'yang24h_interspeech', 'conditioning best-fit speaker-identity content retention enforce conventional audio domain supplement'], ['Yanxiong Li, Jiaxin Tan, Guoqing Chen, Jialong Li, Yongjie Si, Qianhua He', 'Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Network', 'li24k_interspeech', 'dcase challenge contextual global local exceeds distillation method clip pre-processing'], ['Yifei Xin, Zhihong Zhu, Xuxin Cheng, Xusheng Yang, Yuexian Zou', 'Audio-text Retrieval with Transformer-based Hierarchical Alignment and Disentangled Cross-modal Representation', 'xin24b_interspeech', 'atr dcr tha latent factor transformer audio finegrained semantic single-level'], ['Huai-Zhe Yang, Chia-Ping Chen, Shan-Yun He, Cheng-Ruei Li', 'Bilingual and Code-switching TTS Enhanced with Denoising Diffusion Model and GAN', 'yang24i_interspeech', 'adversarial consistency mo speaker employ classifier speech mandarin-english push featuring'], ['Shiu-Hsiang Liou, Po-Cheng Chan, Chia-Ping Chen, Tzu-Chieh Lin, Chung-Li Lu, Yu-Han Cheng, Hsiang-Feng Chuang, Wei-Yu Chen', 'Enhancing ECAPA-TDNN with Feature Processing Module and Attention Mechanism for Speaker Verification', 'liou24_interspeech', 'kernel temporal front-end weight ecapa capture flop assigns expands mindcf'], ['HengYu Li, Kangdi Mei, Zhaoci Liu, Yang Ai, Liping Chen, Jie Zhang, Zhenhua Ling', 'Refining Self-supervised Learnt Speech Representation using Brain Activations', 'li24l_interspeech', 'similarity model downstream pre-trained often-used superb fmri human aligning refine'], ['Tianteng Gu, Bei Liu, Hang Shao, Yanmin Qian', 'SparseWAV: Fast and Accurate One-Shot Unstructured Pruning for Large Speech Foundation Models', 'gu24_interspeech', 'parameter remove compression pre-trained unimportant eliminated sacrificing negligible performance consumption'], ['Changhwan Kim', 'ClariTTS: Feature-ratio Normalization and Duration Stabilization for Code-mixed Multi-speaker Speech Synthesis', 'kim24h_interspeech', 'tt accent language speaker synthesized disentangles flow-based speaker-related linguistic affine'], ['Junhui Li, Pu Wang, Jialu Li, Youshan Zhang', 'Complex Image-Generative Diffusion Transformer for Audio Denoising', 'li24m_interspeech', 'attention image field generation deep model expands leaving receptive scalability'], ['Aijun Li, Jun Gao, Zhiwei Wang', 'Effect of Complex Boundary Tones on Tone Identification: An Experimental Study with Mandarin-speaking Preschool Children', 'li24n_interspeech', 'suabt preschooler word age tonal forty-eight decoding stabilizes impede child-directed'], ['Nameer Hirschkind, Xiao Yu, Mahesh Kumar Nandwana, Joseph Liu, Eloi DuBois, Dao Le, Nicolas Thiebaut, Colin Sinclair, Kyle Spence, Charles Shang, Zoe Abrams, Morgan McGuire', 'Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation', 'hirschkind24_interspeech', 'diffusion-based tacotron-based low-latency translating zero-shot double speech-to-speech bleu count pesq'], ['Yu Nakagome, Michael Hentschel', 'InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictions', 'nakagome24_interspeech', 'label ctc subsequent unknown self-conditioned parameter-free keywords layer pair substituting'], ['Haixin Guan, Wei Dai, Guangyong Wang, Xiaobin Tan, Peng Li, Jiaen Liang', 'Reducing Speech Distortion and Artifacts for Speech Enhancement by Loss Function', 'guan24_interspeech', 'combined governing diminish stride persist dns lightweight learning-based continuity formation'], ['Tzu-Quan
11146Lin, Hung-yi Lee, Hao Tang', 'DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Models', 'lin24d_interspeech', 'fine-tuning inference adaptivity layer need round decides hubert eliminating adjusting'], ['Guanlin Chen, Yun Jin', "Cascaded Transfer Learning Strategy for Cross-Domain Alzheimer's Disease Recognition through Spontaneous Speech", 'chen24i_interspeech', 'subspace second-level first-level corpus gpt- multi-source respectively experiment forest align'], ['Keiko Ochi, Koji Inoue, Divesh Lala, Tatsuya Kawahara', 'Entrainment Analysis and Prosody Prediction of Subsequent Interlocutorâs Backchannels in Dialogue', 'ochi24_interspeech', 'preceding utterance prosodic feature power regression interrelationship empathy svr attentive'], ['Shubham Gupta, Mirco Ravanelli, Pascal Germain, Cem Subakan', 'Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice', 'gupta24b_interspeech', 'explanation discretization faithful understandable associating fastspeech standard tacotron algorithm experimentally'], ['Atsushi Ando, Takafumi Moriya, Shota Horiguchi, Ryo Masumura', 'Factor-Conditioned Speaking-Style Captioning', 'ando24_interspeech', 'caption generates gts factor ensure diverse deterministically original learning guarantee'], ['Zhe Liu, Suyoun Kim, Ozlem Kalinli', 'Evaluating Speech Recognition Performance Towards Large Language Model Based Voice Assistants', 'liu24c_interspeech', 'llm asr semantic metric curated popularity failure cascaded raised judgement'], ['Francesco Paissan, Luca Della Libera, Zhepei Wang, Paris Smaragdis, Mirco Ravanelli, Cem Subakan', 'Audio Editing with Non-Rigid Text Prompts', 'paissan24b_interspeech', 'edits diffusion pipeline latent inpainting faithfulness lora user qualitatively fidelity'], ['Shilin Wang, Haixin Guan, Yanhua Long', 'QMixCAT: Unsupervised Speech Enhancement Using Quality-guided Signal Mixing and Competitive Alternating Model Training', 'wang24o_interspeech', 'teacher-student supervised mixture cat epoch learning-based framework iteratively trained innovative'], ['Shuai Wang, Dehao Zhang, Kexin Shi, Yuchen Wang, Wenjie Wei, Jibin Wu, Malu Zhang', 'Global-Local Convolution with Spiking Neural Networks for Energy-efficient Keyword Spotting', 'wang24p_interspeech', 'kw module fewer efficiency energy extraction sparser hand-crafted lightweight performance'], ['Yuexuan Kong, Viet-Anh Tran, Romain Hennequin', 'STraDa: A Singer Traits Dataset', 'kong24_interspeech', 'metadata downloadable track lead thousand file bias ssc twenty-five benchmarked'], ['Junseok Ahn, Youkyum Kim, Yeunju Choi, Doyeop Kwak, Ji-Hoon Kim, Seongkyu Mun, Joon Son Chung', 'VoxSim: A perceptual voice similarity dataset', 'ahn24b_interspeech', 'speaker prediction vcc utilised benchmarking automate unexplored score leaving out-of-domain'], ['Jialong Mai, Xiaofen Xing, Weidong Chen, Xiangmin Xu', 'DropFormer: A Dynamic Noise-Dropping Transformer for Speech Emotion Recognition', 'mai24_interspeech', 'dropping emotional local information ser token non-emotional overlook meld overly'], ['Peng Wang, Yifan Yang, Zheng Liang, Tian Tan, Shiliang Zhang, Xie Chen', 'Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer', 'wang24q_interspeech', 'fnt ner biasing hurting decoupling triggering excessive lm attention-based risk'], ['Duc-Tuan Truong, Ruijie Tao, Tuan Nguyen, Hieu-Thi Luong, Kong Aik Lee, Eng Siong Chng', 'Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection', 'truong24b_interspeech', 'mhsa temporal transformer dependency channel module neglect ablation input artifact'], ['Fei Zhao, Chenggang Zhang, Shulin He, Jinjiang Liu, Xueliang Zhang', 'Deep Echo Path Modeling for Acoustic Echo Cancellation', 'zhao24_interspeech', 'aec near-end scenario learning unseen single-talk complex full-duplex double-talk generalizing'], ['Jen-Hung Huang, Wei-Tsung Lee, Chung-Hsien Wu', 'USD-AC: Unsupervised Speech Disentanglement for Accent Conversion', 'huang24e_interspeech', 'content generalization disentangles exceptional linguistic adaptability grounded generalizability boosting learning'], ['Yuqin Lin, Longbiao Wang, Jianwu Dang, Nobuaki Minematsu', 'Exploring Pre-trained Speech Model for Articulatory Feature Extraction in Dysarthric Speech Using ASR', 'lin24e_interspeech', 'ph
11146onemic dysarthria pretrained attribute extract torgo detection uaspeech information dysphonia'], ['Yiying Hu, Hui Feng', 'Key Acoustic Cues for the Realization of Metrical Prominence in Tone Languages: A Cross-Dialect Study', 'hu24_interspeech', 'right-dominant pitch cumulative analysis dialect intensity identify metrically dynamic across'], ['Marc Härkönen, Samuel J. Broughton, Lahiru Samarakoon', 'EEND-M2F: Masked-attention mask transformers for speaker diarization', 'harkonen24_interspeech', 'end-to-end dihard-iii segmentation alimeeting winning truly stack eliminating irrelevant der'], ['Dongheon Lee, Jung-Woo Choi', 'DeFTAN-AA: Array Geometry Agnostic Multichannel Speech Enhancement', 'lee24g_interspeech', 'spatial cross-attention microphone block channel-wise foreground alleviates dense gated various'], ['Neil Shah, Shirish Karande, Vineet Gandhi', 'Towards Improving NAM-to-Speech Synthesis Intelligibility using Self-Supervised Speech Models', 'shah24_interspeech', 'nam self-supervision seq ground-truth methodology non-audible mcd murmur cstr gauge'], ['Pin-Yen Liu, Jen-Tzung Chien', 'Modality Translation Learning for Joint Speech-Text Model', 'liu24d_interspeech', 'speech shared text emotional cross-modality harness space unexplored struggle hardly'], ['Semin Kim, Myeonghun Jeong, Hyeonseung Lee, Minchan Kim, Byoung Jin Choi, Nam Soo Kim', 'MakeSinger: A Semi-Supervised Training Method for Data-Efficient Singing Voice Synthesis via Classifier-free Diffusion Guidance', 'kim24i_interspeech', 'svs data pitch tt semisupervised diffusion-based gathering guiding text dual'], ['Hanyu Meng, Qiquan Zhang, Xiangyu Zhang, Vidhyasaharan Sethu, Eliathamby Ambikairajah', 'Binaural Selective Attention Model for Target Speaker Extraction', 'meng24b_interspeech', 'time-domain configuration fasnet filter-and-sum si-sdr inter-channel separator two-speaker anechoic cocktail'], ['Liuxian Ma, Lin Shen, Ruobing Li, Haojie Zhang, Kun Qian, Bin Hu, Björn W. Schuller, Yoshiharu Yamamoto', 'E-ODN: An Emotion Open Deep Network for Generalised and Adaptive Speech Emotion Recognition', 'ma24_interspeech', 'emotional type infer ser model widest finer-grained uneven range unbalanced'], ['Hongyang Chen, Yuhong Yang, Zhongyuan Wang, Weiping Tu, Haojun Ai, Cedar Lin', 'Exploring Sentence Type Effects on the Lombard Effect and Intelligibility Enhancement: A Comparative Study of Natural and Grid Sentences', 'chen24j_interspeech', 'lct pronounced superior normal-to-lombard corpus valuable enhancing maintaining perspective focusing'], ['Masaya Kawamura, Ryuichi Yamamoto, Yuma Shirahata, Takuya Hasumi, Kentaro Tachibana', 'LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning', 'kawamura24_interspeech', 'libritts-r annotation prompt prompt-based tt speaker-level model dataset controllable conventional'], ['Yujie Chen, Jiangyan Yi, Jun Xue, Chenglong Wang, Xiaohui Zhang, Shunbo Dong, Siding Zeng, Jianhua Tao, Zhao Lv, Cunhang Fan', 'RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection', 'chen24k_interspeech', 'long-range fake mamba bonafide capture short information short-range sinc combining'], ['Xujiang Xing, Mingxing Xu, Thomas Fang Zheng', 'A Joint Noise Disentanglement and Adversarial Training Framework for Robust Speaker Verification', 'xing24_interspeech', 'noise-independent encoder embedding condition discourage supervise module speaker-invariant noisy space'], ['Chaeyoung Jung, Suyeon Lee, Ji-Hoon Kim, Joon Son Chung', 'FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching', 'jung24b_interspeech', 'diffusion-based inference speed quality github reduces u-net output learnable degrading'], ['Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo, Siddhant Arora, Shinji Watanabe', 'Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting', 'kashiwagi24_interspeech', 'ctc language-specific prompt self-conditioned conditionally model zero-shot incoming attention-based multi-task'], ['Zhaoqing Li, Haoning Xu, Tianzi Wang, Shoukang Hu, Zengrui Jin, Shujie Hu, Jiajun Deng, Mingyu Cui, Mengzhe Geng, Xunying Liu', 'One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model', 'li24o_interspeech', 'librispeech- wer switchboard- nested incurring single speed-up asr width store'], ['Emiru Tsunoo, Hayato Futami, Yosuke Kashiwagi, Siddhant Arora, Shinji Watanabe', 'Decoder-only Architecture for Streaming End-to-end Speech Recognition', 'tsunoo24_interspeech', 'blockwise prompt asr lm decoder subnetwork ample speech-processing test-other truncated'], ['Sichen Jin, Youngmoon Jung, Seungjin Lee, Jaeyoung Roh, Changwoo Han, Hoonyoung Cho', 'CTC-aligned Audio-Text Embedding for Streaming Open-vocabulary Keyword Spotting', 'jin24d_interspeech', 'kw text libriphrase frame non-streaming mere aligns aggregated attain on-the-fly'], ['Kiyoshi Kurihara, Masanori Sano', 'Enhancing Japanese Text-to-Speech Accuracy with a Novel Combination Transformer-BERT-based G2P: Integrating Pronunciation Dictionaries and Accent Sandhi', 'kurihara24_interspeech', 'transformer numeral counter bert transformer-based noun external proper dictionary employ'], ['Jiahao Li, Miao Liu, Shu Yang, Jing Wang, Xiang Xie', 'Motion Based Audio-Visual Segmentation', 'li24p_interspeech', 'av object task video mva module attention crossmodal pixel optical'], ['Le Xu, Jiangyan Yi, Tao Wang, Yong Ren, Rongxiu Zhong, Zhengqi Wen, Jianhua Tao', 'Residual Speaker Representation for One-Shot Voice Conversion', 'xu24b_interspeech', 'timbre robustness multi-layer approximation unseen encountering limited control challenge page'], ['Hayato Futami, Siddhant Arora, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe', 'Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model', 'futami24_interspeech', 'slu task forgetting previously trained adapting experiencing subnetwork mitigated catastrophic'], ['Pengfei Cai, Yan Song, Kang Li, Haoyu Song, Ian McLoughlin', 'MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection', 'cai24_interspeech', 'psds sed dcase network context pre-trained encoder global-local rnn-based positional'], ['Yuliya Korotkova, Ilya Kalinovskiy, Tatiana Vakhrusheva', 'Word-level Text Markup for Prosody Control in Speech Synthesis', 'korotkova24_interspeech', 'hand-labeling intonation tt one-to-many prosodic scalability interpretable expertise quantized problem'], ['Ryandhimas E. Zezario, Fei Chen, Chiou-Shann Fuh, Hsin-Min Wang, Yu Tsao', 'Non-Intrusive Speech Intelligibility Prediction for Hearing Aids using Whisper and Metadata', 'zezario24_interspeech', 'mbi-net clarity embeddings metric hearing-aid haspi top-performing validating pivotal intrusive'], ['Anfeng Xu, Kevin Huang, Tiantian Feng, Lue Shen, Helen Tager-Flusberg, Shrikanth Narayanan', 'Exploring Speech Foundation Models for Speaker Diarization in Child-Adult Dyadic Interactions', 'xu24c_interspeech', 'understanding child exemplary opened pathway demographic adopting vast opportunity addressing'], ['Mario Zusag, Laurin Wagner, Bernhad Thallinger', 'CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions', 'zusag24_interspeech', 'finetune hallucination tokenizer transcription timed cross-attention adjusting whisper filler adjustment'], ['Andrés Piñeiro-MartÃn, Carmen GarcÃa-Mateo, Laura Docio-Fernandez, MarÃa del Carmen López-Pérez, Georg Rehm', 'Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition', 'pineiromartin24_interspeech', 'high-resource wer whisper asr reduction continual model unbalanced fine-tune remarkable'], ['Yujie Yan, Xiran Xu, Haolin Zhu, Pei Tian, Zhongshu Ge, Xihong Wu, Jing Chen', 'Auditory Attention Decoding in Four-Talker Environment with EEG', 'yan24b_interspeech', 'aad asad trf cortical spatial indicated unattended two-talker scenario lateralization'], ['Cunhang Fan, Shunbo Dong, Jun Xue, Yujie Chen, Jiangyan Yi, Zhao Lv', 'Frequency-mix Knowledge Distillation for Fake Speech Detection', 'fan24_interspeech', 'fsd telephony asvspoof generalization scenario competitively combat undergoes model information'], ['Yafeng Chen, Siqi Zheng, Hui Wang, Luyao Cheng, Qian Chen, Shiliang Zhang, Junjie Li', 'ERes2NetV2: Boosting Short
11146-Duration Speaker Verification Performance with Computational Efficiency', 'chen24l_interspeech', 'trial net voxceleb fusion tasked sub-optimal feature multi-scale backbone ultimately'], ['Anika A. Spiesberger, Andreas Triantafyllopoulos, Alexander Kathan, Anastasia Semertzidou, Caterina Gawrilow, Tilman Reinelt, Wolfgang A. Rauch, Björn Schuller', 'âSo . . . my child . . . â â How Child ADHD Influences the Way Parents Talk', 'spiesberger24_interspeech', 'mental symptomatology exerts parental parent-child surpassed well-being preschool cumbersome impractical'], ['Lifeng Zhou, Yuke Li, Rui Deng, Yuting Yang, Haoqi Zhu', 'Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval', 'zhou24c_interspeech', 'modality framework inference feature alignment flickr interaction dataset effective task'], ['Malin Svensson Lundmark', 'Magnitude and timing of acceleration peaks in stressed and unstressed syllables', 'svenssonlundmark24_interspeech', 'velocity lower articulator lip peak measured segment posture expands accounted'], ['Ruizhe Huang, Mahsa Yarmohammadi, Sanjeev Khudanpur, Daniel Povey', 'Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation', 'huang24f_interspeech', 'rare perturb inject technique enforce context-aware model asr merely encoders'], ['Yue Li, Xinsheng Wang, Li Zhang, Lei Xie', 'SCDNet: Self-supervised Learning Feature based Speaker Change Detection', 'li24q_interspeech', 'scd ssl wavlm wav vec model potent discern showcase task'], ['Zijie Lin, Tianyu He, Siqi Cai, Haizhou Li', 'ASA: An Auditory Spatial Attention Dataset with Multiple Speaking Locations', 'lin24f_interspeech', 'asad datasets localizing sound electroencephalography featuring cocktail attended source eeg'], ['Nan Chen, Yonghe Wang, Feilong Bao', 'Parameter-Efficient Adapter Based on Pre-trained Models for Speech Translation', 'chen24m_interspeech', 'peft parameter trainable fine-tuning parameter-sharing poorest non-negligible performance na lora'], ['Tin Mei Lun, Ekaterina Voskoboinik, Ragheb Al-Ghezi, Tamas Grosz, Mikko Kurimo', 'Oversampling, Augmentation and Curriculum Learning for Speaking Assessment with Limited Training Data', 'lun24_interspeech', 'finland imbalance greatest finnish evaluates swedish remarkable boost proficiency low-resource'], ['Fei Zhao, Jinjiang Liu, Xueliang Zhang', 'SDAEC: Signal Decoupling for Advancing Acoustic Echo Cancellation', 'zhao24b_interspeech', 'energy reference scaling subsequent microphone network impedes multiplied cancel factor'], ['YongKang Yin, Xu Li, Ying Shan, YueXian Zou', 'AFL-Net: Integrating Audio, Facial, and Lip Modalities with a Two-step Cross-attention for Robust Speaker Diarization in the Wild', 'yin24_interspeech', 'avr-net modality enhance obscured strategy fuse sufficiently multi-modal randomly scene'], ['Genshun Wan, Mengzhi Wang, Tingzhi Mao, Hang Chen, Zhongfu Ye', 'Lightweight Transducer Based on Frame-Level Criterion', 'wan24_interspeech', 'blank output probability achieving element encoder decoder truncate memory non-blank'], ['Hiroki Kanagawa, Takafumi Moriya, Yusuke Ijima', 'Pre-training Neural Transducer-based Streaming Voice Conversion for Faster Convergence and Alignment-free Training', 'kanagawa24_interspeech', 'vc-t seq guiding alignment tensor probable path pipeline matrix improbable'], ['Jing Wu, Ting Chen, Minchuan Chen, Wei Hu, Shaojun Wang, Jing Xiao', 'Improving Multilingual Text-to-Speech with Mixture-of-Language-Experts and Accent Disentanglement', 'wu24f_interspeech', 'code-switching tt conquer intra-utterance authenticity seamless comprehensibility aligns thorough fuse'], ['Jens Edlund, Christina TÃ¥nnander, Sébastien Le Maguer, Petra Wagner', 'Assessing the impact of contextual framing on subjective TTS quality', 'edlund24_interspeech', 'evaluation mo situation generalize without varying decontextualized information-rich fiction corroborates'], ['Kexin Wang, Carlos Ishi, Ryoko Hayashi', 'A multimodal analysis of different types of laughter expression in conversational dialogues', 'wang24r_interspeech', 'mirthful boosting gaze body facial softening tenser form predominant nonverbal'], ['Shunsuke Kando, Yusuke Miyao, Jason Naradowsky, Shinnosuke Takamichi', 'Textless Depen
11146dency Parsing by Labeled Sequence Prediction', 'kando24_interspeech', 'capturing method tree excels effectiveness acoustic speech cascading feature asr'], ['Zugang Zhao, Jinghong Zhang, Yonghui Liu, Jianbing Liu, Kai Niu, Zhiqiang He', 'Streamlining Speech Enhancement DNNs: an Automated Pruning Method Based on Dependency Graph with Advanced Regularized Loss Strategies', 'zhao24c_interspeech', 'compression unveils high-performing burgeoning quest layer impede enriches size computational'], ['Jingru Lin, Meng Ge, Junyi Ao, Liqun Deng, Haizhou Li', 'SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech', 'lin24g_interspeech', 'quot pre-trained pipeline speaker shuffling model single-speaker merged limiting individually'], ['Ziyang Ma, Mingjie Chen, Hezhao Zhang, Zhisheng Zheng, Wenxi Chen, Xiquan Li, Jiaxin Ye, Xie Chen, Thomas Hain', 'EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark', 'ma24b_interspeech', 'ser intra-corpus cross-corpus datasets setting balanced fully making suffered language'], ['Haoyu Li, Baochen Yang, Yu Xi, Linfeng Yu, Tian Tan, Hao Li, Kai Yu', 'Text-aware Speech Separation for Multi-talker Keyword Spotting', 'li24r_interspeech', 'kw clue mixed permutation greatly keyword-specific determinization noisy cocktail front-ends'], ['Jaesong Lee, Soyoon Kim, Hanbyul Kim, Joon Son Chung', 'Lightweight Audio Segmentation for Long-form Speech Translation', 'lee24h_interspeech', 'model quality consume overall segment partitioned pre-training system exists self-supervised'], ['Martin Lebourdais, Théo Mariotte, Antonio Almudévar, Marie Tahon, Alfonso Ortega', 'Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing', 'lebourdais24_interspeech', 'interpretable good representation explanation latent modularity informativeness forensics property compactness'], ['Nan Zhou, Youhai Jiang, Jialin Tan, Chongmin Qi', 'PLDNet: PLD-Guided Lightweight Deep Network Boosted by Efï¬cient Attention for Handheld Dual-Microphone Speech Enhancement', 'zhou24d_interspeech', 'u-net mobile low-complexity guidance phone algorithm pre-process top-performing era gated'], ['Martina Valente, Fabio Brugnara, Giovanni Morrone, Enrico Zovato, Leonardo Badino', 'Exploring Spoken Language Identification Strategies for Automatic Transcription of Multilingual Broadcast and Institutional Speech', 'valente24_interspeech', 'diarization sli monolingual reduction relative wer lower change negatively observing'], ['Kenichi Fujita, Takanori Ashihara, Marc Delcroix, Yusuke Ijima', 'Lightweight Zero-shot Text-to-Speech with Mixture of Adapters', 'fujita24b_interspeech', 'tt method speaker module reproducing adapter non-autoregressive characteristic fidelity less'], ['Junzhe Liu, Jianwei Yu, Xie Chen', 'Improved Factorized Neural Transducer Model For Text-only Domain Adaptation', 'liu24e_interspeech', 'ifnt fnt wer datasets cer out-of-domain relative compared vocabulary doubt'], ['Jakub Hoscilowicz, Adam Wiacek, Jan Chojnacki, Adam Cieslak, Leszek Michon, Artur Janicki', 'Non-Linear Inference Time Intervention: Improving LLM Truthfulness', 'hoscilowicz24_interspeech', 'iti truthful multiple-choice probing pointing let manifest forest relative truth'], ['Benjamin Elie, Juraj Simko, Alice Turk', 'A data-driven model of acoustic speech intelligibility for optimization-based models of speech production', 'elie24_interspeech', 'hyper-articulation articulatory least bilstm-based effort hypo lindblom phoneme balancing return'], ['Jinghong Zhang, Zugang Zhao, Yonghui Liu, Jianbing Liu, Zhiqiang He, Kai Niu', 'TD-PLC: A Semantic-Aware Speech Encoding for Improved Packet Loss Concealment', 'zhang24g_interspeech', 'plc facilitating integrates transmission audio semantic scenario integrity prolonged concurrently'], ['Antonio Almudévar, Théo Mariotte, Alfonso Ortega, Marie Tahon, Luis Vicente, Antonio Miguel, Eduardo Lleida', 'Predefined Prototypes for Intra-Class Separation and Disentanglement', 'almudevar24_interspeech', 'embeddings explainable advantage class inter-class disentangling separability different prototypical simplify'], ['Tina Raissi, Christoph Lüscher, Simon Berger, Ralf Schlüter, Hermann Ney', 'Investigating the Effect of Label Topology and Training Criterion on ASR Performance and Alignment Quality', 'raissi24_interspeech', 'comparison hmm dis factored monotonic first-order strictly division classic modular'], ['Kira Tulchynska, Sylvanus Job, Alena Witzlack-Makarevich, Margaret Zellers', 'Prosodic marking of syntactic boun
11146daries in Khoekhoe', 'tulchynska24_interspeech', 'clause-final auxiliary clause position lengthening candidate intonation sov naq following'], ['Premanand Nayak, Kamini Sabu, M. Ali Basha Shaik', 'Multi-mic Echo Cancellation Coalesced with Beamforming for Real World Adverse Acoustic Conditions', 'nayak24_interspeech', 'aec mmaec deep beamformer ser erle psd introduce far-end steering'], ['Martina Di Bratto, Maria Di Maro, Antonio Origlia', 'On the Use of Plausible Arguments in Explainable Conversational AI', 'dibratto24_interspeech', 'recommendation usability concerning delf cross-disciplinary argumentative dialogue believable system interaction'], ['Yaoyao Yue, Michael Proctor, Luping Zhou, Rijul Gupta, Tharinda Piyadasa, Amelia Gully, Kirrie Ballard, Craig Jin', 'Towards Speech Classification from Acoustic and Vocal Tract data in Real-time MRI', 'yue24_interspeech', 'multimodal rtmri unimodal transformer audio phonemic stream model articulatory combine'], ['Thanapat Trachu, Chawan Piansaddhayanon, Ekapol Chuangsuwanich', 'Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridge', 'trachu24_interspeech', 'diffusion model mode regression score-based necessitate regression-based initializing diffusion-based instability'], ['Rohit Paturi, Xiang Li, Sundararajan Srinivasan', 'AG-LSEC: Audio Grounded Lexical Speaker Error Correction', 'paturi24_interspeech', 'wder audio-based diarization pipeline asr system beat callhome relative fisher'], ['Sheng-Chieh Chiu, Chia-Hua Wu, Jih-Kang Hsieh, Yu Tsao, Hsin-Min Wang', 'Learnable Layer Selection and Model Fusion for Speech Self-Supervised Learning Models', 'chiu24_interspeech', 'gumbel ssl dimension-wise fusing interleaved superb promise enhances sum concatenation'], ['Yicong Jiang, Tianzi Wang, Xurong Xie, Juan Liu, Wei Sun, Nan Yan, Hui Chen, Lan Wang, Xunying Liu, Feng Tian', 'Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition', 'jiang24b_interspeech', 'dysarthric afflicted non-dysarthric lora profound stemming perceiver fixed-length variable-length dissimilarity'], ['Premanand Nayak, M. Ali Basha Shaik', 'Elucidating Clock-drift Using Real-world Audios In Wireless Mode For Time-offset Insensitive End-to-End Asynchronous Acoustic Echo Cancellation', 'nayak24b_interspeech', 'non-linear exacerbation device delineate clock cancellers revisit conventional playback causing'], ['Hao Tan, Xiaochen Liu, Huan Zhang, Junjian Zhang, Yaguan Qian, Zhaoquan Gu', 'DualPure: An Efficient Adversarial Purification Method for Speech Command Recognition', 'tan24_interspeech', 'purify malicious defense perturbation attack frequency unconditional disrupt white-box black-box'], ['Robert Flynn, Anton Ragni', 'Self-Train Before You Transcribe', 'flynn24_interspeech', 'self-training adaptation domain teacher student gain test-time training noisy utilises'], ['Bulat Khaertdinov, Pedro Jeruis, Annanda Sousa, Enrique Hortal', 'Exploring Self-Supervised Multi-view Contrastive Learning for Speech Emotion Recognition with Limited Annotations', 'khaertdinov24_interspeech', 'ser ssl unprecedented reaching performance costly unweighted paralinguistic pre-training advancement'], ['Chengxu Yang, Lin Zheng, Sanli Tian, Gaofeng Cheng, Sujie Xiao, Ta Li', 'Contextual Biasing with Confidence-based Homophone Detector for Mandarin End-to-End Speech Recognition', 'yang24j_interspeech', 'fusion shallow phrase method infrequently deep asr aishell- incorrectly relative'], ['Robert Flynn, Anton Ragni', 'How Much Context Does My Attention-Based ASR System Need?', 'flynn24b_interspeech', 'second long-format length tedlium uncommon acoustic podcasts positional width zero-shot'], ['Sophie Fagniart, Brigitte Charlier, Véronique Delvaux, Bernard Harmegnies, Anne Huberlant, Myriam Piccaluga, Kathy Huet', 'Production of fricative consonants in French-speaking children with cochlear implants and typical hearing: acoustic and phonological analyses.', 'fagniart24_interspeech', 'group stopping lower percentage higher amplitude correct mid-frequency chronological value'], ['Ming Gao, Hang Chen, Jun Du, Xin Xu, Hongxiao Guo, Hui Bu, Jianxing Yang, Ming Li, Chin-Hui Lee', 'Enhancing Voice Wake-Up for Dysarthria: Mandarin Dysarthria Speech Corpus Release and Customized System Design', 'gao24c_interspeech', 'mdsc
11146wws dysarthric home individual intelligibility effortless exceptional encompasses challenge'], ['Jeremy Chang, Kuan-Yu Chen, Chung-Hsien Wu', 'Applying Reinforcement Learning and Multi-Generators for Stage Transition in an Emotional Support Dialogue System', 'chang24_interspeech', 'rouge-l empathetic distress bleu skill user experiencing response grown coping'], ['Bingsong Bai, Fengping Wang, Yingming Gao, Ya Li', 'SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion', 'bai24_interspeech', 'svc cross-domain scenario model innovatively ssim posing diffusion-based disparity hoarseness'], ['Song Li, Yongbin You, Xuezhi Wang, Zhengkun Tian, Ke Ding, Guanglu Wan', 'MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research', 'li24s_interspeech', 'asr whisper publicly impeded gateway chatgpt huggingface garnered immense pave'], ['Zheshu Song, Jianheng Zhuo, Yifan Yang, Ziyang Ma, Shixiong Zhang, Xie Chen', 'LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR', 'song24_interspeech', 'language lora interference persist witnessed mitigating emergence degrading performance incorporation'], ['Na Hu, Hugo Schnack, Amalia Arvaniti', 'Automatic pitch accent classification through image classification', 'hu24b_interspeech', 'classifying showcasing effectiveness feature pixel posed feature-based type labelling yielded'], ['Wei-lin Xie, Yu-Xuan Xi, Yan Song, Jian-tao Zhang, Hao-yu Song, Ian McLoughlin', 'DB-PMAE: Dual-Branch Prototypical Masked AutoEncoder with locality for domain robust speaker verification', 'xie24b_interspeech', 'sid pretrained cnceleb similarity siamese finetuned finetuning frontend framework remarkably'], ['Dan Oneata, Herman Kamper', 'Translating speech with just images', 'oneata24_interspeech', 'translation caption low-resource audio image yoruba captioning regime albeit grounded'], ['Per E Kummervold, Javier de la Rosa, Freddy Wetjen, Rolv-Arild Braaten, Per Erik Solberg', 'Whispering in Norwegian: Navigating Orthographic and Dialectic Challenges', 'kummervold24_interspeech', 'openai whisper dataset large-v fleurs summarise weakly translating converting tailored'], ['David Ortiz-Perez, Jose Garcia-Rodriguez, David Tomás', 'Cognitive Insights Across Languages: Enhancing Multimodal Interview Analysis', 'ortizperez24_interspeech', 'decline taukadial initiating anomalous in-depth audio mild transcribe differentiate comprises'], ['Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas', 'ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings', 'mariotte24_interspeech', 'osd vad spatial self-attention-based filter steer speech-processing explainability multi-microphone segment'], ['Rong Gong, Hongfei Xue, Lezhi Wang, Xin Xu, Qisheng Li, Lei Xie, Hui Bu, Shaomei Wu, Jiaming Zhou, Yong Qin, Binbin Zhang, Jun Du, Jia Bin, Ming Li', 'AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection', 'gong24_interspeech', 'asr inclusivity diminishes human-level verbatim sed encompassing task speech-related stand'], ['Sumit Ranjan, Rupayan Chakraborty, Sunil Kumar Kopparapu', 'Reinforcement Learning based Data Augmentation for Noise Robust Speech Emotion Recognition', 'ranjan24_interspeech', 'ser technique building empathetic scenario picking machine validating cross-corpus reward'], ['Bilal Rahou, Hervé Bredin', 'Multi-latency look-ahead for streaming speaker segmentation', 'rahou24_interspeech', 'latency frame-wise detection inference prism bare contribution computational causal overlapped'], ['Hiroki Kanagawa, Yusuke Ijima', 'Knowledge Distillation from Self-Supervised Representation Learning Model with Discrete Speech Units for Any-to-Any Streaming Voice Conversion', 'kanagawa24b_interspeech', 'ssl content teacher offline prosody operation student encoder inferencing vcs'], ['Yuchen Hu, Chen Chen, Ruizhe Li, Qiushi Zhu, Eng Siong Chng', 'Noise-aware Speech Enhancement using Diffusion Probabilistic Model', 'hu24c_interspeech', 'nase noise reverse guide unseen plug-and-play surge mainstream attracted specificity'], ['Jinming Chen, Jingyi Fang, Yuanzhong Zheng, Yaoxuan Wang, Haojun Fei', 'Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition', 'chen24n_interspeech', 'fusion accent auto facilitating multi chunk streaming cer fine-grained frame-level'], ['Tianci Wu, Shulin He, Jiahui Pan, Haifeng Huang, Zhijian Mo, Xueliang Zhang', 'Unified Audio Visual Cues for Target Speaker Extraction', 'wu24h_interspeech', 'lip fuse distinct network divide-and-conquer movement capitalizing attention tse blend'], ['Hui Wang, Shiwan Zhao, Jiaming Zhou, Xiguang Zheng, Haoqin Sun, Xuechen Wang, Yong Qin', 'Uncertainty-Aware Mean Opinion Score Prediction', 'wang24s_interspeech', 'mo uncertainty diverse system practical epistemic heteroscedastic hindering real monte'], ['Marcely Zanon Boito, Vivek Iyer, Nikolaos Lagos, Laurent Besacier, Ioan Calapodescu', 'mHuBERT-147: A Compact Multilingual HuBERT Model', 'zanonboito24_interspeech', 'params hour larger ml-superb up-sampling leaderboards mm competitiveness massively unprecedented'], ['Seung-bin Kim, Chan-yeong Lim, Jungwoo Heo, Ju-ho Kim, Hyun-seo Shin, Kyo-Won K
11146oo, Ha-Jin Yu', 'MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms', 'kim24j_interspeech', 'multi-resolution waveform-based robustness adjusts persistent obstacle optimally utilization ensuring insufficient'], ['Dejan Porjazovski, Anssi Moisio, Mikko Kurimo', 'Out-of-distribution generalisation in spoken language understanding', 'porjazovski24_interspeech', 'ood slu split slurp modified data emphasising technique unexpectedly dataset'], ['Juan M. MartÃn-Doñas, Aitor Ãlvarez, Eros Rosello, Angel M. Gomez, Antonio M. Peinado', 'Exploring Self-supervised Embeddings and Synthetic Data Augmentation for Robust Audio Deepfake Detection', 'martindonas24_interspeech', 'classifier downstream upstream revisit complemented anti-spoofing feed augmenting specialized foundation'], ['Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Yuto Kondo', 'PRVAE-VC2: Non-Parallel Voice Conversion by Distillation of Speech Representations', 'tanaka24_interspeech', 'streamable hubert converted gap hidden-unit persists webpage posing many-to-many non-streaming'], ['Markéta ÅezáÄková, Daniel Tihelka, JindÅich MatouÅ¡ek', 'Homograph Disambiguation with Text-to-Text Transfer Transformer', 'rezackova24_interspeech', 'single-model wikipedia grapheme-to-phoneme fine-tuned model published proved outperformed powerful online'], ['Séverine Guillaume, Maxime Fily, Alexis Michaud, Guillaume Wisniewski', 'Gender and Language Identification in Multilingual Models of Speech: Exploring the Genericity and Robustness of Speech Representations', 'guillaume24_interspeech', 'xls-r unispeech snippet distill assess informational audio away irrelevant refined'], ['Beomseok Lee, Ioan Calapodescu, Marco Gaido, Matteo Negri, Laurent Besacier', 'Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond', 'lee24i_interspeech', 'massive language datasets slot-filling inherits massively few-shot assess versatile benchmarking'], ['Longbiao Cheng, Ashutosh Pandey, Buye Xu, Tobi Delbruck, Shih-Chii Liu', 'Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement', 'cheng24_interspeech', 'rnn gru gate select step model resource-constrained rnn-based dns neuron'], ['Félix Saget, Meysam Shamsi, Marie Tahon', 'Lifelong Learning MOS Prediction for Synthetic Speech Quality Evaluation', 'saget24_interspeech', 'predictor mode bvcc chronological long-standing breakthrough cross-corpus synthesis reproducible blizzard'], ['Mark Huckvale, Gaston Hilkhuysen', 'Evaluating a 3-factor listener model for prediction of speech intelligibility to hearing-impaired listeners', 'huckvale24_interspeech', 'pure-tone impaired hearing factor sensitivity threshold listener-dependent audiogram held-out evaluate'], ['Séverin Baroudi, Thomas Pellegrini, Hervé Bredin', 'Specializing Self-Supervised Speech Representations for Speaker Segmentation', 'baroudi24_interspeech', 'diarization pretraining wavlm single-speaker pretrained multi-speaker conversational specialize pretext pre-segmented'], ['Xun Gong, Anqi Lv, Zhiming Wang, Yanmin Qian', 'Contextual Biasing Speech Recognition in Speech-enhanced Large Language Model', 'gong24b_interspeech', 'speechllm bias wer persists hallucination declined test-clean word reduction relative'], ['Yangze Li, Xiong Wang, Songjun Cao, Yike Zhang, Long Ma, Lei Xie', 'A Transcription Prompt-based Efficient Audio Large Language Model for Robust Speech Recognition', 'li24t_interspeech', 'repetition decoding llm k-hour nar tokenizer illusion fundamentally non-autoregressive cer'], ['Cheng Gong, Erica Cooper, Xin Wang, Chunyu Qiang, Mengzhe Geng, Dan Wells, Longbiao Wang, Jianwu Dang, Marc Tessier, Aidan Pine, Korin Richmond, Junichi Yamagishi', 'An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios', 'gong24c_interspeech', 'fine-tuning multilingual similarity ssl-based massively adaptability data target surprisingly audio-only'], ['Lingwei Meng, Jiawen Kang, Yuejiao Wang, Zengrui Jin, Xixin Wu, Xunying Liu, Helen Meng', 'Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System', 'meng24c_interspeech', 'talker task embedding librispeechmix librimix empower plug freeze pioneering separator'], ['Takuto Igarashi, Yuki Saito, Kentaro Seki, Shinnosuke Takamichi, Ryuichi Yamamoto, Kentaro Tachibana, Hiroshi Saruwatari', 'Noise-Robust Voice Conversion by Conditional Denoising Training Using Latent Variables of Recording Quality and Environment', 'igarashi24_interspeech', 'speech converted source noisy-to-clean utterance-wise conventional frame-wise noise scene model'], ['Zuoliang Li, Wu Guo, Bin Gu, Shengyu Peng, Jie Zhang', 'Contrastive Learning and Inter-Speaker Distribution Alignment Based Unsupervised Domain Adaptation for Robust Speaker Verification', 'li24u_interspeech', 'uda source target source-domain target-domain method cn-celeb momentum compactness mitigating'], ['Kubilay Can Demir, Belén Lojo RodrÃguez, Tobias Weise, Andreas Maier, Seung Hee Yang', 'Towards Intelligent Speech Assistants in Operating Rooms: A Multimodal Model for Surgical Workflow Analysis', 'demir24_interspeech', 'phase operation mono-modal merges seamlessly prerequisite multi-stage frame-wise -score gated'], ['Dong-Hyun Kim, Joon-Hyuk Chang', 'Mitigating Overfitting in Structured Pruning of ASR Models with Gradient-Guided Parameter Regularization', 'kim24k_interspeech', 'availability shift model exacerbated confront limited generality regularize catastrophic forgetting'], ['Oliver Schrüfer, Manuel Milling, Felix Burkhardt, Florian Eyben, Björn Schuller', 'Are you sure? Analysing Uncertainty Quantification Approaches for Real-world Speech Emotion Recognition', 'schrufer24_interspeech', 'ser faulty ood prediction ambiguity reliable out-of-distribution many documented indication'], ['Katharina Anderer, Andreas Reich, Matthias Wölfel', 'MaViLS, a Benchmark Dataset for Video-to-Slide Alignment, Assessing Baseline Accuracy with a Multimodal Alignment Algorithm Leveraging Speech, OCR, and Visual Features', 'anderer24_interspeech', 'slide lecture highlight matching image video sift underscoring challenge optical'], ['Jinlong Xue, Yayue Deng, Yingming Gao, Ya Li', 'Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretraining', 'xue24b_interspeech', 'prompt rag tt llm speech style-related in-context akin clone model'], ['Gábor Gosztoly
11146a, László Tóth', "Combining Acoustic Feature Sets for Detecting Mild Cognitive Impairment in the Interspeech'24 TAUKADIAL Challenge", 'gosztolya24_interspeech', 'mci task cross-validation machine workflow functionals custom learning mmse rmse'], ['Zhiyuan Tang, Dong Wang, Shen Huang, Shidong Shang', 'Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models', 'tang24_interspeech', 'llm dataset error-correcting paradise hypothesis asr website specialized straightforward enhances'], ['Maryam Naderi, Enno Hermann, Alexandre Nanchen, Sevada Hovsepyan, Mathew Magimai.-Doss', 'Towards interfacing large language models with ASR systems using confidence measures and prompting', 'naderi24_interspeech', 'llm transcript confidence-based post-hoc grow less rescoring n-best correction beyond'], ['Delphine Charuau, Andrea Briglia, Erika Godde, Gérard Bailly', 'Training speech-breathing coordination in computer-assisted reading', 'charuau24_interspeech', 'highlighting respiratory untrained assistance aloud repeated text principle trained karaoke'], ['Koichi Miyazaki, Yoshiki Masuyama, Masato Murata', 'Exploring the Capability of Mamba in Speech Applications', 'miyazaki24_interspeech', 'transformer-based ssms model e-branchformer evaluation long-form facto well-designed asr summarization'], ['Gábor Gosztolya, Mercedes Vetráb, Veronika Svindt, Judit Bóna, Ildikó Hoffmann', 'Wav2vec 2.0 Embeddings Are No Swiss Army Knife -- A Case Study for Multiple Sclerosis', 'gosztolya24b_interspeech', 'functionals surprisingly feature self-supervised classification model unannotated ecapa-tdnn audio performance'], ['Stefan Kalabakov, Monica Gonzalez-Machorro, Florian Eyben, Björn W. Schuller, Bert Arnrich', 'A Comparative Analysis of Federated Learning for Speech-Based Cognitive Decline Detection', 'kalabakov24_interspeech', 'healthy centralised solution hampered collectively discern alzheimer timely state healthcare'], ['Tim Polzehl, Tim Herzig, Friedrich Wicke, Kathleen Wermke, Razieh Khamsehashari, Michiko Dahlem, Sebastian Möller', 'Towards Classifying Mother Tongue from Infant Cries - Findings Substantiating Prenatal Learning Theory', 'polzehl24_interspeech', 'panns neonate model network adhere substantiate confounding cry thereof held-out'], ['Jérémy Giroud, Jessica Lei, Kirsty Phillips, Matthew H. Davis', 'Behavioral evidence for higher speech rate convergence following natural than artificial time altered speech', 'giroud24_interspeech', 'interaction artificially crucial phenomenon ai-powered multiplying proliferation amplified inform everyday'], ['Andrei Andrusenko, Aleksandr Laptev, Vladimir Bataev, Vitaly Lavrukhin, Boris Ginsburg', 'Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter', 'andrusenko24_interspeech', 'recognition candidate pressing nemo method nvidia contextualized model reuse slowing'], ['Huihang Zhong, Yanlu Xie, ZiJin Yao', 'Leveraging Large Language Models to Refine Automatic Feedback Generation at Articulatory Level in Computer Aided Pronunciation Training', 'zhong24b_interspeech', 'gpt- llm helpfulness invite potential effectiveness generated comprehensibility computer-aided capt'], ['Qiuming Zhao, Guangzhi Sun, Chao Zhang, Mingxing Xu, Thomas Fang Zheng', 'SAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASR', 'zhao24d_interspeech', 'moe quantised model mixture-of-experts test-time adaptation personalised ted-lium resource-constrained conformer-based'], ['Siyang Wang, Ãva Székely, Joakim Gustafson', 'Contextual Interactive Evaluation of TTS Models in Dialogue Systems', 'wang24t_interspeech', 'mo shortcoming setup context mean-opinion-score custom-built paramount system questioned evaluate'], ['Gábor Gosztolya, Veronika Svindt, Judit Bóna, Ildikó Hoffmann', 'Automatic Longitudinal Investigation of Multiple Sclerosis Subjects', 'gosztolya24c_interspeech', 'year healthy third category nervous control chronic workflow change classification'], ['Imen Ben-Amor, Jean-Francois Bonastre, Salima Mdhaffar', 'Extraction of interpretable and shared speaker-specific speech attributes through binary auto-encoder', 'benamor24_interspeech', 'explainability proposal attribute embeddings eer lack binarization attribute-based restructuring posing'], ['Anisia Popescu, Lori Lamel, Ioana Vasilescu, Laurence Devillers', 'Automatic Speech Recognition with parallel L1 and L2 acoustic phone models to evaluate /l/ allophony in L2 English speech production', 'popescu24_interspeech', 'french lateral staple darkness dar
11146k clearer asr documented less consuming'], ['Zizhen Lin, Xiaoting Chen, Junyu Wang', 'MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enhancement', 'lin24h_interspeech', 'met u-net lightweight spatial csa deformable voicebank channel attention mere'], ['Yin-Long Liu, Rui Feng, Jia-Hong Yuan, Zhen-Hua Ling', "Clever Hans Effect Found in Automatic Detection of Alzheimer's Disease through Speech", 'liu24f_interspeech', 'pitt recording bias datasets preprocessed uncover audio necessity emphasize accessible'], ['Biswajit Karan, Joshua Jansen van Vüren, Febe de Wet, Thomas Niesler', 'A Transformer-Based Voice Activity Detector', 'karan24_interspeech', 'vad architecture multilingual benchmark end-to-end widens enterprise dataset off-the-shelf auc'], ['Tasnima Sadekova, Mikhail Kudinov, Vadim Popov, Assel Yermekova, Artem Khrapov', 'PitchFlow: adding pitch control to a Flow-matching based TTS model', 'sadekova24_interspeech', 'guidance generation recent diffusion high timbre denoising quality stability fine-grained'], ['Tonmoy Rajkhowa, Amartya Roy Chowdhury, Sankalp Nagaonkar, Achyut Mani Tripathi, Mahadeva Prasanna', 'TM-PATHVQA: 90000+ Textless Multilingual Questions for Medical Visual Question Answering', 'rajkhowa24_interspeech', 'vqa pathological speech-based dataset performing image scenario diagnostics system interaction'], ['Erfan A. Shams, Iona Gessinger, Patrick Cormac English, Julie Carson-Berndsen', 'Are Articulatory Feature Overlaps Shrouded in Speech Embeddings?', 'shams24_interspeech', 'probe assimilation activation transformer articulation explanatory probing spreading ipa phonetic'], ['Sevada Hovsepyan, Mathew Magimai.-Doss', "Neurocomputational model of speech recognition for pathological speech detection: a case study on Parkinson's disease speech detection", 'hovsepyan24_interspeech', 'healthy accumulates computational two-level uncover syllable auc modest merit plausible'], ['Anurag Chowdhur
11146y, Abhinav Misra, Mark C. Fuhs, Monika Woszczyna', 'Investigating Confidence Estimation Measures for Speaker Diarization', 'chowdhury24_interspeech', 'score system downstream identity error derived propagate speaker-adapted adversely segment'], ['Mengjie Qian, Siyuan Tang, Rao Ma, Kate M. Knill, Mark J.F. Gales', "Learn and Don't Forget: Adding a New Language to ASR Foundation Models", 'qian24_interspeech', 'ewc tuning soft fine-tuning code parameter capability performance consolidation set'], ['Benjamin van Niekerk, Julian Zaïdi, Marc-André Carbonneau, Herman Kamper', 'Spoken-Term Discovery using Discrete Speech Units', 'vanniekerk24_interspeech', 'pattern find sub-sequences longstanding discretization zerospeech zero-resource revisit challenge discovering'], ['Mukhtar Mohamed, Oli Danyi Liu, Hao Tang, Sharon Goldwater', 'Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations', 'mohamed24_interspeech', 'probing correlate centroid property downstream degree phone space spanned nuanced'], ['Jinlong Xue, Yayue Deng, Yicheng Han, Yingming Gao, Ya Li', 'Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model', 'xue24c_interspeech', 'tt llm prompt leverage token adapt scenario audiobook -second personalized'], ['Alexis Plaquet, Hervé Bredin', 'On the calibration of powerset speaker diarization models', 'plaquet24_interspeech', 'low-confidence region confidence formulation random explore multiclass model unannotated validating'], ['Kishan Gupta, Nicola Pia, Srikanth Korse, Andreas Brendel, Guillaume Fuchs, Markus Multrus', 'On Improving Error Resilience of Neural End-to-End Speech Coders', 'gupta24c_interspeech', 'packet fec plc bitrates loss low resilient robustness like concealment'], ['Ryo Masumura, Naoki Makishima, Tomohiro Tanaka, Mana Ihori, Naotaka Kawata, Shota Orihashi, Kazutoshi Shinoda, Taiga Yamane, Saki Mizuno, Keita Suzuki, Satoshi Suzuki, Nobukatsu Hojo, Takafumi Moriya, Atsushi Ando', 'Unified Multi-Talker ASR with and without Target-speaker Enrollment', 'masumura24_interspeech', 'mt-asr modeling process form independent bridging enrolled mutually trained autoregressive'], ['Guinan Li, Jiajun Deng, Youjun Chen, Mengzhe Geng, Shujie Hu, Zhe Li, Zengrui Jin, Tianzi Wang, Xurong Xie, Helen Meng, Xunying Liu', 'Joint Speaker Features Learning for Audio-visual Multichannel Speech Separation and Recognition', 'li24v_interspeech', 'wavlm -ted feature purpose-built lr best-performing ecapa-tdnn tightly dev zero-shot'], ['Zexu Pan, Gordon Wichern, François G. Germain, Kohei Saijo, Jonathan Le Roux', 'PARIS: Pseudo-AutoRegressIve Siamese Training for Online Speech Separation', 'pan24_interspeech', 'streaming offline autoregressive step training-inference empowering network si-snr forcing regime'], ['Jizhen Li, Xinmeng Xu, Weiping Tu, Yuhong Yang, Rong Zhu', 'Improving Speech Enhancement by Integrating Inter-Channel and Band Features with Dual-branch Conformer', 'li24w_interspeech', 'channel t-f aware correlation time-frequency information dns-challenge relation recent different'], ['Vasileios Moschopoulos, Thanasis Kotsiopoulos, Pablo Peso Parada, Konstantinos Nikiforidis, Alexandros Stergiadis, Gerasimos Papakostas, Md Asif Jalal, Jisi Zhang, Anastasios Drosou, Karthikeyan Saravanan', 'Exploring compressibility of transformer based text-to-music (TTM) models', 'moschopoulos24_interspeech', 'params compression generative fad infeasible desktop state-of-the distillation server applicability'], ['Thomas Muller, Stephane Ragot, Laetitia Gros, Pierrick Philippe, Pascal Scalart', 'Speech quality evaluation of neural audio codecs', 'muller24c_interspeech', 'codec ev encodec dmos opus lpcnet bitrates targeting technological complement'], ['Yi-Cheng Lin, Haibin Wu, Huang-Cheng Chou, Chi-Chun Lee, Hung-yi Lee', 'Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition', 'lin24i_interspeech', 'ser gender upstream model ssl toward exhibit cutting-edge aiding ssl-based'], ['Judith Dineley, Ewan Carr, Lauren L. White, Catriona Lucas, Zahia Rahman, Tian Pan, Faith Matcham, Johnny Downs, Richard J. Dobson, Thomas F. Quatieri, Nicholas Cummins', 'Variability of speech timing features across repeated recordings: a comparison of open-source extraction techniques', 'dineley24_interspeech', 'extracted clinical via replication hinder variation within-speaker susceptible week symptom'], ['Mahdi Amiri, Ina Kodrasi', 'Adversarial Robustness Analysis in Automatic Pathological Speech Detection Approaches', 'amiri24_interspeech', 'dl-based perturbation imperceptibility imperceptible ineffective healthcare vulnerability unexplored attend projected'], ['Chun-Yi
11146Kuan, Wei-Ping Huang, Hung-yi Lee', 'Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models', 'kuan24_interspeech', 'lalms discriminative audio enhance overlooking assess captioning inadequate struggle weakness'], ['Yiyuan Yang, Niki Trigoni, Andrew Markham', 'Pre-training Feature Guided Diffusion Model for Speech Enhancement', 'yang24k_interspeech', 'efficiency streamline vae optimizes clarity deterministic reverse guidance pretraining utilization'], ['Chung-Wen Wu, Berlin Chen', 'Optimizing Automatic Speech Assessment: W-RankSim Regularization and Hybrid Feature Fusion Strategies', 'wu24i_interspeech', 'asa ordinal vector weighted handcrafted ssl closer showcasing imbalanced challenge'], ['Livia Qian, Gabriel Skantze', 'Joint Learning of Context and Feedback Embeddings in Spoken Dialogue', 'qian24b_interspeech', 'response appropriateness ranking conversational short neglecting backchannels function primarily carry'], ['Nicolò Loddo, Francisca Pessanha, Almila Akdag', 'What if HAL breathed? Enhancing Empathy in Human-AI Interactions with Breathing Speech Synthesis', 'loddo24_interspeech', 'agent novelty towards synthesized diverges empathetic dilemma deepen methodologically engagement'], ['Sameer Khurana, Chiori Hori, Antoine Laurent, Gordon Wichern, Jonathan Le Roux', 'ZeroST: Zero-Shot Speech Translation', 'khurana24_interspeech', 'foundation model multilingual mm bypassing synergistic massively speech-text pave connect'], ['Stefano Goria, Roseline Polle, Salvatore Fara, Nicholas Cummins', 'Revealing Confounding Biases: A Novel Benchmarking Approach for Aggregate-Level Performance Metrics in Health Assessments', 'goria24_interspeech', 'model assessment exaggerate overestimation overestimated machine alzheimer report cross-sectional small-scale'], ['Lucas Block Medin, Thomas Pellegrini, Lucile Gelin', "Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning", 'blockmedin24_interspeech', 'wavlm child base transformer non-english hubert various continue ctc wav'], ['Jules Cauzinille, Benoît Favre, Ricard Marxer, Dena Clink, Abdul Hamid Ahmad, Arnaud Rey', "Investigating self-supervised speech models' ability to classify animal vocalizations: The case of gibbon's vocal signatures", 'cauzinille24_interspeech', 'ssl probing pre-trained grey bioacoustic primate bird non-human classifier explainability'], ['Maurice Gerczuk, Shahin Amiriparian, Justina Lutz, Wolfgang Strube, Irina Papazova, Alkomiet Hasan, Björn W. Schuller', 'Exploring Gender-Specific Speech Patterns in Automatic Suicide Risk Assessment', 'gerczuk24_interspeech', 'patient modelling female gender-based psychiatric medicine specialised subject emergency hindered'], ['Thomas Rolland, Alberto Abad', 'Introduction To Partial Fine-tuning: A Comprehensive Evaluation Of End-to-end Childrenâs Automatic Speech Recognition Adaptation', 'rolland24_interspeech', 'asr dealing data departing granular overfit limited model challenge feedforward'], ['Thomas Rolland, Alberto Abad', 'Shared-Adapters: A Novel Transformer-based Parameter Efficient Transfer Learning Approach For Childrenâs Automatic Speech Recognition', 'rolland24b_interspeech', 'peft parameter-efficient asr fine-tuning pre-trained strike minimising model exceptional challenge'], ['Kentaro Seki, Shinnosuke Takamichi, Norihiro Takamune, Yuki Saito, Kanami Imamura, Hiroshi Saruwatari', 'Spatial Voice Conversion: Voice Conversion Preserving Spatial Information and Non-target Signals', 'seki24_interspeech', 'inherent waveform organize balancing bs stereo ignoring mixing encourage exploration'], ['Nina R. Benway, Jonathan L. Preston, Carol Espy-Wilson', 'Examining Vocal Tract Coordination in Childhood Apraxia of Speech with Acoustic-to-Articulatory Speech Inversion Feature Sets', 'benway24_interspeech', 'disorder auroc genetically neurodevelopmental correlation-based spatiotemporal nested sound -fold replicated'], ['Anna Stein, Kevin Tang', 'Modeling probabilistic reduction across domains with Naive Discriminative Learning', 'stein24_interspeech', 'word context syllable predictability competition cue outcome segment duration local'], ['Alkis Koudounas, Gabriele Ciravegna, Marco Fantini, Erika Crosetti, Giovanni Succo, Tania Cerquitelli, Elena Baralis', 'Voice Disorder Analysis: a Transformer-based Approach', 'koudounas24_interspeech', 'shortage pathology diagnosis data type solution under-explored recording private non-invasive'], ['KiHyun Nam, Hee-Soo Heo, Jee-weon Jung, Joonson Chung', 'Disentangled Representation Learning for Environment-agnostic Speaker Recognition', 'nam24b_interspeech', 'embedding auto-encoder framework extractor code popularly versatility utilises compatibility disentanglement'], ['Tomoki Koriyama', 'VAE-based Phoneme Alignment Using Gradient Annealing and SSL Acoustic Features', 'koriyama24_interspeech', 'vae model -based acoustic-feature mfa ctc-based boundary state-level linguistic widely-used'], ['Iva Ewert, Marvin Borsdorf, Haizhou Li, Tanja Schultz', 'Does the Lombard Effect Matter in Speech Separation? Introducing the Lombard-GRID-2mix Dataset', 'ewert24_interspeech', 'work normal reflexive soundscapes studied style speaking change two-speaker
11146cocktail'], ['Cliodhna Hughes, Guy Brown, Ning Ma, Nicola Dibben', 'Acoustic Effects of Facial Feminisation Surgery on Speech and Singing: A Case Study', 'hughes24_interspeech', 'altered vocal tract people single-case procedure undergoing understudied undergo characteristic'], ['Gaëlle Laperrière, Sahar Ghannay, Bassam Jabaian, Yannick Estève', 'A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding', 'laperriere24_interspeech', 'samu-xlsr slu enrichment specializing loss specialization language-agnostic vastly enrich portability'], ['Jacob Kealey, John R. Hershey, François Grondin', 'Unsupervised Improved MVDR Beamforming for Sound Enhancement', 'kealey24_interspeech', 'multi-channel separation data supervised isolated channel in-the-wild single distortionless case'], ['Yoshiaki Bando, Tomohiko Nakamura, Shinji Watanabe', 'Neural Blind Source Separation and Diarization for Distant Speech Recognition', 'bando24_interspeech', 'gss dsr multichannel supervision mixture method jointly separate weakly-supervised signal-level'], ['Jian Cheng', 'Context-Aware Speech Recognition Using Prompts for Language Learners', 'cheng24b_interspeech', 'gemini whisper spoken asr text context-awareness elicitors wer apps response'], ['Khalid Daoudi, Solange Milhé de Saint Victor, Alexandra Foubert-Samier, Margherita Fabbri, Anne Pavy-Le Traon, Olivier Rascol, Virginie Woisard, Wassilios G. Meissner', "Electroglottography for the assessment of dysphonia in Parkinson's disease and multiple system atrophy", 'daoudi24_interspeech', 'egg early msa-p parkinsonian msa diagnosis disorder stage analysis noninvasive'], ['Arunav Arya, Murtiza Ali, Karan Nathwani', 'Exploiting Wavelet Scattering Transform for an Unsupervised Speaker Diarization in Deep Neural Network Framework', 'arya24_interspeech', 'wst embeddings model speechbrain manner voxconverse segment-wise pyannote customize api'], ['Alexander Barnhill, Elmar Noeth, Andreas Maier, Christian Bergler', 'ANIMAL-CLEAN â A Deep Denoising Toolkit for Animal-Independent Signal Enhancement', 'barnhill24_interspeech', 'bioacoustic animal downstream largely bioacoustics myriad impede non-human existing recording'], ['Adriana Fernandez-Lopez, Honglie Chen, Pingchuan Ma, Lu Yin, Qiao Xiao, Stavros Petridis, Shiwei Liu, Maja Pantic', 'MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization', 'fernandezlopez24_interspeech', 'dense vsr avsr regularization gradient transitioning stabilizes abbreviated vanishing non-zero'], ['James Tanner, Morgan Sonderegger, Jane Stuart-Smith, Tyler Kendall, Jeff Mielke, Robin Dodsworth, Erik Thomas', 'Exploring the anatomy of articulation rate in spontaneous English speech: relationships between utterance length effects and social factors', 'tanner24_interspeech', 'conditioned across gender age effect modulate leaving less broader shown'], ['Lila Kim, Cédric Gendrot', 'Using wav2vec 2.0 for phonetic classification tasks: methodological aspects', 'kim24l_interspeech', 'sequence phoneme longer correlating react speaker vector nasality airflow re
11146covering'], ['Zhaoyu Wang, Haohe Liu, Harry Coppock, Björn Schuller, Mark D. Plumbley', 'Neural Compression Augmentation for Contrastive Audio Representation Learning', 'wang24u_interspeech', 'nca self-supervised music underperform twin lossy audioset pivotal surpass generalisation'], ['Kwanghee Choi, Ankita Pasad, Tomohiko Nakamura, Satoru Fukayama, Karen Livescu, Shinji Watanabe', 'Self-Supervised Speech Representations are More Phonetic than Semantic', 'choi24b_interspeech', 'similarity pair datasets synonym curate corroborates snip property word linguistic'], ['Wiebke Hutiri, Tanvina Patel, Aaron Yi Ding, Odette Scharenborg', 'As Biased as You Measure: Methodological Pitfalls of Bias Evaluations in Speaker Verification Research', 'hutiri24_interspeech', 'base metric choice ratio-based hindering recommend contradictory group favour across'], ['Charles McGhee, Kate Knill, Mark Gales', 'Highly Intelligible Speaker-Independent Articulatory Synthesis', 'mcghee24_interspeech', 'synthesiser inversion deep real simulation-based wer synthetic training acoustic-to-articulatory struggle'], ['Xizi Wei, Stephen McGregor', 'Prompt Tuning for Speech Recognition on Unknown Spoken Name Entities', 'wei24_interspeech', 'entity phrase scenario reflecting named model unheard stratification pertains bot'], ['Rémi Uro, Marie Tahon, David Doukhan, Antoine Laurent, Albert Rilliard', 'Detecting the terminality of speech-turn boundary for spoken interactions in French TV and Radio content', 'uro24_interspeech', 'turn-taking terminal analyzing turn fusion place interrupting non-terminal floor initialization'], ['Liwei Liu, Huihui Wei, Dongya Liu, Zhonghua Fu', 'HarmoNet: Partial DeepFake Detection Network based on Multi-scale HarmoF0 Feature Fusion', 'liu24g_interspeech', 'add region audio track loss post-processor fake locating framework spoofing'], ['Nhan Phan, Anna von Zansen, Maria Kautonen, Ekaterina Voskoboinik, Tamas Grosz, Raili Hilden, Mikko Kurimo', 'Automated content assessment and feedback for Finnish L2 learners in a picture description speaking task', 'phan24_interspeech', 'grading asa language explanation low-resource automatic generation solution visual nlg'], ['Mathilde Hutin, Junfei Hu, Liesbeth Degand', 'Uh, um and mh: Are filled pauses prone to conversational converge?', 'hutin24_interspeech', 'speaker-oriented interlocutor frequent yet conversation asymmetrical interaction form participate debate'], ['Iona Gessinger, Bistra Andreeva, Benjamin R. Cowan', 'The Use of Modifiers and f0 in Remote Referential Communication with Human and Computer Partners', 'gessinger24_interspeech', 'competitor ground partner status condition description privileged common information responded'], ['Marvin Borsdorf, Zexu Pan, Haizhou Li, Tanja Schultz', 'wTIMIT2mix: A
11146Cocktail Party Mixtures Database to Study Target Speaker Extraction for Normal and Whispered Speech', 'borsdorf24_interspeech', 'tse mode signal reference work two-speaker closed-set given equipped smart'], ['Louis Bahrman, Mathieu Fontaine, Jonathan Le Roux, Gaël Richard', 'Speech dereverberation constrained on room impulse response characteristics', 'bahrman24_interspeech', 'dereverberated rir regularizing dry signal loss acoustic black-box provision physically'], ['Xiang Li, Vivek Govindan, Rohit Paturi, Sundararajan Srinivasan', 'Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarization', 'li24x_interspeech', 'eend embeddings speaker framework local embedding-based -pass additional mitigates generalizing'], ['Neelesh Samptur, Tanuka Bhattacharjee, Anirudh Chakravarty K, Seena Vengalil, Yamini Belur, Atchayaram Nalini, Prasanta Kumar Ghosh', 'Exploring Syllable Discriminability during Diadochokinetic Task with Increasing Dysarthria Severity for Patients with Amyotrophic Lateral Sclerosis', 'samptur24_interspeech', 'ddk al manual classification decline among automatic healthy cue impacted'], ['Benjamin Elie, David Doukhan, Rémi Uro, Lucas Ondel-Yang, Albert Rilliard, Simon Devauchelle', 'Articulatory Configurations across Genders and Periods in French Radio and TV archives', 'elie24b_interspeech', 'maeda frame gender female parameter protrusion diachronic assertion lowered spanning'], ['Lingyun Gao, Cristian Tejedor-Garcia, Helmer Strik, Catia Cucchiarini', 'Reading Miscue Detection in Primary School through Automatic Speech Recognition', 'gao24d_interspeech', 'whisper sota child exercise wav diagnosis vec asr highest dutch'], ['Michaela Watkins, Paul Boersma, Silke Hamann', 'Revisiting Pitch Jumps: F0 Ratio in Seoul Korean', 'watkins24_interspeech', 'octave periodicity vibration algorithm capture vocal-fold fortis downward upward chart'], ['Xuanjun Chen, Haibin Wu, Roger Jang, Hung-yi Lee', 'Singing Voice Graph Modeling for SingFake Detection', 'chen24o_interspeech', 'singer unseen sota model music groundbreaking mert struggled copyright deepfakes'], ['Chin-Yun Yu, György Fazekas', 'Differentiable Time-Varying Linear Prediction in the Context of End-to-End Analysis-by-Synthesis', 'yu24b_interspeech', 'generalise frame-wise vocoder efficient reconstructs time-invariant acceleration barrier source-filter recursive'], ['Xuanjun Chen, Jiawei Du, Haibin Wu, Jyh-Shing Roger Jang, Hung-yi Lee', 'Neural Codec-based Adversarial Sample Detection for Speaker Verification', 'chen24p_interspeech', 'asv sota codecs codec method single-model delivering surpassing re-synthesized defense'], ['Trung Dang, David Aponte, Dung Tran, Kazuhito Koishida', 'LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes', 'dang24_interspeech', 'streaming codebook token codebooks codec grouping model-based hard enabling generative'], ['Adaeze Adigwe, Sarenne Wallbridge, Simon King', 'What do people hear? Listenersâ Perception of Conversational Speech', 'adigwe24_interspeech', 'tt explanation preference style underscoring pinpoint prompting synthesise organisation inappropriate'], ['Yifan Peng, Jinchuan Tian, William Chen, Siddhant Arora, Brian Yan, Yui Sudo, Muhammad Shakeel, Kwanghee Choi, Jiatong Shi, Xuankai Chang, Jee-weon Jung, Shinji Watanabe', 'OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer', 'peng24b_interspeech', 'openai predecessor emergent toolkits reproducing biasing license data inferior zero-shot'], ['Kazutoshi Shinoda, Nobukatsu Hojo, Saki Mizuno, Keita Suzuki, Satoshi Kobashikawa, Ryo Masumura', 'Learning from Multiple Annotator Biased Labels in Multimodal Conversation', 'shinoda24_interspeech', 'bias minority class majority debiasing label overlook mitigates distribution value'], ['Shabnam Ghaffarzadegan, Luca Bondi, Wei-Chang Lin, Abinaya Kumar, Ho-Hsiang Wu, Hans-Georg Horst, Samarjit Das', 'Sound of Traffic: A Dataset for Acoustic Traffic Identification and Counting', 'ghaffarzadegan24_interspeech', 'vehicle zenodo org record http right-to-left radar passenger coil inductive'], ['Tobias Weise, Philipp Klumpp, Kubilay Can Demir, Paula Andrea Pérez-Toro, Maria Schuster, Elmar Noeth, Bjoern He
11146ismann, Andreas Maier, Seung Hee Yang', 'Speaker- and Text-Independent Estimation of Articulatory Movements and Phoneme Alignments from Speech', 'weise24_interspeech', 'aai inversion two-staged phoneme-related pta alignment frame aligner acoustic-to-articulatory task'], ['Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung, Skyler Seto, Tatiana Likhomanenko, Stephen Shum, Ahmed Hussen Abdelaziz, Shinji Watanabe, Barry-John Theobald', 'Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?', 'aldeneh24_interspeech', 'verification simplify ingest filter-banks superb revisit sacrificing filter-bank performance inherently'], ['Donna Erickson, Albert Rilliard, Malin Svensson Lundmark, Adelaide Silva, Leticia Rebollo Couto, Oliver Niebuhr, João Antonio de Moraes', 'Collecting Mandible Movement in Brazilian Portuguese', 'erickson24_interspeech', 'closing quick speaker post-stress helmet prosodic structure sentence synchronization lowering'], ['Saurav Pahuja, Gabriel Ivucic, Pascal Himmelmann, Siqi Cai, Tanja Schultz, Haizhou Li', 'Leveraging Graphic and Convolutional Neural Networks for Auditory Attention Detection with EEG', 'pahuja24_interspeech', 'spatiotemporal selective ensemble spatial st-gcn single-trial prediction electroencephalography locus -second'], ['Seong-Gyun Leem, Daniel Fulford, Jukka-Pekka Onnela, David Gard, Carlos Busso', 'Keep, Delete, or Substitute: Frame Selection Strategy for Noise-Robust Speech Emotion Recognition', 'leem24_interspeech', 'ser noise framework background noisy dropped discarding emotionally suppressing avoiding'], ['Alkis Koudounas, Flavio Giobergia, Eliana Pastor, Elena Baralis', 'A Contrastive Learning Approach to Mitigate Bias in Speech Models', 'koudounas24b_interspeech', 'subgroup internal affected three-level overlooking user-defined fair imbalance adoption representation'], ['Debasmita Bhattacharya, Eleanor Lin, Run Chen, Julia Hirschberg', 'Switching Tongues, Sharing Hearts: Identifying the Relationship between Empathy and Code-switching in Speech', 'bhattacharya24_interspeech', 'csw multilingual motivation empathetic prior prevalence sociolinguistic qualitatively acoustic-prosodic asking'], ['Lucas Goncalves, Donita Robinson, Elizabeth Richerson, Carlos Busso', 'Bridging Emotions Across Languages: Low Rank Adaptation for Multilingual Speech Emotion Recognition', 'goncalves24_interspeech', 'ser lora expression surge envision taiwanese linguistic refining overcoming constantly'], ['Abinay Reddy Naini, Lucas Goncalves, Mary A. Kohler, Donita Robinson, Elizabeth Richerson, Carlos Busso', 'WHiSER: White House Tapes Speech Emotion Recognition Corpus', 'naini24_interspeech', 'ser speech-emotion complex authenticity defense healthcare advancing office offering perfect'], ['Joseph Liu, Mahesh Kumar Nandwana, Janne Pylkkönen, Hannes Heikinheimo, Morgan McGuire', 'Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment', 'liu24h_interspeech', 'semantic classification classifier across general-purpose text framework ablation cross-modal conducting'], ['Sri Harsha Dumpala, Dushyant Sharma, Chandramouli Shama Sastry, Stanislav Kruchinin, James Fosburgh, Patrick A. Naylor', 'XANE: eXplainable Acoustic Neural Embeddings', 'dumpala24_interspeech', 'background detection parameter signal non-intrusive wavlm noise overlapped type method'], ['Spyretta Leivaditi, Tatsunari Matsushima, Matt Coler, Shekhar Nayak, Vass Verkhodanova', 'Fine-Tuning Strategies for Dutch Dysarthric Speech Recognition: Evaluating the Impact of Healthy, Disease-Specific, and Speaker-Specific Data', 'leivaditi24_interspeech', 'ssl third ineffective asr inadequate learning second widespread scarcity sufficiently'], ['Tanel Pärnamaa, Ando Saabas', 'Personalized Speech Enhancement Without a Separate Speaker Embedding Model', 'parnamaa24_interspeech', 'pse suppression winner teleconferencing icassp audio echo surpasses cancellation representation'], ['Deepanshu Gupta, Javier Latorre', 'Positional Description for Numerical Normalization ', 'gupta24d_interspeech', 'pd arithmetic digit model fatal mitigates tokenization tractable fst challenge'], ['Wangyou Zhang, Robin Scheibler, Kohei Saijo, Samuele Cornell, Chenda Li, Zhaoheng Ni, Jan Pirklbauer, Marvin Sach, Shinji Watanabe, Tim Fingscheidt, Yanmin Qian', 'URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement', 'zhang24h_interspeech', 'sub-tasks metric curated existing unify witnessed dereverberation data fill learning-based'], ['Kohei Saijo, Gordon Wichern, François G. Germain, Zexu Pan, Jonathan Le Roux', 'Enhanced Reverberation as Supervision for Unsupervised Speech Separation', 'saijo24_interspeech', 'ra mapped channel mixture era separated stable source-channel pseudo-targets loss'], ['ChengHung Hu, Yusuke Yasuda, Tomoki Toda', 'Embedding Learning for Preference-based Speech Quality Assessment', 'hu24d_interspeech', 'mo embeddings loss utterance closer similar preference score t-sne out-domain'], ['Pravin Mote, Berrak Sisman, Carlos Busso', 'Unsupervised Domain Adaptation for Speech Emotion Recognition using K-Nearest Neighbors Voice Conversion', 'mote24_interspeech', 'unlabeled labeled data ser transformed knn sample re-training model ineffective'], ['Catarina Botelho, John Mendonça, Anna Pompili, Tanja Schultz, Alberto Abad, Isabel Trancoso', "Macro-descriptors for Alzheimer's disease detection using large language models", 'botelho24_interspeech', 'llm transcription designated surpassing prompting experiment interpretable coherence annotator high-level'], ['Ali N. Salman, Zongyang Du, Shreeram Suresh Chandra, İsmail Rasim Ãlgen, Carlos Busso, Berrak Sisman', 'Towards Naturalistic Voice Conversion: NaturalVoices Dataset with an Automatic Processing Pipeline', 'salman24_interspeech', 'natural speech expressive providing spontaneity msp-podcast sourced podcast podcasts scripted'], ['Muhammad Shakeel, Yui Sudo, Yifan Peng, Shinji Watanabe', 'Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss', 'shakeel24_interspeech', 'contextual employing non-contextual contextualization layer unbiased objective ignore biased baseline'], ['Ailin Liu, Pepijn Vunderink, Jose Vargas Quiros, Chirag Raman, Hayley Hung', 'How Private is Low-Frequency Speech Audio in the Wild? An Analysis of Verbal Intelligibility by Humans and Machines', 'liu24i_interspeech', 'privacy social behavior delicate privacy-preserving wearable comprehensively ensures simulating balance'], ['Ladislav MoÅ¡ner, Romain Serizel, Lukáš Burget, OldÅich Plchot, Emmanuel Vincent, Junyi Peng, Jan Äernocký', 'Multi-Channel Extension of Pre-trained Models for Speaker Verification', 'mosner24_interspeech', 'ssl designing best-published enhancement interleaf downside noteworthy propagated cross-channel focus'], ['William Ravenscroft, George Close, Stefan Goetze, Thomas Hain, Mohammad Soleymanpour, Anurag Chowdhur
11146y, Mark C. Fuhs', 'Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition', 'ravenscroft24_interspeech', 'asr pit signal-level loss reference training separator artefact often permutation'], ['Tsun-An Hsieh, Heeyoul Choi, Minje Kim', 'Multimodal Representation Loss Between Timed Text and Audio for Regularized Speech Separation', 'hsieh24b_interspeech', 'ttr summarizer semantics gap regularizer underexplored promotes wavlm text-based bert'], ['Wangyou Zhang, Kohei Saijo, Jee-weon Jung, Chenda Li, Shinji Watanabe, Yanmin Qian', 'Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement', 'zhang24i_interspeech', 'architecture insight larger-scale small-sized size under-explored multi-domain budget plateau provide'], ['Jianyuan Sun, Wenwu Wang, Mark D. Plumbley', 'PFCA-Net: Pyramid Feature Fusion and Cross Content Attention Network for Automated Audio Captioning', 'sun24c_interspeech', 'aac scale fuse existing intricate across struggle facilitating high-dimensional top-down'], ['Woo-Jin Chung, Hong-Goo Kang', 'Speaker-Independent Acoustic-to-Articulatory Inversion through Multi-Channel Attention Discriminator', 'chung24_interspeech', 'aai model intricate overcoming kinematic pearson ema articulography attention-based electromagnetic'], ['Maria Teleki, Xiangjue Dong, Soohwan Kim, James Caverlee', 'Comparing ASR Systems in the Context of Speech Disfluencies', 'teleki24_interspeech', 'whisperx podcasts disfluent google non-scripted node podcast episode larger closer'], ['Ricardo GarcÃa, Rodrigo Mahu, Nicolás Grágeda, Alejandro Luzanto, Nicolas Bohmer, Carlos Busso, Néstor Becerra Yoma', 'Speech emotion recognition with deep learning beamforming on a distant human-robot interaction scenario', 'garcia24_interspeech', 'hri ser testing ccc average technology non-acted emulates indoor msp-podcast'], ['Sarthak Yadav, Zheng-Hua Tan', 'Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations', 'yadav24_interspeech', 'general-purpose transformer spectrogram ssast spurred self-supervision size space model patch'], ['Brady Houston, Omid Sadjadi, Zejiang Hou, Srikanth Vishnubhotla, Kyu J. Han', 'Improving Multilingual ASR Robustness to Errors in Language Input', 'houston24_interspeech', 'sensitivity information inference model label common strategy susceptible continues ensuring'], ['Minh Nguyen, Franck Dernoncourt, Seunghyun Yoon, Hanieh Deilamsalehy, Hao Tan, Ryan Rossi, Quan Hung Tran, Trung Bui, Thien Huu Nguyen', 'Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models', 'nguyen24_interspeech', 'medium large-scale name speaker-identification encompassing speaker accessibility lacking novel archive'], ['Matthew Perez, Aneesha Sampath, Minxue Niu, Emily Mower Provost', 'Beyond Binary: Multiclass Paraphasia Detection with Generative Pretrained Transformers and End-to-End Models', 'perez24_interspeech', 'paraphasias gpt aphasia sequence automatic invention misuse single multiple focus'], ['Nicholas Klein, Tianxiang Chen, Hemlata Tak, Ricardo Casal, Elie Khoury', 'Source Tracing of Audio Deepfake Systems', 'klein24_interspeech', 'generation deepfakes anti-spoofing spoofing attribute discerning multi-language fake undergo genuine'], ['Christoph Boeddeker, Tobias Cord-Landwehr, Reinhold Haeb-Umbach', 'Once more Diarization: Improving meeting transcription systems through segment-level speaker reassignment', 'boeddeker24_interspeech', 'confusion enhancement correct revisiting error attribution assigning ease highlighting applicability'], ['Gabriel Pîrlogeanu, Octavian Pascu, Alexandru-Lucian Georgescu, Horia Cucu', 'Hybrid-Diarization System with Overlap Post-Processing for the DISPLACE 2024 Challenge', 'pirlogeanu24_interspeech', 'diarization der detection eval exhaustive participating collaborative overlapped semi-supervised ensemble'], ['Chris Bras, Tanvina Patel, Odette Scharenborg', 'Using articulated speech EEG signals for imagined speech decoding', 'bras24_interspeech', 'bcis amongst interface end transformative brain-computer point connecting electroencephalography vowel'], ['Emmy Phung, Harsh Deshpande, Ahmad Emami, Kanishk Singh', 'AR-NLU: A Framework for Enhancing Natural Language Understanding Model Robustness against ASR Errors', 'phung24_interspeech', 'nlu asr-robust gold transcript upstream pre-existing adversely challenge input intent'], ['Alireza Bayestehtashk, Amit Kumar, Mike Wurtz', 'Design of Feedback Active Noise Cancellation Filter Using Nested Recurrent Neural Networks', 'bayestehtashk24_interspeech', 'anc stability classical anti-noise problem iir stochastically intractable machine avenue'], ['Paige TuttösÃ, H. Henny Yeung, Yue Wang, Fenqi Wang, Guillaume Denis, Jean-Julien Aucouturier, Angelica Lim', 'Mmm whatcha s
11146ay? Uncovering distal and proximal context effects in first and second-language word perception using psychophysical reverse correlation', 'tuttosi24_interspeech', 'surrounding profile pitch french timescales strikingly rate acoustic speaker vowel'], ['Alan Baade, Puyuan Peng, David Harwath', 'Neural Codec Language Models for Disentangled and Textless Voice Conversion', 'baade24_interspeech', 'speaker vall-e similarity any-to-any synthesis disentanglement normalizing less disentangle guidance'], ['Daniel Friedrichs, Monica Lancheros, Sam Kirkham, Lei He, Andrew Clark, Clemens Lutz, Volker Dellwo, Steven Moran', 'Temporal Co-Registration of Simultaneous Electromagnetic Articulography and Electroencephalography for Precise Articulatory and Neural Data Alignment', 'friedrichs24_interspeech', 'eeg ema planning precision onset synchronizes signal integrity kinematics event-related'], ['Octavian Pascu, Adriana Stan, Dan Oneata, Elisabeta Oneata, Horia Cucu', 'Towards generalisable and calibrated audio deepfake detection with self-supervised representations', 'pascu24_interspeech', 'generalisation reliable building desideratum rawnet model frozen less logistic coupled'], ['Suwon Shon, Kwangyoun Kim, Yi-Te Hsu, Prashant Sridhar, Shinji Watanabe, Karen Livescu', 'DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding', 'shon24_interspeech', 'dsu llm encoder instruction-following adapter answering diverse task integration capability'], ['Wazeer Zulfikar, Nishat Protyasha, Camila Canales, Heli Patel, James Williamson, Laura Sarnie, Lisa Nowinski, Nataliya Kosmyna, Paige Townsend, Sophia Yuditskaya, Tanya Talkar, Utkarsh Oggy Sarawgi, Christopher McDougle, Thomas Quatieri, Pattie Maes, Maria Mody', 'Analyzing Speech Motor Movement using Surface Electromyography in Minimally Verbal Adults with Autism Spectrum Disorder', 'zulfikar24_interspeech', 'semg muscle skill facial greater gender-matched neurotypical discharge video-based correlation'], ['John Janiczek, Dading Chong, Dongyang Dai, Arlo Faria, Chao Wang, Tao Wang, Yuzong Liu', 'Multi-modal Adversarial Training for Zero-Shot Voice Cloning', 'janiczek24_interspeech', 'model magnified conditionally tt failing discriminates speech dataset fastspeech gan'], ['Xin Jing, Andreas Triantafyllopoulos, Björn Schuller', 'ParaCLAP â Towards a general language-audio model for computational paralinguistic tasks', 'jing24b_interspeech', 'clap audio query set pretraining relies surpass captioning available extending'], ['Michael Neumann, Hardik Kothare, Jackson Liscombe, Emma C.L. Leschly, Oliver Roesler, Vikram Ramanarayanan', 'Multimodal Digital Biomarkers for Longitudinal Tracking of Speech Impairment Severity in ALS: An Investigation of Clinically Important Differences', 'neumann24_interspeech', 'clinical remote disease meaningful assessment alsfrs-r responsiveness responsive change progression'], ['Sefik Emre Eskimez, Xiaofei Wang, Manthan Thakker, Chung-Hsien Tsai, Canrun Li, Zhen Xiao, Hemin Yang, Zirun Zhu, Min Tang, Jinyu Li, Sheng Zhao, Naoyuki Kanda', 'Total-Duration-Aware Duration Modeling for Text-to-Speech Systems', 'eskimez24_interspeech', 'tda adjusting diversity phoneme speech model total flow-matching quality intelligibility'], ['Keita Suzuki, Nobukatsu Hojo, Kazutoshi Shinoda, Saki Mizuno, Ryo Masumura', 'Participant-Pair-Wise Bottleneck Transformer for Engagement Estimation from Video Conversation', 'suzuki24_interspeech', 'multi-person token global participant multimodal stream attention among interaction sentiment'], ['Qiao Xiao, Pingchuan Ma, Adriana Fernandez-Lopez, Boqian Wu, Lu Yin, Stavros Petridis, Mykola Pechenizkiy, Maja Pantic, Decebal Constantin Mocanu, Shiwei Liu', 'Dynamic Data Pruning for Automatic Speech Recognition', 'xiao24b_interspeech', 'asr ever-growing barely prohibitively training speech-related entail save overhead granularity'], ['Aryan Chaudhary, Arshdeep Singh, Vinayak Abrol, Mark D. Plumbley', 'Efficient CNNs with Quaternion Transformations and Pruning for Audio Tagging', 'chaudhary24_interspeech', 'footprint memory cost algebra computational large-scale reduce resource-constrained audioset challenge'], ['Yatong Bai, Trung Dang, Dung Tran, Kazuhito Koishida, Somayeh Sojoudi', 'ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation', 'bai24b_interspeech', 'tta diffusion latent query inference classifier-free clap audiocaps cfg model'], ['Florian Lux, Sarina Meyer, Lyonel Behringer, Frank Zalkow, Phat Do, Matt Coler, Emanuël A. P. Habets, Ngoc Thang Vu', 'Meta Learning Text-to-Speech Synthesis in over 7000 Languages', 'lux24_interspeech', 'empower massively landscape releasing linguistic foster innovation zero-shot pretraining speech'], ['Xiaofei Wang, Sefik Emre Eskimez, Manthan Thakker, Hemin Yang, Zirun Zhu, Min Tang, Yufei Xia, Jinzhu Li, Sheng Zhao, Jinyu Li, Na
11146oyuki Kanda', 'An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS', 'wang24v_interspeech', 'prompt audio pre-training quality generated strategy deteriorates mixing masked denoising'], ['Thomas Bott, Florian Lux, Ngoc Thang Vu', 'Controlling Emotion in Text-to-Speech with Natural Language Prompts', 'bott24_interspeech', 'prompt conditioned embeddings tractability steering emotionally prompting text merged intuitive'], ['Hao Yen, Pin-Jui Ku, Sabato Marco Siniscalchi, Chin-Hui Lee', 'Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition', 'yen24_interspeech', 'skr phoneme-based seen character setting wer dat language sequence reduction'], ['Yanis Labrak, Adel Moumen, Richard Dufour, Mickael Rouvier', 'Zero-Shot End-To-End Spoken Question Answering In Medical Domain', 'labrak24_interspeech', 'sqa llm methodology resource transformative question-answering landscape accumulation resource-constrained underscore'], ['Jee-weon Jung, Wangyou Zhang, Jiatong Shi, Zakaria Aldeneh, Takuya Higuchi, Alex Gichamba, Barry-John Theobald, Ahmed Hussen Abdelaziz, Shinji Watanabe', 'ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models', 'jung24c_interspeech', 'embeddings extractor vox effortlessly effortless support use including simplifies facilitating'], ['Jing Pan, Jian Wu, Yashesh Gaur, Sunit Sivasankaran, Zhuo Chen, Shujie Liu, Jinyu Li', 'COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning', 'pan24b_interspeech', 'instruction-following -shot capability llm contextual sqa gpt- question-answer cost-effective biasing'], ['Weiran Wang, Zelin Wu, Diamantino Caseiro, Tsendsuren Munkhdalai, Khe Chai Sim, Pat Rondon, Golan Pundak, Gan Song, Rohit Prabhavalkar, Zhong Meng, Ding Zhao, Tara Sainath, Yanzhang He, Pedro Moreno Mengibar', 'Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm', 'wang24w_interspeech', 'bonus receives efficie
11146ncy vectorization search-based search trade cancel wfst gpu'], ['Tiantian Feng, Dimitrios Dimitriadis, Shrikanth S. Narayanan', 'Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?', 'feng24b_interspeech', 'speech-related usc-sail distance generation high-fidelity quality com heavily github assessing'], ['Grant Anderson, Emma Hart, Dimitra Gkatzia, Ian Beaver', 'Automated Human-Readable Label Generation in Open Intent Discovery', 'anderson24_interspeech', 'unlabelled extraction candidate cluster applying resorting dataset discovering analysing method'], ['Benjamin Barrera-Altuna, Daeun Lee, Zaima Zarnaz, Jinyoung Han, Seungbae Kim', 'The Interspeech 2024 TAUKADIAL Challenge: Multilingual Mild Cognitive Impairment Detection with Multimodal Approach', 'barreraaltuna24_interspeech', 'mci mortality speaking language dementia linguistic across worldwide scalability decline'], ['Ruchao Fan, Natarajan Balaji Shankar, Abeer Alwan', "Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models", 'fan24b_interspeech', 'finetuning sfms peft child wavlm whisper various benchmark state-ofthe-art stabilize'], ['Jee-weon Jung, Xin Wang, Nicholas Evans, Shinji Watanabe, Hye-jin Shim, Hemlata Tak, Siddhant Arora, Junichi Yamagishi, Joon Son Chung', 'To what extent can ASV systems naturally defend against spoofing attacks?', 'jung24d_interspeech', 'advancement spoofing-robust cutting-edge effortlessly necessitating acquires defense underscore non-target threat'], ['Ye Ni, Cong Pang, Chengwei Huang, Cairong Zou', 'MSA-DPCRN: A Multi-Scale Asymmetric Dual-Path Convolution Recurrent Network with Attentional Feature Fusion for Acoustic Echo Cancellation', 'ni24_interspeech', 'overlook deep-learning aec merge fuse numerous model validate majority maintaining'], ['Min Ma, Yuma Koizumi, Shigeki Karita, Heiga Zen, Jason Riesa, Haruko Ishikawa, Michiel Bacchiani', 'FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks', 'ma24c_interspeech', 'fleurs restoration catalyze tt n-way few-shot language fidelity maintains quality'], ['Carly Demopoulos, Linnea Lampinen, Cristian Preciado, Hardik Kothare, Vikram Ramanarayanan', 'Preliminary Investigation of Psychometric Properties of a Novel Multimodal Dialog Based Affect Production Task in Children and Adolescents with Autism', 'demopoulos24_interspeech', 'apt age sex facial neurotypical ethnicity communication vocal race ability'], ['Shiyao Wang, Shiwan Zhao, Jiaming Zhou, Aobo Kong, Yong Qin', 'Enhancing Dysarthric Speech Recognition for Unseen Speakers via Prototype-Based Adaptation', 'wang24x_interspeech', 'dsr fine-tuning prototype per-word inconvenient formidable encapsulate disabled markedly hubert'], ['Shruti Palaskar, Ognjen Rudovic, Sameer Dharur, Florian Pesce, Gautam Krishna, Aswin Sivaraman, Jack Berkowitz, Ahmed Hussen Abdelaziz, Saurabh Adya, Ahmed Tewfik', 'Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection', 'palaskar24_interspeech', 'llm fft eer pre-trained device-directed parity lower consume needing attains'], ['Lin Zhang, Xin Wang, Erica Cooper, Mireia Diez, Federico Landini, Nicholas Evans, Junichi Yamagishi', 'Spoof Diarization: "What Spoofed When" in Partially Spoofed Audio', 'zhang24j_interspeech', 'spoofing clustering partialspoof scenario pioneering task locating defines establishing localization'], ['Zehua Zhang, Xuyi Zhuang, Yukun Qian, Mingjiang Wang', 'Lightweight Dynamic Sparse Transformer for Monaural Speech Enhancement', 'zhang24k_interspeech', 'branch deep coarse fine block wb-pesq spectrum si-sdr feature aggregation'], ['Yu Tomita, Yingxiang Gao, Nobuaki Minematsu, Noriko Nakanishi, Daisuke Saito', 'Analysis and Visualization of Directional Diversity in Listening Fluency of World Englishes Speakers in the Framework of Mutual Shadowing', 'tomita24_interspeech', 'fluently listens disfluency passage communicability larger franca pronunciation shadowed lingua'], ['Yuxuan Xi, Yan Song, Lirong Dai, Haoyu Song, Ian McLoughlin', 'An Effective Local Prototypical Mapping Network for Speech Emotion Recognition', 'xi24_interspeech', 'prototype utterance-level frame-level optimized emotion-aware complex loss mer emotion-related backbone'], ['Yun Liu, Xuechen Liu, Xiaoxiao Miao, Junichi Yamagishi', 'Target Speaker Extraction with Curriculum Learning', 'liu24j_interspeech', 'tse selects interfer
11146ing increasing strategically libri similarity exceeded signal-to-distortion expose'], ['Jihyun Kim, Stijn Kindt, Nilesh Madhu, Hong-Goo Kang', 'Enhanced Deep Speech Separation in Clustered Ad Hoc Distributed Microphone Environments', 'kim24m_interspeech', 'ad-hoc transform-average-concatenate dual-path layer tailor blindly unpredictable learning accommodate fuse'], ['Behnam Gholami, Mostafa El-Khamy, KeeBong Song', 'Knowledge Distillation for Tiny Speech Enhancement with Latent Feature Augmentation', 'gholami24_interspeech', 'model teacher smaller student dnn voicebank complex resource-constrained deploying mimic'], ['Hardik Kothare, Michael Neumann, Cathy Zhang, Jackson Liscombe, Jordi W J van Unnik, Lianne C M Botman, Leonard H van den Berg, Ruben P A van Eijk, Vikram Ramanarayanan', 'How Consistent are Speech-Based Biomarkers in Remote Tracking of ALS Disease Progression Across Languages? A Case Study of English and Dutch', 'kothare24_interspeech', 'pal non-bulbar dutch-speaking bulbar onset english-speaking metric trajectory responsiveness amyotrophic'], ['Dongchao Yang, Dingdong Wang, Haohan Guo, Xueyuan Chen, Xixin Wu, Helen Meng', 'SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models', 'yang24l_interspeech', 'sq-codec nar speech-only space compact finite named speech tt non-'], ['Liu Xiaowang, Jinsong Zhang', 'A Study on the Information Mechanism of the 3rd Tone Sandhi Rule in Mandarin Disyllabic Words', 'xiaowang24_interspeech', 'lexical perspective sentence loss communicative minimal level definitive pair confusing'], ['Byeongjoo Ahn, Karren Yang, Brian Hamilton, Jonathan Sheaffer, Anurag Ranjan, Miguel Sarabia, Oncel Tuzel, Jen-Hao Rick Chang', 'Novel-view Acoustic Synthesis From 3D Reconstructed Rooms', 'ahn24c_interspeech', 'scene psnr dereverberation source sdr localization sound separation naively near-perfect'], ['Bence Mark Halpern, Thomas Tienkamp, Wen-Chin Huang, Lester Phillip Violeta, Teja Rebernik, Sebastiaan de Visscher, Max Witjes, Martijn Wieling, Defne Abur, Tomoki Toda', 'Quantifying the effect of speech pathology on automatic and human speaker verification', 'halpern24_interspeech', 'asv severity negatively perceptual performance correlated post-surgery surgical objective surgery'], ['Xinghao Huang, Weiwei Jiang, Long Rao, Wei Xu, Wenqing Cheng', 'Active Speaker Detection in Fisheye Meeting Scenes with Scene Spatial Spectrums', 'huang24g_interspeech', 'multi-party asd audio roundtable map on-screen circular dataset sota impressive'], ['Vishwanath Pratap Singh, Federico Malato, Ville Hautamäki, Md. Sahidullah, Tomi Kinnunen', 'ROAR: Reinforcing Original to Augmented Data Ratio Dynamics for Wav2vec2.0 Based ASR', 'singh24c_interspeech', 'augmentation heuristic librispeech dqn training amount balancing reinforcement recipe min'], ['Bin Zhao, Mingxuan Huang, Chenlu Ma, Jinyi Xue, Aijun Li, Kunyu Xu', 'Decoding Human Language Acquisition: EEG Evidence for Predictive Probabilistic Statistics in Word Segmentation', 'zhao24e_interspeech', 'stream tri-syllable glean auditory lobe lexical temporal statistical gyrus assertion'], ['Muhammad Yeza Baihaqi, Angel Garcia Contreras, Seiya Kawano, Koichiro Yoshino', 'Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting', 'baihaqi24_interspeech', 'free-form engagement satisfaction score human-agent naturalness correlation prompting collaborative llm'], ['Sahil Kumar, Jialu Li, Youshan Zhang', 'Vision Transformer Segmentation for Visual Bird Sound Denoising', 'kumar24_interspeech', 'vitvs contribution vit encompass persistent positioning long-range multi-scale audio struggle'], ['Vahid Khanagha, Dimitris Koutsaidis, Kaustubh Kalgaonkar, Sriram Srinivasan', 'Interference Aware Training Target for DNN based joint Acoustic Echo Cancellation and Noise Suppression', 'khanagha24_interspeech', 'double-talk shadowing near-end truth ground speech far-end aec spectral altering'], ['Yashish M. Siriwardena, Nathan Swedlow, Audrey Howard, Evan Gitterman, Dan Darcy, Carol Espy-Wilson, Andrea Fanelli', 'Accent Conversion with Articulatory Representations', 'siriwardena24_interspeech', 'speech non-native representation incorporate idea originates acoustic acoustic-to-articulatory phonetic used'], ['Amir Hussein, Desh Raj, Matthew Wiesner, Daniel Povey, Paola Garcia, Sanjeev Khudanpur', 'Enhancing Neural Transducer for Multilingual ASR with Synchronized Language Diarization', 'hussein24_interspeech', 'lid auxiliary synchronizes spanish-english seamless mandarin-english synchronize code-switching multitask switching'], ['Haolan Wang, Amin Edraki, Wai-Yip Chan, Iván López-Espejo, Jesper Jensen', 'No-Reference Speech Intelligibility Prediction Leveraging a Noisy-Speech ASR Pre-Trained Model', 'wang24y_interspeech', 'sip algorithm wav vec data-driven reference-based datasets parameter-efficient low-rank backbone'], ['Bao Hoang, Yijiang Pang, Hiroko Dodge, Jiayu Zhou', 'Translingual Language Markers for Cognitive Assessment from Spontaneous Speech', 'hoang24_interspeech', 'mci mmse detection treatment bilingual clinical taukadial prodromal enrichment mini-mental'], ['Hengchao Shang, Zongyao Li, Jiaxin Guo, Shaojun Li, Zhiqiang Rao, Yuanchang Luo, Daimeng Wei, Hao Yang', 'An End-to-End
11146Speech Summarization Using Large Language Model', 'shang24_interspeech', 'ssum llm summary text connector abstractive long generate audio-text intricate'], ['Shuhua Li, Qirong Mao, Jiatong Shi', 'PL-TTS: A Generalizable Prompt-based Diffusion TTS Augmented by Large Language Model', 'li24y_interspeech', 'style diffusion-based libritts-r enhanced description grained control hot synthesis unsatisfactory'], ['Fabian Ritter-Gutierrez, Kuan-Po Huang, Jeremy H. M. Wong, Dianwen Ng, Hung-yi Lee, Nancy F. Chen, Eng-Siong Chng', 'Dataset-Distillation Generative Model for Speech Emotion Recognition', 'rittergutierrez24_interspeech', 'dataset iemocap downstream training reduces yet hinge accelerates size class'], ['Jiarui Hai, Karan Thakkar, Helin Wang, Zengyi Qin, Mounya Elhilali', 'DreamVoice: Text-Guided Voice Conversion', 'hai24_interspeech', 'timbre one-shot quot desired generation plugin libritts inclusive diffusion-based technology'], ['Yuwu Tang, Ziang Ma, Haitao Zhang', 'Enhanced Feature Learning with Normalized Knowledge Distillation for Audio Tagging', 'tang24b_interspeech', 'cnn-based lightweight transformer-based temperature model customized abundant backbone mainstream method'], ['George Joseph, Arun Baby', 'Speaker Personalization for Automatic Speech Recognition using Weight-Decomposed Low-Rank Adaptation', 'joseph24_interspeech', 'lora personalizing asr fine-tuning optimization model holy showcasing paramount limited'], ['Yinlin Guo, Yening Lv, Jinqiao Dou, Yan Zhang, Yuehai Wang', 'FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis', 'guo24c_interspeech', 'fourier model parameter-sharing convnext intel vits flow-based wavlm compress baseline'], ['Hanbin Bae, Pavel Andreev, Azat Saginbaev, Nicholas Babaev, WonJun Lee, Hosang Sung, Hoon-Young Cho', 'Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds', 'bae24_interspeech', 'on-device latency usage conversation complexity solution anc computational design wireless'], ['Tanya Talkar, Sherman Charles, Chelsea Krantsevich, Kan Kawabata', "Detection of Cognitive Impairment And Alzheimer's Disease Using a Speech- and Language-Based Protocol", 'talkar24_interspeech', 'pad mci auc tool speech-based individual administer presence medication blood'], ['Hyunjae Cho, Junhyeok Lee, Wonbin Jung', 'JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis', 'cho24b_interspeech', 'artifact inference aliasing stacking non-autoregressive low-pass vocoders prevent audible evaluation'], ['Iwen E Kang, Christophe Van Gysel, Man-Hung Siu', 'Transformer-based Model for ASR N-Best Rescoring and Rewriting', 'kang24c_interspeech', 'rewrite rescore pertaining on-device privacy assistant exploring ensure increasingly engine'], ['Jaewon Kim, Won-Gook Choi, Seyun Ahn, Joon-Hyuk Chang', 'Sound of Vision: Audio Generation from Visual Text Embedding through Training Domain Discriminator', 'kim24n_interspeech', 'text-to-audio advancement tta aligns address inability adaptability fidelity compromise ensures'], ['Haojie Zhang, Tao Zhang, Ganjun Liu, Dehui Fu, Xiaohui Hou, Ying Lv', 'DysArinVox: DYSphonia & DYSarthria mandARIN speech corpus', 'zhang24l_interspeech', 'chinese pathological comprehensive meticulously imagery diagnostics crafted diagnosed facilitating ensuring'], ['Noumida A, Rajeev Rajan', 'Multi-label Bird Species Classification from Field Recordings using Mel_Graph-GCN Framework', 'a24_interspeech', 'graph deep cnn convolutional gcn macro specaugment mel-spectrograms mel-spectrogram neural'], ['Sai Srujana Buddi, Satyam Kumar, Utkarsh Sarawgi, Vineet Garg, Shivesh Ranjan, Ognjen Rudovic, Ahmed Hussen Abdelaziz, Saurabh Adya', 'Comparative Analysis of Personalized Voice Activity Detection Systems: Assessing Real-World Effectiveness', 'buddi24_interspeech', 'pvad assess vad comprehensive various metric understanding paramount context-aware technology'], ['Ho-Young Choi, Won-Gook Choi, Joon-Hyuk Chang', 'Retrieval-Augmented Classifier Guidance for Audio Generation', 'choi24c_interspeech', 'sampling incurred low-quality noise-free diffusion dcase retrieved pretraining retrieve acquire'], ['Payal Mohapatra, Shamika Likhite, Subrata Biswas, Bashima Islam, Qi Zhu', 'Missingness-resilient Video-enhanced Multimodal Disfluency Detection', 'mohapatra24_interspeech', 'modality video missing unified fusion accommodates assured resilient curate available'], ['Qifei Li, Yingming Gao, Yuhua Wen, Cong Wang, Ya Li', 'Enhancing Modal Fusion by Alignment and Label Matching for Multimodal Emotion Recognition', 'li24z_interspeech', 'mem mer audio-video information emotional multitask guiding learning arising framework'], ['Zhengyang Chen, Xuechen Liu, Erica Cooper, Junichi Yamagishi, Yanmin Qian', 'Generating Speakers by Prompting Listener Impressions for Pre-trained Multi-Speaker Text-to-Speech Systems', 'chen24q_interspeech', 'prompt trait multispeaker tt pretrained flow-matching texttospeech method module tailor'], ['Junxu Wang, Zhihua Fang, Liang He', 'Self-Supervised Speaker Verification with Mini-Batch Prediction Correction', 'wang24z_interspeech', 'pseudo-labels noisy re-clustering method rectified exponential batch learning bound determines'], ['Zhong Meng, Zelin Wu, Rohit Prabhavalkar, Cal Peyser, Weiran Wang, Nanxin Chen, Tara N. Sainath, Bhuvana Ramabhadran', 'Text Injection for Neural Contextual Biasing', 'meng24d_interspeech', 'cti unpaired asr wer mwer injected phrase speech-like speech-text model'], ['Zihan Pan, Tianchi Liu, Hardik B. Sailor, Qiongqiong Wang', 'Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection', 'pan24c_interspeech', 'wavlm transformer hierarchical behavior layer uncertain large notably multi-layer ssl'], ['Kentaro Onda, Joonyong Park, Nobuaki Minematsu, Daisuke Saito', 'A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora', 'onda24_interspeech', 'gslm accent language spoken process inputting mentally listens reproduction unit'], ['Donghyun Seong, Joon-Hyuk Chang', 'H4C-TTS: Leveraging Multi-Modal Historical Context for Conversational Text-to-Speech', 'seong24_interspeech', 'tt conversation encoder situation appropriate modeling recent contextually natural distinguishing'], ['Daryush D. Mehta, Jarrad H. Van Stan, Hamzeh Ghasemzadeh, Robert E. Hillman', 'Comparing ambulatory voice measures during daily life with brief laboratory assessments in speakers with and without vocal hyperfunction', 'mehta24_interspeech', 'recording hyperfunctional accelerometer habitual assess use accounted tilt relate pressure'], ['Li Li, Shogo Seki', 'Improved Remixing Process for Domain Adaptation-Based Speech Enhancement by Mitigating Data Imbalance in Signal-to-Noise Ratio', 'li24aa_interspeech', 'remixed underrepresented snr balanced teacher remixit encompass re
11146corded model dataset'], ['Yuke Lin, Ming Cheng, Fulin Zhang, Yingying Gao, Shilei Zhang, Ming Li', 'VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark', 'lin24j_interspeech', 'dataset gallery afterward single-model explore encompassing categorize wild probe concrete'], ['A F M Saif, Lisha Chen, Xiaodong Cui, Songtao Lu, Brian Kingsbury, Tianyi Chen', 'M2ASR: Multilingual Multi-task Automatic Speech Recognition via Multi-objective Optimization', 'saif24_interspeech', 'training conflict supervised formulates model objective across multiple task degrading'], ['Liangyu Nie, Sudarsana Reddy Kadiri, Ruchit Agrawal', 'MMSD-Net: Towards Multi-modal Stuttering Detection', 'nie24_interspeech', 'uni-modal speech stuttered impediment disruption context-aware irregular -score neural integral'], ['Mingyue Shi, Huali Zhou, Qinglin Meng, Nengheng Zheng', 'DBD-CI: Doubling the Band Density for Bilateral Cochlear Implants', 'shi24c_interspeech', 'electrode odd alternately speech-in-noise side even stimulating ripple ace dichotic'], ['Peidong Wang, Jian Xue, Jinyu Li, Junkun Chen, Aswin Shanmugam Subramanian', 'Soft Language Identification for Language-Agnostic Many-to-One End-to-End Speech Translation', 'wang24aa_interspeech', 'input model linear source accomplish initialized ensures network specified keeping'], ['Takaaki Saeki, Soumi Maiti, Shinnosuke Takamichi, Shinji Watanabe, Hiroshi Saruwatari', 'SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics', 'saeki24_interspeech', 'subjective bertscore gold dense human computes cross-lingual applicability growing opinion'], ['Kang Zhu, Cunhang Fan, Jianhua Tao, Zhao Lv', 'Prompt Link Multimodal Fusion in Multimodal Sentiment Analysis', 'zhu24_interspeech', 'cpl linkage spl connecting modality dimension distance channel randomness connects'], ['Min-Han Shih, Ho-Lam Chung, Yu-Chi Pai, Ming-Hao Hsu, Guan-Ting Lin, Shang-Wen Li, Hung-yi Lee', 'GSQA: An End-to-End Model for Generative Spoken Question Answering', 'shih24b_interspeech', 'abstractive extractive sqa dataset answer empowers directly stride text surpasses'], ['Yiyang Zhao, Shuai Wang, Guangzhi Sun, Zehua Chen, Chao Zhang, Mingxing Xu, Thomas Fang Zheng', 'Whisper-PMFA: Partial Multi-Scale Feature Aggregation for Speaker Verification using Whisper Models', 'zhao24f_interspeech', 'block eer encoder pmfa cn-celeb low-rank eers ecapa-tdnn receiving resnet'], ['Anna Oura, Hideaki Kikuchi, Tetsunori Kobayashi', 'Preprocessing for acoustic-to-articulatory inversion using real-time MRI movies of Japanese speech', 'oura24_interspeech', 'rtmri aai normalization filtering articulatory estimation extraneous resemble indirect wavelet'], ['Yuting Yang, Guodong Ma, Yuke Li, Binbin Du, Haoqi Zhu, Liang Ruan', 'Learning from Back Chunks: Acquiring More Future Knowledge for Streaming ASR Models via Self Distillation', 'yang24m_interspeech', 'long-distance look-ahead aishell- later latency window information contextual fat chunk-based'], ['Yakun Song, Zhuo Chen, Xiaofei Wang, Ziyang Ma, Guanrou Yang, Xie Chen', 'TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers', 'song24b_interspeech', 'inference efficiency speed vall-e layer cross-attention auto-regressive neural demo suffers'], ['Yaoxun Xu, Shi-Xiong Zhang, Jianwei Yu, Zhiyong Wu, Dong Yu', 'Comparing Discrete and Continuous Space LLMs for Speech Recognition', 'xu24d_interspeech', 'asr llama llm-based open-sourced organizing language advancing hubert achievement representation'], ['Chun Yin, Tai-Shih Chi, Yu Tsao, Hsin-Min Wang', 'SVSNet+: Enhancing Speaker Voice Similarity Assessment Models with Representations from Speech Foundation Models', 'yin24b_interspeech', 'wavlm sfms sfm pre-trained downstream incorporating performance dataset thoroughly baseline'], ['Oliver Roesler, Jackson Liscombe, Michael Neumann, Hardik Kothare, Abhishek Hosamath, Lakshmi Arbatti, Doug Habberstad, Christiane Suendermann-Oeft, Meredith Bartlett, Cathy Zhang, Nikhil Sukhdev, Kolja Wilms, Anusha Badathala, Sandrine Istas, Steve Ruhmel, Bryan Hansen, Madeline Hannan, David Henley, Arthur Wallace, Ira Shoulson, David Suendermann-Oeft, Vikram Ramanarayanan', 'Towards Scalable Remote Assessment of Mild Cognitive Impairment Via Multimodal Dialog', 'roesler24_interspeech', 'mci patient control administering liked reported biomarkers orofacial self-reported cloud-based'], ['Nahomi Kusunoki, Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi', 'Hierarchical Multi-Task Learning with CTC and Recursive Operation', 'kusunoki24_interspeech', 'hmtl intermediate layer prediction model lower-level subwords balancing asr target'], ['Eva Szekely, Maxwell Hope', 'An inclusive approach to creating a palette of synthetic voices for gender diversity', 'szekely24_interspeech', 'tt speaker identity expansive gender-independent failing vocal sgd emergent seeking'], ['Dail Kim, Da-Hee Yang, Donghyun Kim, Joon-Hyuk Chang, Jeonghwan Choi, Moa Lee, Jaemo Yang, Han-gil Moon', 'Guided conditioning with predictive network on score-based diffusion model for speech enhancement', 'kim24o_interspeech', 'removal trade-off diffusion-based guiding noise highlighted method emerged reflects outperforming'], ['Osamu Take, Shinnosuke Takamichi, Kentaro Seki, Yoshiaki Bando, Hiroshi Saruwatari', 'SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis', 'take24_interspeech', 'environment audio diverse spontaneous text-to-speech communication adaptation watch seamless model'], ['Hanzhao Li, Liumeng Xue, Haohan Guo, Xinfa Zhu, Yuanjun Lv, Lei Xie, Yunlin Chen, Hao Yin, Zhifei Li', 'Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation', 'li24ba_interspeech', 'multi-codebook module discrete encodec vq-vae time-invariant resampling decouple upsampling downsampling'], ['Woon-Haeng Heo, Joongyu Maeng, Yoseb Kang, Namhyun Cho', 'Centroid Estimation with Transformer-Based Speaker Embedder for Robust Target Speaker Extraction', 'heo24_interspeech', 'tse separator enrollment aiding information division separating stability utterance speech'], ['Xinyi Wu, Changqing Xu, Nan Li, Rongfeng Su, Lan Wang, Nan Yan', 'Depression Enhances Internal Inconsistency between Spoken and Semantic Emotion: Evidence from the Analysis of Emotion Expression in Conversation', 'wu24j_interspeech', 'depressed expressed modality healthy consistency talk neutral patient emotional topic'], ['Yan Xiong, Visar Berisha, Julie Liss, Chaital
11146i Chakrabarti', 'Improving Speech-Based Dysarthria Detection using Multi-task Learning with Gradient Projection', 'xiong24_interspeech', 'mtl clinical conflict size diagnostics single-task adversely task analytic task-specific'], ['Christina TÃ¥nnander, Shivam Mehta, Jonas Beskow, Jens Edlund', 'Beyond graphemes and phonemes: continuous phonological features in neural text-to-speech synthesis', 'tannander24_interspeech', 'confirming tt matcha-tts position perception change phoneme monotonic dual gradual'], ['Peter Wu, Ryan Kaveh, Raghav Nautiyal, Christine Zhang, Albert Guo, Anvitha Kachinthaya, Tavish Mishra, Bohan Yu, Alan W Black, Rikky Muller, Gopala Krishna Anumanchipalli', 'Towards EMG-to-Speech with Necklace Form Factor', 'wu24k_interspeech', 'emg electrode neck placed reveal device dry inconvenient electromyography regularly'], ['Tuan Nguyen, Huy Dat Tran', 'LingWav2Vec2: Linguistic-augmented wav2vec 2.0 for Vietnamese Mispronunciation Detection', 'nguyen24b_interspeech', 'canonical phoneme mha pronunciation top- feeding challenge linguistic multi-head adoption'], ['Jinyu Li, Leonardo Lancia', 'A multimodal approach to study the nature of coordinative patterns underlying speech rhythm', 'li24ca_interspeech', 'prominence language-specific production coordination sensorimotor speaker pre-recorded syllable defines unfamiliar'], ['Vahid Noroozi, Zhehuai Chen, Somshubra Majumdar, Steve Huang, Jagadeesh Balam, Boris Ginsburg', 'Instruction Data Generation and Unsupervised Adaptation for Speech Language Models', 'noroozi24_interspeech', 'synthetic generate sample text emerges component expand cross-modal large scarcity'], ['Shaoxiang Dang, Tetsuya Matsumoto, Yoshinori Takeuchi, Takashi Tsuboi, Yasuhiro Tanaka, Daisuke Nakatsubo, Satoshi Maesawa, Ryuta Saito, Masahisa Katsuno, Hiroaki Kudo', 'Developing vocal system impaired patient-aimed voice quality assessment approach using ASR representation-included multiple features', 'dang24b_interspeech', 'stn-dbs patient clinical predicting extraordinary showcasing hurdle immense deep pcc'], ['Xuyuan Li, Zengqiang Shang, Peiyang Shi, Hua Hua, Ta Li, Pengyuan Zhang', 'Expressive paragraph text-to-speech synthesis with multi-step variational autoencoder', 'li24da_interspeech', 'ep-mstts speech sliced variable vits-based style model audiobook challenge blizzard'], ['Shivam Mehta, Harm Lameris, Rajiv Punmiya, Jonas Beskow, Eva Szekely, Gustav Eje Henter', 'Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech', 'mehta24b_interspeech', 'nar modelling regression-based speaks non-autoregressive ignore deterministic sampled converting aloud'], ['Haitong Sun, Jaehyun Choi, Nobuaki Minematsu, Daisuke Saito', 'Acceleration of Posteriorgram-based DTW by Distilling the Class-to-class Distances Encoded in the Classifier Used to Calculate Posteriors', 'sun24d_interspeech', 'frame-to-frame posteriorgram n-dimensional distance bhattacharyya class distill fly often sequence'], ['Xu Li, Qirui Wang, Xiaoyu Liu', 'MaskSR: Masked Language Model for Full-band Speech Restoration', 'li24ea_interspeech', 'restoring token distortion reconstructs clipping sub-tasks extracted reverb target high'], ['Sathvik Udupa, Jesuraj Bandekar, Saurabh Kumar, Deekshitha G, Sandhya B, Abhayjeet S, Savitha Murthy, Priyanka Pai, Srinivasa Raghavan, Raoul Nanavati, Prasanta Kumar Ghosh', 'Adapter pre-training for improved speech recognition in unseen domains using low resource adapter tuning of self-supervised models', 'udupa24_interspeech', 'fine-tune ssl low-resource language decoding source target method large cer'], ['Daniel Galvez, Vladimir Bataev, Hainan Xu, Tim Kaldewey', 'Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU', 'galvez24_interspeech', 'billion idle cuda quot implementation transducer inference end-to-end gpu-based parameter'], ['Melanie Weirich, Daniel Duran, Stefanie Jannedy', 'Gender and age based f0-variation in the German Plapper Corpus', 'weirich24_interspeech', 'femininity germany participant mean speaker difference effect masculinity donated female'], ['Han EunGi, Oh Hyun-Bin, Kim Sung-Bin, Corentin Nivelet Etcheberry, Suekyeong Nam, Janghoon Ju, Tae-Hyun Oh', 'Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert', 'eungi24_interspeech', 'loss motion movement garnered overlook generate perceptual realism readability cost-effective'], ['Liangwei Chen, Xiren Zhou, Qiang Tu, Huanhuan Chen', 'Enhancing Speech and Music Discrimination Through the Integration of Static and Dynamic Features', 'chen24r_interspeech', 'audio raw classification reservoir speech-music readout extracted evolve autoencoders stacked'], ['Yan Wan, Mengyi Sun, Xinchen Kang, Jingting Li, Pengfei Guo, Ming Gao, Su-Jing Wang', 'CDSD: Chinese Dysarthria Speech Database', 'w
11146an24b_interspeech', 'dysarthric cer formidable individual impacting html socially featuring dsr widespread'], ['Qingye Shen, Leonardo Lancia, Noel Nguyen', 'A novel experimental design for the study of listener-to-listener convergence in phoneme categorization', 'shen24c_interspeech', 'listener endpoint game constraint identify psychometric comply unambiguously sound avenue'], ['Yuchun Shu, Bo Hu, Yifeng He, Hao Shi, Longbiao Wang, Jianwu Dang', 'Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition', 'shu24_interspeech', 'asr wrong hypothesis n-best well-founded word cross-attention non-autoregressive edit recovering'], ['Meiling Chen, Pengjie Liu, Heng Yang, Haofeng Wang', 'Towards End-to-End Unified Recognition for Mandarin and Cantonese', 'chen24s_interspeech', 'cer mandarin-only efficiency doubled coexist training system model high-resource demanding'], ['Ted Kye', 'Affricates in Lushootseed', 'kye24_interspeech', 'salish ejective coast voiced acoustic-articulatory affricate diachronic frication gravity typological'], ['Zeyang Song, Qianhui Liu, Qu Yang, Yizhou Peng, Haizhou Li', 'ED-sKWS: Early-Decision Spiking Neural Networks for Rapid, and Energy-Efficient Keyword Spotting', 'song24c_interspeech', 'kw energy consumption command speech efficiency snns snn end timestamp'], ['Zimeng Li, Zhongxuan Mao, Shengting Shen, Ivan Yuen, Ping Tang', 'The Production of Contrastive Focus by 7 to 13-year-olds Learning Mandarin Chinese', 'li24fa_interspeech', 'age revealed acquire discourse child tonal perceived tone lexical conveys'], ['Sarina Meyer, Florian Lux, Ngoc Thang Vu', 'Probing the Feasibility of Multilingual Speaker Anonymization', 'meyer24_interspeech', 'privacy language globe speech restricts anonymized protect deterioration component english'], ['Yuejiao Wang, Xianmin Gong, Lingwei Meng, Xixin Wu, Helen Meng', 'Large Language Model-based FMRI Encoding of Language Functions for Subjects with Neurocognitive Disorder', 'wang24ba_interspeech', 'ncd brain language-related functional score cognitive older correlation change adult'], ['Yue Gu, Zhihao Du, Shiliang Zhang, jiqing Han, Yongjun He', 'Personality-memory Gated Adaptation: An Efficient Speaker Adaptation for Personalized End-to-end Automatic Speech Recognition', 'gu24b_interspeech', 'adapter target generalization asr backbone personality cer encoder sacrifice vocal'], ['Daniel Haider, Felix Perfler, Vincent Lostanlen, Martin Ehler, Peter Balazs', 'Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement', 'haider24_interspeech', 'audio encoder adapt guaranteeing conservation filter solution preprocess low-complexity objective'], ['Muhammad Umer Sheikh, Hassan Abid, Bhuiyan Sanjid Shafique, Asif Hanif, Muhammad Haris Khan', 'Bird Whisperer: Leveraging Large Pre-trained Acoustic Model for Bird Call Classification', 'sheikh24_interspeech', 'whisper adapting bioacoustic non-human categorizing feature underscore -score imbalance human'], ['Sylvain Coulange, Tsuneo Kato, Solange Rossato, Monica Masperi', 'Exploring Impact of Pausing and Lexical Stress Patterns on L2 English Comprehensibility in Real Time', 'coulange24_interspeech', 'pause click stressed incorrectly protocol real-time struggling sixty listener word'], ['Rhiannon Mogridge, Anton Ragni', 'Learning from memory-based models', 'mogridge24_interspeech', 'cpc psychology memory parametric field equivalently feature task eliminated sacrificing'], ['Chan-yeong Lim, Hyun-seo Shin, Ju-ho Kim, Jungwoo Heo, Kyo-Won K
11146oo, Seung-bin Kim, Ha-Jin Yu', 'Improving Noise Robustness in Self-supervised Pre-trained Model for Speaker Verification', 'lim24_interspeech', 'warm-up distorting loss noisy information teacher-student strategy angular unexplored prototypical'], ['Jiajun He, Tomoki Toda', '2DP-2MRC: 2-Dimensional Pointer-based Machine Reading Comprehension Method for Multimodal Moment Retrieval', 'he24_interspeech', 'clip-based coarse-grained video underperforms overlooking pointer imprecise existing heavy categorized'], ['Qiang Fang', 'On The Performance of EMA-synchronized Speech and Stand-alone Speech in Acoustic-to-articulatory Inversion', 'fang24_interspeech', 'aai synchronized degrade articulatory root-mean-square acoustic-articulatory pearson various ema latest'], ['Raj Gothi, Rahul Kumar, Mildred Pereira, Nagesh Nayak, Preeti Rao', 'A Dataset and Two-pass System for Reading Miscue Detection', 'gothi24_interspeech', 'asr wide-ranging resource-intensive diagnostics mispronounced elementary limiting alternate viewed apart'], ['Yuxin Xie, Zhihong Zhu, Xianwei Zhuang, Liming Liang, Zhichang Wang, Yuexian Zou', 'GPA: Global and Prototype Alignment for Audio-Text Retrieval', 'xie24c_interspeech', 'coarse-grained audio text atr pair fine-grained interaction similarity justify pursue'], ['Yaqian Hao, Chenguang Hu, Yingying Gao, Shilei Zhang, Junlan Feng', 'On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations', 'hao24_interspeech', 'overconfidence calibrating task guaranteeing classifier deep decision-making mitigating sacrificing emphasizes'], ['Taisei Omine, Kenta Akita, Reiji Tsuruno', 'Robust Laughter Segmentation with Automatic Diverse Data Synthesis', 'omine24_interspeech', 'audio arbitrary annotation annotates datasets training necessitates laugh automatically annotate'], ['Wing-Zin Leung, Mattias Cross, Anton Ragni, Stefan Goetze', 'Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesis', 'leung24_interspeech', 'dasr asr diffusion-based fine-tuning pwd augmentative aac limited finetuning dysarthria'], ['Denise Moussa, Sandra Bergmann, Christian Riess', 'Unmasking Neural Codecs: Forensic Identification of AI-compressed Speech', 'moussa24_interspeech', 'audio ai-based forensics compression lossy trace neurally towards encodec cross-dataset'], ['Yaqian Hao, Chenguang Hu, Yingying Gao, Shilei Zhang, Junlan Feng', 'Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification', 'hao24b_interspeech', 'ood energy score joint enhance conclusively loss sharpness model confronted'], ['Hao Li, Yuan Fang, Xueliang Zhang, Fei Chen, Guanglai Gao', 'Cross-Attention-Guided WaveNet for EEG-to-MEL Spectrogram Reconstruction', 'li24ga_interspeech', '-band mel eeg granularity modality enhance mixup correlation combined cross-attention'], ['Raul Monteiro', 'Adding User Feedback To Enhance CB-Whisper', 'monteiro24_interspeech', 'ov-kws biasing keywords tt keyword-spotting open-vocabulary classifier non-trivial assess audio'], ['Sarah Wesolek, Piotr Gulgowski, Joanna Blaszczak, Marzena Zygis', 'The influence of L2 accent strength and different error types on personality trait ratings', 'wesolek24_interspeech', 'warmth competence grammatical less phonological substitution towards impact unfavorable graded'], ['Ashishkumar Gudmalwar, Nirmesh Shah, Sai Akarsh, Pankaj Wasnik, Rajiv Ratn Shah', 'VECL-TTS: Voice identity and Emotional style controllable Cross-Lingual Text-to-Speech', 'gudmalwar24_interspeech', 'tt emotion dubbing marathi necessitates introduce limited language telugu transferring'], ['Jenifer Vega Rodriguez, Nathalie Vallée, Christophe Savariaux, Silvain Gerber', 'Nasal Air Flow During Speech Production In Korebaju', 'vegarodriguez24_interspeech', 'consonant oral colombia amazonian implosive eva ejective coe harmony carryover'], ['Juhwan Yoon, WooSeok Ko, Seyun Um, Sungwoong Hwang, Soojoong Hwang, Changhwan Kim, Hong-Goo Kang', 'UNIQUE : Unsupervised Network for Integrated Speech Quality Evaluation', 'yoon24b_interspeech', 'score metric manner synthetic anomaly objective measure comprising sophisticated paired'], ['Xuenan Xu, Haohe Liu, Mengyue Wu, Wenwu Wang, Mark D. Plumbley', 'Efficient Audio Captioning with Encoder-Level Knowledge Distillation', 'xu24e_interspeech', 'aac loss mse contrastive data-scarce sequence-level model distill exhibiting performance'], ['Zhiyong Wang, Ruibo Fu, Zhengqi Wen, Yuankun Xie, Yukun Liu, Xiaopeng Wang, Xuefei Liu, Yongwei Li, Jianhua Tao, Xin Qi, Yi Lu, Shuchen Shi', 'Generalized Fake Audio Detection via Deep Stable Learning', 'wang24ca_interspeech', 'swl extra datasets distribution training shift weight decorrelating complicate sample'], ['Haoxiang Shi, Ziqi Liang, Jun Yu', 'Emotional Cues Extraction and Fusion for Multi-modal Emotion Prediction and Recognition in Conversation', 'shi24d_interspeech', 'epc stage modality erc modality-specific overlooking meld forthcoming forecast learning'], ['Xuenan Xu, Pingyue Zhang, Ming Yan, Ji Zhang, Mengyue Wu', 'Enhancing Zero-shot Audio Classification using Sound Attribute Knowledge from Large Language Models', 'xu24f_interspeech', 'class description label innate audioset multi-dimensional learning relied ablation never'], ['Neha Sahipjohn, Ashishkumar Gudmalwar, Nirmesh Shah, Pankaj Wasnik, Rajiv Ratn Shah', 'DubWise: Video-Guided Speech Duration Control in Multimodal LLM-based Text-to-Speech for Dubbing', 'sahipjohn24_interspeech', 'lip token text different language video tt sync via cloning'], ['Zeyu Xie, Baihan Li, Xuenan Xu, Zheng Liang, Kai Yu, Mengyue Wu', 'FakeSound: Deepfake General Audio Detection', 'xie24d_interspeech', 'human discerning tester proliferation model dataset website surpasses locate viewed'], ['Tomi H. Kinnunen, Rosa Gonzalez Hautamäki, Xin Wang, Junichi Yamagishi', 'Speaker Detection by the Individual Listener and the Crowd: Parametric Models Applicable to Bonafide and Deepfake Speech', 'kinnunen24_interspeech', 'role-play subjective det eers fake set-up crowdsourcing spoofed less observing'], ['Ying Shi, Lantian Li, Shi Yin, Dong Wang, Jiqing Han', '
11146Serialized Output Training by Learned Dominance', 'shi24e_interspeech', '-mix pit multi-talker speech component showcased sot librimix time-based module'], ['Bolaji Yusuf, Jan Honza Cernocky, Murat Saraçlar', 'Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units', 'yusuf24b_interspeech', 'aud untranscribed kw generally system complimentary asr-based finetuning data simplify'], ['Wei Liu, Jingyong Hou, Dong Yang, Muyong Cao, Tan Lee', 'LUPET: Incorporating Hierarchical Information Path into Multilingual ASR', 'liu24k_interspeech', 'lid layer routed design mitigates phoneme language high-resource high-performance linguistic'], ['Jing Xu, Minglin Wu, Xixin Wu, Helen Meng', 'Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models', 'xu24g_interspeech', 'existed ssl new preservation re-clustering impairing adaptation ability re-synthesis lora'], ['Martha Schubert, Daniel Duran, Ingo Siegert', 'Challenges of German Speech Recognition: A Study on Multi-ethnolectal Speech Among Adolescents', 'schubert24_interspeech', 'engine multi-ethnic openai meta nemo spontaneous nvidia underrepresented discern persist'], ['Taewoo Kim, Choonsang Cho, Young Han Lee', 'Period Singer: Integrating Periodic and Aperiodic Variational Autoencoders for Natural-Sounding End-to-End Singing Voice Synthesis', 'kim24p_interspeech', 'svs alignment corroborated one-to-many aligner address monotonic high-fidelity component owing'], ['Nao Hodoshima', 'Effects of talker and playback rate of reverberation-induced speech on speech intelligibility of older adults', 'hodoshima24_interspeech', 'oas intelligible reverberation fast original slow significantly twenty-four announcement headphone'], ['Swarup Ranjan Behera, Abhishek Dhiman, Karthik Gowda, Aalekhya Satya Narayani', 'FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation', 'behera24_interspeech', 'ast tome speed accuracy framework inference resource-efficient impact throughput compromising'], ['Zirui Ge, Xinzhou Xu, Haiyan Guo, Tingting Wang, Zhen Yang, Björn W. Schuller', 'DGPN: A Dual Graph Prototypical Network for Few-Shot Speech Spoofing Algorithm Recognition', 'ge24_interspeech', 'inter-speech impeding incipient showcasing ample depict realm anti-spoofing representation emerging'], ['Baihan Li, Zeyu Xie, Xuenan Xu, Yiwei Guo, Ming Yan, Ji Zhang, Kai Yu, Mengyue Wu', 'DiveSound: LLM-Assisted Automatic Taxonomy Construction for Diverse Audio Generation', 'li24ha_interspeech', 'diversity dataset multimodal framework subcategories text-to-audio visual overlook class diversified'], ['Zuzanna Miodonska, Michal KrÄcichwost, Ewa KwaÅniok, Agata Sage, Pawel Badura', 'Frication noise features of Polish voiceless dental fricative and affricate produced by children with and without speech disorder', 'miodonska24_interspeech', 'interdental articulation band formant-related employed normative sibilant computer-aided disordered accompanying'], ['Ying Hu, Huamin Yang, Hao Huang, Liang He', 'Cross-modal Features Interaction-and-Aggregation Network with Self-consistency Training for Speech Emotion Recognition', 'hu24e_interspeech', 'ser multimodal modality supervise task-related shallower bimodal selective adaptively deeper'], ['Donghyun Seong, Hoyoung Lee, Joon-Hyuk Chang', 'TSP-TTS: Text-based Style Predictor with Residual Vector Quantization for Expressive Text-to-Speech', 'seong24b_interspeech', 'speech tt representation incorporating reference human-like quality fail conditioned regular'], ['Ziping Zhao, Tian Gao, Haishuai Wang, Björn Schuller', 'MFDR: Multiple-stage Fusion and Dynamically Refined Network for Multimodal Emotion Recognition', 'zhao24g_interspeech', 'perception window context strip cmu-mosei frame misalignment truncation emotionally discovering'], ['Bubai Maji, Rajlakshmi Guha, Aurobinda Routray, Shazia Nasreen, Debabrata Majumdar', 'Investigation of Layer-Wise Speech Representations in Self-Supervised Learning Models: A Cross-Lingual Study in Detecting Depression', 'maji24_interspeech', 'upstream wavlm hubert pooling add single-language mixed-language detection language max'], ['Yun Hao, Reihaneh Amooie, Wietse de Vries, Thomas Tienkamp, Rik van Noord, Martijn Wieling', 'Exploring Self-Supervised Speech Representations for Cross-lingual Acoustic-to-Articulatory Inversion', 'hao24c_interspeech', 'aai articulatory ssl data potential language prospect inferring less english'], ['Wei Liu, Jingyong Hou, Dong Yang, Muyong Cao, Tan Lee', 'A Parameter-efficient Language Extension Framework for Multilingual ASR', 'liu24l_interspeech', 'masr peft continual module candidate sub-problems add-on probabilistically low-resourced catastrophic'], ['Debasish Ray Mohapatra, Victor Zappi, Sidney Fels', '2.5D Vocal Tract Modeling: Bridging Low-Dimensional Efficiency with 3D Accuracy', 'mohapatra24b_interspeech', 'solver geometry symmetry model finite-difference blend mid-sagittal cross-sectional surpassing aligns'], ['Jesuraj Bandekar, Sathvik Udupa, Prasanta Kumar Ghosh', 'Articulatory synthesis using representations learnt through phonetic label-aware contrastive loss', 'bandekar24_interspeech', 'speech trajectory human-level framewise deep human-like learning learning-based baseline sequence-to-sequence'], ['Yongjie Si, Yanxiong Li, Jialong Li, Jiaxin Tan, Qianhua He', 'Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor', 'si24_interspeech', 'ast session prototype base fsc- embedding classifier training class sample'], ['Rastislav Rabatin, Frank Seide, Ernie Chang', 'Navigating the Minefield of MT Beam Search in Cascaded Streaming Speech Translation', 'rabatin24_interspeech', 'beam-search greedy handling intermediate real-time emitting final unequal machine anticipated'], ['Ling Dong, Zhengtao Yu, Wenjun Wang, Yuxin Huang, Shengxiang Gao, Guojiang Zhou', 'Integrating Speech Self-Supervised Learning Models and Large Language Models for ASR', 'dong24_interspeech', 'llm decoder-only garnered potential transport connecting mainstream aligning writing ssl'], ['Anbai Jiang, Bing Han, Zhiqiang Lv, Yufeng Deng, Wei-Qiang Zhang, Xie Chen, Yanmin Qian, Jia Liu, Pingyi Fan', 'AnoPatch: Towards Better Consistency in Machine Anomalous Sound Detection', 'jiang24c_interspeech', 'pre-trained asd audio dcase inconsistency vit fine-tunes datasets inductive model'], ['Nguyen Manh Tien Anh, Thach Ho Sy', 'Improving Speech Recognition with Prompt-based Contextualized ASR and LLM-based Re-predictor', 'manhtienanh24_interspeech', 'contextual mechanism bot system biasing adapter task text encounter task-specific'], ['Katelyn Taylor, Amelia Gully, Helena Daffern', 'Familiar and Unfamiliar Speaker Identification in Speech and Singing', 'taylor24_interspeech', 'social close network listener sung familiarity recognise sample foil listening'], ['Zihan Zhang, Xianjun Xia, Chuanzeng Huang, Yijian Xiao, Lei Xie', 'BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation', 'zhang24m_interspeech', 'plc icassp plcmos noncausal future complexity dual-path flop module computational'], ['Shuchen Shi, Ruibo Fu, Zhengqi Wen, Jianhua Tao, Tao Wang, Chunyu Qiang, Yi Lu, Xin Qi, Xuefei Liu, Yukun Liu, Yongwei Li, Zhiyong Wang, Xiaopeng Wang', 'PPPR: Portable Plug-in Prompt Refiner for Text to Audio Generation', 'shi24f_interspeech', 'tta description rich enhance text-to-audio inception surpassing altering playing faced'], ['Minglin Wu, Jing Xu, Xixin Wu, Helen Meng', 'Prompting Large Language Models with Mispronunciation Detection and Diagnosis Abilities', 'wu24l_interspeech', 'llm audio prompt english per encoder decoder phone mdd text'], ['Keigo Hojo, Yukoh Wakabayashi, Kengo Ohta, Atsunori Ogawa, Norihide Kitaoka', 'Boosting CTC-based ASR using inter-layer attention-based CTC loss', 'hojo24_interspeech', 'layer encoder intermediate output wer tedlium attention mechanism rtf dividing'], ['Dan Wells, Andrea Lorena Aldana Blanco, Cassia Valentini, Erica Cooper, Aidan Pine, Junichi Yamagishi, Korin Richmond', 'Experimental evaluation of MOS, AB and BWS listening test designs', 'wells24_interspeech', 'type listener seeming liked likeability counterbalanced re-use fastest questioned easiest'], ['Alon Vinnikov, Amir Ivry, Aviv Hurvitz, Igor Abramovski, Sharon K
11146oubi, Ilya Gurvich, Shai Peer, Xiong Xiao, Benjamin Martinez Elizalde, Naoyuki Kanda, Xiaofei Wang, Shalev Shaer, Stav Yagev, Yossi Asher, Sunit Sivasankaran, Yifan Gong, Min Tang, Huaming Wang, Eyal Krupka', 'NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription', 'vinnikov24_interspeech', 'dasr benchmark launch attendee dataset office far-field -hour averaging multi-channel'], ['Jinpeng Li, Yu Pu, Qi Sun, Wei-Qiang Zhang', "Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text", 'li24ia_interspeech', 'pseudo-labeled data gpt researching hallucination worth low-cost penalty fine-tune ultimately'], ['Yunrui Cai, Zhiyong Wu, Jia Jia, Helen Meng', 'LoRA-MER: Low-Rank Adaptation of Pre-Trained Speech Models for Multimodal Emotion Recognition Using Mutual Information', 'cai24b_interspeech', 'mer challenge extract lora mine model feature frozen surpasses fine-tune'], ['Kim Sung-Bin, Lee Chae-Yeon, Gihun Son, Oh Hyun-Bin, Janghoon Ju, Suekyeong Nam, Tae-Hyun Oh', 'MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset', 'sungbin24_interspeech', 'lip-sync movement datasets speech-driven convincing covering comprising github enhances mouth'], ['Wenjun Wang, Shangbin Mo, Ling Dong, Zhengtao Yu, Junjun Guo, Yuxin Huang', 'DGSRN: Noise-Robust Speech Recognition Method with Dual-Path Gated Spectral Refinement Network', 'wang24da_interspeech', 'addressing noise joint enhancement distortion residue persist issue dense suppression'], ['Gahye Kim, Yunjung Eom, Selina S. Sung, Seunghee Ha, Tae-Jin Yoon, Jungmin So', 'Automatic Children Speech Sound Disorder Detection with Age and Speaker Bias Mitigation', 'kim24q_interspeech', 'ssd debiasing age-dependent impediment dataset group pivotal childhood mitigating multi-head'], ['Jen-Tzung Chien, I-Ping Yeh, Man-Wai Mak', 'Collaborative Contrastive Learning for Hypothesis Domain Adaptation', 'chien24c_interspeech', 'source speaker domain-invariant collaboratively harsh pursue pseudo dual data representation'], ['Xuefei Li, Hao Huang, Ying Hu, Liang He, Jiabao Zhang, Yuyi Wang', 'YOLOPitch: A Time-Frequency Dual-Branch YOLO Model for Pitch Estimation', 'li24ja_interspeech', 'sota determination unvoiced music voiced additional detection f-score proposing accuracy'], ['Qi Wu', 'Mandarin T3 Production by Chinese and Japanese Native Speakers', 'wu24m_interspeech', 'tone adjacent face learner influence challenge underscore study creaky mispronunciation'], ['Saturnino Luz, Sofia De La Fuente Garcia, Fasih Haider, Davida Fromm, Brian MacWhinney, Alyssa Lanzi, Ya-Ning Chang, Chia-Ju Chou, Yi-Chien Liu', 'Connected Speech-Based Cognitive Assessment in Chinese and English', 'luz24_interspeech', 'prediction diagnosis score impairment propensity language-agnostic encompass dataset assess generalise'], ['Jae-Hong Lee, Sang-Eon Lee, Dong-Hyun Kim, DoHee Kim, Joon-Hyuk Chang', 'Online Subloop Search via Uncertainty Quantization for Efficient Test-Time Adaptation', 'lee24j_interspeech', 'iteration leader updated method number quantizes inefficiency test thread sample'], ['Haoyu Wang, Guoqiang Hu, Guodong Lin, Wei-Qiang Zhang, Jian Li', 'Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection', 'wang24ea_interspeech', 'chunk decoding chunk-based out-of-distribution hinders cross-attention truncated auto-regressive impressive encoder-decoder'], ['Arnav Goel, Medha Hira, Anubha Gupta', 'Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-Attention Cues in Multitask Learning', 'goel24_interspeech', 'ser benchmark cross-validation field ravdess crema-d emodb advent -fold wavlm'], ['Ilseok Kim, Ju-Seok Seong, Joon-Hyuk Chang', 'Few-Shot Keyword-Incremental Learning with Total Calibration', 'kim24r_interspeech', 'fill session kw class new prototype keywords loses initial mixup'], ['Amit Meghanani, Thomas Hain', 'LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks', 'meghanani24_interspeech', 'cost-effective wavlm hubert fine-tuning regularisation ssl-based superb observed continuing asr'], ['Siddique Latif, Raja Jurdak, Björn W. Schuller', 'Evaluating Transformer-Enhanced Deep Reinforcement Learning for Speech Emotion Recognition', 'latif24_interspeech', 'ser rnns transformer-based transformer benchmark speech-emotion prior centred using recent'], ['Eunseop Yoon, Hee Suk Yoon, John Harvill, Mark Hasegawa-Johnson, Chang D. Yoo', 'LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition', 'yoon24c_interspeech', 'tta self-supervision correction linguistic asr shift exemplification diverges loss wherein'], ['Georgios Paraskevopoulos, Chara Tsoukala, Athanasios Katsamanis, Vassilis Katsouros', 'The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data', 'paraskevopoulos24_interspeech', 'modern data-intensive silver large-v exacerbated assembling compile podcasts technology correlating'], ['Qiquan Zhang, Hongxu Zhu, Xinyuan Qian, Eliathamby Ambikairajah, Haizhou Li', 'An Exploration of Length Generalization in Transformer-Based Speech Enhancement', 'zhang24n_interspeech', 'transformer position embedding utterance ape explore infeasible unexplored quadratic facilitated'], ['Shareef Babu Kalluri, Prachi Singh, Pratik Roy Chowdhuri, Apoorva Kulkarni, Shikha Baghel, Pradyoth Hegde, Swapnil Sontakke, Deepak K T, S.R. Mahadeva Prasanna, Deepu Vijayasenan, Sriram Ganapathy', 'The Second DISPLACE Challenge: DIarization of SPeaker and LAnguage in Conversational Environments', 'kalluri24_interspeech', 'dataset track hour leader recording asr board far-field highlighted baseline'], ['Marc Frei
11146xes, Marc Arnela, Joan Claudi Socoró, Luis Joglar-Ongay, Oriol Guasch, Francesc AlÃas-Pujol', 'Glottal inverse filtering and vocal tract tuning for the numerical simulation of vowel /a/ with different levels of vocal effort', 'freixes24_interspeech', 'source low methodology predominates inverse-filtered liljencrants-fant adjusts model validates reproducing'], ['Shuochen Gao, Shun Lei, Fan Zhuo, Hangyu Liu, Feng Liu, Boshi Tang, Qiaochu Huang, Shiyin Kang, Zhiyong Wu', 'An End-to-End Approach for Chord-Conditioned Song Generation', 'gao24e_interspeech', 'chord music accompaniment flaw vocal harmony inaccuracy control cross-attention lyric'], ['Shuai Wang, Ke Zhang, Shaoxiong Lin, Junjie Li, Xuefei Wang, Meng Ge, Jianwei Yu, Yanmin Qian, Haizhou Li', 'WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction', 'wang24fa_interspeech', 'tse avaliable subsequential isolating featured toolkits off-the-shelf cocktail multi-talker on-the-fly'], ['Minmin Yang, Rachid Ridouane', 'Intrusive schwa within French stop-liquid clusters: An acoustic analysis', 'yang24n_interspeech', 'word-final liquid consonant stop occurrence place articulation position prevalence factor'], ['Wenhao Guan, Kaidi Wang, Wangjin Zhou, Yang Wang, Feng Deng, Hui Wang, Lin Li, Qingyang Hong, Yong Qin', 'LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation', 'guan24b_interspeech', 'diffusion audio step regressing tta sample generated space sacrificing facilitated'], ['Xiaopeng Wang, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Yuankun Xie, Yukun Liu, Jianhua Tao, Xuefei Liu, Yongwei Li, Xin Qi, Yi Lu, Shuchen Shi', 'Genuine-Focused Learning using Mask AutoEncoder for Generalized Fake Audio Detection', 'wang24ga_interspeech', 'fad genuine mae spoofed reconstruction feature gfl content-related focus supplement'], ['Xueyuan Chen, Dongchao Yang, Dingdong Wang, Xixin Wu, Zhiyong Wu, Helen Meng', 'CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction', 'chen24t_interspeech', 'prosody dsr naturalness codecs similarity speaker embeddings encoder normal extract'], ['Peikun Chen, Sining Sun, Changhao Shan, Qing Yang, Lei Xie', 'Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study', 'chen24u_interspeech', 'non-streaming unified token model attention introduce speech-text designed asr speech-related'], ['Valentin Pelloin, Léna Dodson, Ãmile Chapuis, Nicolas Hervé, David Doukhan', 'Automatic Classification of News Subjects in Broadcast News: Application to a Gender Bias Representation Analysis', 'pelloin24_interspeech', 'topic woman llm dataset politics french channel broadcasted delineate computational'], ['Xuanru Zhou, Anshul Kashyap, Steve Li, Ayati Sharma, Brittany Morin, David Baquirin, Jet Vonk, Zoe Ezzes, Zachary Miller, Maria Tempini, Jiachen Lian, Gopala Anumanchipalli', 'YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection', 'zhou24e_interspeech', 'dysfluencies dysfluent aggregator aphasia open-sourced speech-text prolongation governed imperfect state-of-the-art'], ['Ziqian Ning, Shuai Wang, Pengcheng Zhu, Zhichao Wang, Jixun Yao, Lei Xie, Mengxiao Bi', 'DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion', 'ning24_interspeech', 'encoder optional multi-level popularity k-means cascade adopts chunk clustered ssl'], ['Chao-Wei Huang, Hui Lu, Hongyu Gong, Hirofumi Inaguma, Ilia Kulikov, Ruslan Mavlyutov, Sravya Popuri', 'Investigating Decoder-only Large Language Models for Speech-to-text Translation', 'huang24h_interspeech', 'llm covost fleurs consume parameter-efficient exceptional proprietary avenue task speech-related'], ['Dake Guo, Xinfa Zhu, Liumeng Xue, Yongmao Zhang, Wenjie Tian, Lei Xie', 'Text-aware and Context-aware Expressive Audiobook Speech Synthesis', 'guo24d_interspeech', 'style diverse tt expressiveness encoder vits-based capture narrator space audiobooks'], ['Hang Zhao, Yifei Xin, Zhesong Yu, Bilei Zhu, Lu Lu, Zejun Ma', 'MINT: Boosting Audio-Language Model via Multi-Target Pre-Training and Instruction Tuning', 'zhao24h_interspeech', 'audio-text frozen task diverse integration alignment empowers generation cross-modality understanding'], ['Yudong Yang, Rongfeng Su, Rukiye Ruzi, Manwa Ng, Shaofeng Zhao, Nan Yan, Lan Wang', 'Optical Flow Guided Tongue Trajectory Generation for Diffusion-based Acoustic to Articulatory Inversion', 'yang24o_interspeech', 'uti aai diffusion reference generated data omitting constraint contour additional'], ['Xiang-Li Lu, Yi-
11146Fen Liu', 'Deep Prosodic Features in Tandem with Perceptual Judgments of Word Reduction for Tone Recognition in Conversed Speech', 'lu24d_interspeech', 'classification transformer-based rhythmic tackle leveraging encoding classify predicting jointly encoder'], ['Han Kunmei', 'Modelling Lexical Characteristics of the Healthy Aging Population: A Corpus-Based Study', 'kunmei24_interspeech', 'nlp language old age concreteness large-language prodromal tool help normative'], ['Shaojun Li, Daimeng Wei, Hengchao Shang, Jiaxin Guo, ZongYao Li, Zhanglin Wu, Zhiqiang Rao, Yuanchang Luo, Xianghui He, Hao Yang', 'Speaker-Smoothed kNN Speaker Adaptation for End-to-End ASR', 'li24ka_interspeech', 'pre-built setting k-nearest comparably data neighbor x-vector sparsity cer adjust'], ['Jeong-Hwan Choi, Ye-Rin Jeoung, Ilseok Kim, Joon-Hyuk Chang', 'Efficient Speaker Embedding Extraction Using a Twofold Sliding Window Algorithm for Speaker Diarization', 'choi24d_interspeech', 'frame-level representation concatenated pre-trained employ extract floating-point adapter non-overlapping distillation'], ['Mun-Hak Lee, Jae-Hong Lee, DoHee Kim, Ye-Eun Ko, Joon-Hyuk Chang', 'Balanced-Wav2Vec: Enhancing Stability and Robustness of Representation Learning Through Sample Reweighting Techniques', 'lee24k_interspeech', 'collapse mode wav codebook exacerbates stably loss skewed suppresses converges'], ['Xuankai Chang, Jiatong Shi, Jinchuan Tian, Yuning Wu, Yuxun Tang, Yihan Wu, Shinji Watanabe, Yossi Adi, Xie Chen, Qin Jin', 'The Interspeech 2024 Challenge on Speech Processing Using Discrete Units', 'chang24b_interspeech', 'compelling assess pivotal encompasses foster evolving restoration singing highlighted baseline'], ['Hang Su, Yuxiang Kong, Lichun Fan, Peng Gao, Yujun Wang, Zhiyong Wu', 'Speaker Change Detection with Weighted-sum Knowledge Distillation based on Self-supervised Pre-trained Models', 'su24_interspeech', 'scd method fine-tuning model basic consumes many industrial selectively industry'], ['Yeh-Sheng Lin, Shu-Chuan Tseng, Jyh-Shing Roger Jang', 'Leveraging Phonemic Transcription and Whisper toward Clinically Significant Indices for Automatic Child Speech Assessment', 'lin24k_interspeech', 'normative diagnosing early speech-language ssd unsuitable workflow phoneme validates pathologist'], ['Rui Wang, Liping Chen, Kong Aik Lee, Zhen-Hua Ling', 'Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding', 'wang24ha_interspeech', 'attribute perception human preserved pseudo-speaker obscured machine anonymized disentanglement altering'], ['Yishuang Li, Wenhao Guan, Hukai Huang, Shiyu Miao, Qi Su, Lin Li, Qingyang Hong', 'Efficient Integrated Features Based on Pre-trained Models for Speaker Verification', 'li24la_interspeech', 'ptms handcrafted representation undoubtedly decent discarded fine-tune adaptively fuse multi-layer'], ['Jiu Feng, Mehmet Hamza Erol, Joon Son Chung, Arda Senocak', 'ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutions', 'feng24c_interspeech', 'asts ast inference flexibility input packing inherit accommodates fixed-size training'], ['Kun Zou, Fengyun Tan, Ziyang Zhuang, Chenfeng Miao, Tao Wei, Shaodan Zhai, Zijian Li, Wei Hu, Shaojun Wang, Jing Xiao', 'E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition', 'zou24_interspeech', 'paraformer cif speedup aishell- embeddings integrate-and-fire inefficiency nar mechanism token-level'], ['Yu Watanabe, Koichiro Ito, Shigeki Matsubara', 'Utilization of Text Data for Response Timing Detection in Attentive Listening', 'watanabe24_interspeech', 'narrative punctuation agent utilize accumulated trained model insertion mark inspired'], ['Ziyun Cui, Chang Lei, Wen Wu, Yinan Duan, Diyang Qu, Ji Wu, Runsen Chen, Chao Zhang', 'Spontaneous Speech-Based Suicide Risk Detection Using Whisper and Large Language Models', 'cui24_interspeech', 'adolescent finetuning llm potential parameter-efficient eighteen audio-text speech -score aged'], ['Chia-Kai Yeh, Chih-Chun Chen, Ching-Hsien Hsu, Jen-Tzung Chien', 'Cross-Modality Diffusion Modeling and Sampling for Speech Recognition', 'yeh24_interspeech', 'discrete transformer excels decorrelation continuous serving non-autoregressive merit identifies redundancy'], ['Ainikaerjiang Aimaiti, Di Wu, Liting Jiang, Gulinigeer Abudouwaili, Hao Huang, Wushour Silamu', 'An Uyghur Extension to the MASSIVE Multi-lingual Spoken Language Understanding Corpus with Comprehensive Evaluations', 'aimaiti24_interspeech', 'slu dataset embedding affix agglutinative available stem task-oriented com github'], ['Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Neeraj Gaur, Zhong Meng', 'Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions', 'baskar24_interspeech', 'frozen indic prefix fine-tuned asr applying approches testset language-based lead'], ['Mojtaba Kadkhodaie Elyaderani, John Glover, Thomas Schaaf', 'Reference-Free Estimation of the Quality of Clinical Notes Generated from Doctor-Patient Conversations', 'kadkhodaieelyaderani24_interspeech', 'n
11146ote quot collection automatically-generated reference-based generation robust section counterpart absence'], ['Tianqi Geng, Hui Feng', "Form and Function in Prosodic Representation: In the Case of 'ma' in Tianjin Mandarin", 'geng24_interspeech', 'deixis pronoun particle modal marker pitch discourse distinct narrowest widest'], ['Shijie Lai, Minglu He, Zijing Zhao, Kai Wang, Hao Huang, Jichen Yang', 'Synthesizing Long-Form Speech merely from Sentence-Level Corpus with Content Extrapolation and LLM Contextual Enrichment', 'lai24b_interspeech', 'generalization pause llm-based generate model natural equipped gated failure fail'], ['Bingliang Zhao, Jiangping Kong, Xiyu Wu', 'Age-related Differences in Acoustic Cues for the Perception of Checked Syllables in Shengzhou Wu', 'zhao24i_interspeech', 'coda stop glottal evolution perceptual vowel duration chinese unchecked weaken'], ['Sreyan Ghosh, Sonal Kumar, Ashish Seth, Purva Chiniya, Utkarsh Tyagi, Ramani Duraiswami, Dinesh Manocha', 'LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition', 'ghosh24b_interspeech', 'motion lip asr llm visual cue instruct datasets beam-search avsr'], ['David Doukhan, Lena Dodson, Manon Conan, Valentin Pelloin, Aurélien Clamouse, Mélina Lepape, Géraldine Van Hille, Cécile Méadel, Marlène Coulomb-Gully', 'Gender Representation in TV and Radio: Automatic Information Extraction methods versus Manual Analyses', 'doukhan24_interspeech', 'woman descriptor channel protagonist french war reference systemic depicting journalist'], ['Neeraj Gaur, Rohan Agrawal, Gary Wang, Parisa Haghani, Andrew Rosenberg, Bhuvana Ramabhadran', 'ASTRA: Aligning Speech and Text Representations for Asr without Sampling', 'gaur24_interspeech', 'rnnt match modality length fleurs duration-based injection prevailing upsampling misalignment'], ['Anaïs Rameau, Satrajit Ghosh, Alexandros Sigaras, Olivier Elemento, Jean-Christophe Belisle-Pipon, Vardit Ravitsky, Maria Powell, Alistair Johnson, David Dorr, Philip Payne, Micah Boyer, Stephanie Watts, Ruth Bahr, Frank Rudzicz, Jordan Lerner-Ellis, Shaheen Awan, Don Bolser, Yael Bensoussan', 'Developing Multi-Disorder Voice Protocols: A team science approach involving clinical expertise, bioethics, standards, and DEI.', 'rameau24_interspeech', 'respiratory cohort disease large-scale ethically fuel biomarkers sourced pro anxiety'], ['Yuewei Zhang, Huanbin Zou, Jie Zhu', 'Sub-PNWR: Speech Enhancement Based on Signal Sub-Band Splitting and Pseudo Noisy Waveform Reconstruction Loss', 'zhang24o_interspeech', 'full-band denoised bank filter module spectrum computational spaced devise entail'], ['Kai-Wei Chang, Ming-Hao Hsu, Shan-Wen Li, Hung-yi Lee', 'Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks', 'chang24c_interspeech', 'icl demonstration nlp manner equipping capability gpt- first perform few-shot'], ['Akihiro Kato, Hiroyuki Nagano, Kohei Chike, Masaki Nose', 'Self-Supervised Learning for ASR Pre-Training with Uniquely Determined Target Labels and Controlling Cepstrum Truncation for Speech Augmentation', 'kato24_interspeech', 'pre-trained libri-light limited hubert data conformer method condition cer non'], ['Fangjing Niu, Xiaozhe Qi, Xinya Chen, Liang He', 'Speech Topic Classification Based on Multi-Scale and Graph Attention Networks', 'niu24b_interspeech', 'node transcribed convolutional global capture relationship stc surpassing subjected text'], ['Jinchuan Tian, Yifan Peng, William Chen, Kwanghee Choi, Karen Livescu, Shinji Watanabe', 'On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models', 'tian24_interspeech', 'owsm open series staying heterogeneity transparency proxy less punctuation llm'], ['Fathima Zaheera, Supritha Shetty, Gayadhar Pradhan, Deepak K T', 'Automatic Assessment of Dysarthria using Speech and synthetically generated Electroglottograph signal', 'zaheera24_interspeech', 'lmfe dysarthric stm averaged mfccs mel complementary automated computed ua-speech'], ['Yixiang Niu, Ning Chen, Hongqing Zhu, Zhiying Zhu, Guangqiang Li, Yibo Chen', 'Auditory Spatial Attention Detection Based on Feature Disentanglement and Brain Connectivity-Informed Graph Neural Networks', 'niu24c_interspeech', 'eeg asad connectivity cross-subject single-trial surround inter-subject electroencephalogram graph-based model'], ['Tianhua Qi, Shiyan Wang, Cheng Lu, Yan Zhao, Yuan Zong, Wenming Zheng', 'Towards Realistic Emotional Voice Conversion using Controllable Emotional Intensity', 'qi24_interspeech', 'evc diversity rhythm emotion renderer pseudo-labels mere smoothly controllability feature'], ['Jincen Wang, Yan Zhao, Cheng Lu, Chuangao Tang, Sunan Li, Yuan Zong, Wenming Zheng', 'Boosting Cross-Corpus Speech Emotion Recognition using CycleGAN with Contrastive Learning', 'wang24ia_interspeech', 'premise gan ser data casia testing enterface synthetic originates identically'], ['Cheng Lu, Yuan Zong, Yan Zhao, Hailun Lian, Tianhua Qi, Björn Schuller, Wenming Zheng', 'Hierarchical Distribution Adaptation for Unsupervised Cross-corpus Speech Emotion Recognition', 'lu24e_interspeech', 'hda testing utterance-level ser domain undermines sda uda module fda'], ['Jacob Bitterman, Daniel Levi, Hilel Hagai Diamandi, Sharon Gannot, Tal Rosenwein', 'RevRIR: Joint Reverberant Speech and Room Impulse Response Embedding using Contrastive Learning with Application to Room Shape Classification', 'bitterman24_interspeech', 'rir task fingerprinting determine cumbersome specific embed receives volume utterance'], ['Tianyi Xu, Kaixun Huang, Pengcheng Guo, Yu Zhou, Longtao Huang, Hui Xue, Lei Xie', 'Towards Rehearsal-Free Multilingual ASR: A LoRA-based Case Study on Whisper ', 'xu24h_interspeech', 'forgetting original language model parameter uyghur tibetan allocate new lora'], ['Jincen Wang, Yan Zhao, Cheng Lu, Hailun Lian, Hongli Chang, Yuan Zong, Wenming Zheng', 'Confidence-aware Hypothesis Transfer Networks for Source-Free Cross-Corpus Speech Emotion Recognition', 'wang24ja_interspeech', 'ser source module target emovo casia enterface emodb self-training confident'], ['Ofer Schwartz, Sharon Gannot', 'Efficient Joint Bemforming and Acoustic Echo Cancellation Structure for Conference Call Scenarios', 'schwartz24_interspeech', 'aec microphone scheme pre-filter indifferent weight apply far-end cir
11146cumvent change'], ['Zhu Li, Xiyuan Gao, Yuqing Zhang, Shekhar Nayak, Matt Coler', 'A Functional Trade-off between Prosodic and Semantic Cues in Conveying Sarcasm', 'li24ma_interspeech', 'sarcastic phrase semantics meaning expression utterance propensity illocutionary disentangles propositional'], ['Katerina Papadimitriou, Gerasimos Potamianos', 'Multimodal Continuous Fingerspelling Recognition via Visual Alignment Learning', 'papadimitriou24_interspeech', 'skeletal signing st-gcn bigru d-cnn paramount spatio-temporal persist accessibility parameterization'], ['Sathvik Udupa, Soumi Maiti, Prasanta Kumar Ghosh', 'IndicMOS: Multilingual MOS Prediction for 7 Indian languages', 'udupa24b_interspeech', 'tt predictor level open-source evaluation indic train assess challenge gold'], ['Xiuwen Zheng, Bornali Phukon, Mark Hasegawa-Johnson', "Fine-Tuning Automatic Speech Recognition for People with Parkinson's: An Effective Strategy for Enhancing Speech Technology Accessibility", 'zheng24c_interspeech', 'multi-task librispeech sap palsy model dysphonic cerebral asr dysarthric data'], ['Peter Birkholz, Patrick Häsner', 'Measurement and simulation of pressure losses due to airflow in vocal tract models', 'birkholz24_interspeech', 'tube viscous section proportional glottis kinetic power area diameter bernoulli'], ['Khanh Le, Duc Chau', 'Improving Streaming Speech Recognition With Time-Shifted Contextual Attention And Dynamic Right Context Masking', 'le24_interspeech', 'tsca user-perceived drc future in-context chunk-based valued restricts featuring stand'], ['Vu Hoang, Viet Thanh Pham, Hoa Nguyen Xuan, Pham Nhi, Phuong Dat, Thi Thu Trang Nguyen', 'VSASV: a Vietnamese Dataset for Spoofing-Aware Speaker Verification', 'hoang24b_interspeech', 'sasv spoofed language system authentic unexplored anti-spoofing concentrated encourage latest'], ['Tuyen Tran, Khanh Le, Ngoc Dang Nguyen, Minh Vu, Huyen Ngo, Woomyoung Park, Thi Thu Trang Nguyen', 'VN-SLU: A Vietnamese Spoken Language Understanding Dataset', 'tran24b_interspeech', 'slu ensuring intent tool crowd-sourcing smart slot scarcity home utterance'], ['Hemant Yadav, Sunayana Sitaram, Rajiv Ratn Shah', 'MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations', 'yadav24b_interspeech', 'hubert self-supervised asr swap traction disparity finetuning beat vanilla lag'], ['Mattias Nilsson, Riccardo Miccini, Clement Laroche, Tobias Piechowiak, Friedemann Zenke', 'Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps', 'nilsson24_interspeech', 'mixed-precision bam device dnsmos commonplace dot prohibitive resource-constrained multiplication -bit'], ['Atli Sigurgeirsson, Eddie L. Ungless', "Just Because We Camp, Doesn't Mean We Should: The Ethics of Modelling Queer Voices.", 'sigurgeirsson24_interspeech', 'gay voice pipeline rating lgbtq ramification death capture fairness loss'], ['Adham Ibrahim, Shady Shehata, Ajinkya Kulkarni, Mukhtar Mohamed, Muhammad Abdul-Mageed', 'What Does it Take to Generalize SER Model Across Datasets? A Comprehensive Benchmark', 'ibrahim24_interspeech', 'emotional emotion oversampling explore imbalanced emphasizing thorough whisper speech-based evaluation'], ['Alexander Blatt, Aravind Krishnan, Dietrich Klakow', 'Joint vs Sequential Speaker-Role Detection and Automatic Speech Recognition for Air-traffic Control', 'blatt24_interspeech', 'srd atc architecture asr transcript atco natural-language traditional step preferable'], ['Weiqin Li, Peiji Yang, Yicheng Zhong, Yixuan Zhou, Zhisheng Wang, Zhiyong Wu, Xixin Wu, Helen Meng', 'Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models', 'li24na_interspeech', 'prosody speech diverse naturalness low-quality variation categorize uniformly human-like encounter'], ['Sneha Ray Barman, Shakuntala Mahanta, Neeraj Kumar Sharma', 'Deciphering Assamese Vowel Harmony with Featural InfoWaveGAN', 'raybarman24_interspeech', 'regressive long-distance iterative learning illicit grasping non-iterative insightful curated universality'], ['Orchid Chetia Phukan, Priyabrata Mallick, Swarup Ranjan Behera, Aalekhya Satya Narayani, Arun Balaji Buduru, Rajesh Sharma', 'Towards Multilingual Audio-Visual Question Answering', 'phukan24_interspeech', 'avqa benchmark datasets work existing replicating language suite prevents allocation'], ['Hongchen Wu, Jiwon Yun', 'Influences of Morphosyntax and Semantics on the Intonation of Mandarin Chinese Wh-indeterminates', 'wu24n_interspeech', 'morphosyntactic production faculty prosodic shaping interrogative clause convey speech interact'], ['Jinhyeok Yang, Junhyeok Lee, Hyeong-Seok Choi, Seunghoon Ji, Hyeongju Kim, Juheon Lee', 'DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance', 'yang24q_interspeech', 'tt control exceptional nuance diffusion phoneme-level replicate surpasses demo advancement'], ['Tianchi Liu, Lin Zhang, Rohan Kumar Das, Yi Ma, Ruijie Tao, Haizhou Li', 'How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio?', 'liu24m_interspeech', 'cm bona fide prioritize decision-making lay interpretability focus explains manipulating'], ['Tillmann Pistor, Adrian Leemann', 'Echoes of Implicit Bias Exploring Aesthetics and Social Meanings of Swiss German Dialect Features', 'pistor24_interspeech', 'bern zurich stereotypical aesthetic importance category stereotype single-word rater perception'], ['Aryan Chaudhary, Vinayak Abrol', 'QGAN: Low Footprint Quaternion Neural Vocoder for Speech Synthesis', 'chaudhary24b_interspeech', 'low-footprint vastly landscape model grown gans evolved compromising diffusion high-fidelity'], ['Edresson Casanova, Kelly Davis, Eren Gölge, Görkem Göknar, Iulian Gulea, Logan Hart, Aya Aljafari, Joshua Meyer, Reuben Morais, Samuel Olayemi, Julian Weber', 'XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model', 'casanova24_interspeech', 'zs-tts medium language voicebox vall-e resource cloning sota limiting proposing'], ['Nan Chen, Yonghe Wang, Feilong Bao', 'Sign Value Constraint Decomposition for Efficient 1-Bit Quantization of Speech Translation Tasks', 'chen24v_interspeech', 'quantized model matrix layer cost linear approximates distillation speech-to-text trainable'], ['Devang Kulshreshtha, Nikolaos Pappas, Brady Houston, Saket Dingliwal, Srikanth Ronanki', 'Sequential Editing for Lifelong Training of Speech Recognition Models', 'kulshreshtha24_interspeech', 'domain lll necessitate prior new asr fine-tuning access multi-accent inefficiency'], ['Vincenzo Norman Vitale, Loredana Schettino, Francesco Cutugno', 'Rich speech signal: exploring and exploiting end-to-e
11146nd automatic speech recognizersâ ability to model hesitation phenomena', 'vitale24_interspeech', 'decoder disrupting deepen disregarded procedural system prolongation conformer-based neglect acknowledged'], ['Anna Favaro, Tianyu Cao, Najim Dehak, Laureano Moro-Velazquez', 'Leveraging Universal Speech Representations for Detecting and Assessing the Severity of Mild Cognitive Impairment Across Languages', 'favaro24_interspeech', 'mci feature mmse taukadial cross-lingually language-agnostic mini-mental interpretable suitability cohort'], ['Zitha Sasindran, Harsha Yelchuri, T. V. Prabhakar', 'SeMaScore: A new evaluation metric for automatic speech recognition tasks', 'sasindran24_interspeech', 'bertscore serf segment-wise score atypical corresponds algorithm signal-to-noise scoring involving'], ['Bhasi K. C., Rajeev Rajan, Noumida A', 'Attention-augmented X-vectors for the Evaluation of Mimicked Speech Using Sparse Autoencoder-LSTM framework', 'kc24_interspeech', 'artist mimicking fed encoded later embeddings rank- mimicry competency lstm-based'], ['Vidar Freyr Gudmundsson, Keve Márton Gönczi, Malin Svensson Lundmark, Donna Erickson, Oliver Niebuhr', 'The MARRYS helmet: A new device for researching and training âjaw dancingâ', 'gudmundsson24_interspeech', 'portrait articulograph ema electromagnetic teaching motivation outline science illustrate analyzing'], ['Nikhil Jakhar, Sudhanshu Srivastava, Arun Baby', 'A Unified Approach to Multilingual Automatic Speech Recognition with Improved Language Identification for Indic Languages', 'jakhar24_interspeech', 'lid asr scalability der whisper diarization model language-specific low-resource enhancing'], ['Patrick Cormac English, John D. Kelleher, Julie Carson-Berndsen', 'Searching for Structure: Appraising the Organisation of Speech Features in wav2vec 2.0 Embeddings', 'english24_interspeech', 'within transformer organisational relationship encapsulate uncovering explainability model probing mining'], ['Danilo de Oliveira, Simon Welker, Julius Richter, Timo Gerkmann', "The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement", 'deoliveira24_interspeech', 'metric pesq model evaluation listening misleading detrimental imply instrumental used'], ['Liam Kelley, Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Yoshiaki Bando, Kazuyoshi Yoshii', 'RIR-in-a-Box: Estimating Room Acoustics from 3D Mesh Data through Shoebox Approximation', 'kelley24_interspeech', 'rirs rir latent differentiable code scene real estimator consistency physical'], ['Himanshu Maurya, Atli Sigurgeirsson', 'A Human-in-the-Loop Approach to Improving Cross-Text Prosody Transfer', 'maurya24_interspeech', 'reference hitl text rendition target prosodic utterance appropriate suffices closeness'], ['Themos Stafylakis, Anna Silnova, Johan Rohdin, OldÅich Plchot, Lukáš Burget', 'Challenging margin-based speaker embedding extractors by using the variational information bottleneck', 'stafylakis24_interspeech', 'loss margin logit principled angular merely softmax target deterministic cross-entropy'], ['Federico Lo Iacono, Valentina Colonna, Antonio Romano', 'Preservation, conservation and phonetic study of the voices of Italian poets: A study on the seven years of the VIP archive', 'loiacono24_interspeech', 'poetic cultural preserving oral crucial conserving inheritance fragile project culturally'], ['Si-Ioi Ng, Lingfeng Xu, Kimberly D. Mueller, Julie Liss, Visar Berisha', 'Segmental and Suprasegmental Speech Foundation Models for Classifying Cognitive Risk Factors: Evaluating Out-of-the-Box Performance', 'ng24_interspeech', 'trillsson clinical mci dementia precludes macro-f intraclass use-cases analysis challenged'], ['Miku Nishihara, Dan Wells, Korin Richmond, Aidan Pine', 'Low-dimensional Style Token Control for Hyperarticulated Speech Synthesis', 'nishihara24_interspeech', 'clear pca variation gsts gst dimension tt example space text-tospeech'], ['Janek Ebbers, François G. Germain, Gordon Wichern, Jonathan Le Roux', 'Sound Event Bounding Boxes', 'ebbers24_interspeech', 'extent presence frame-level confidence thresholding prediction posterior psds frame decouple'], ['Youssef Nafea, Shady Shehata, Zeerak Talat, Ahmed Aboeitta, Ahmed Sharshar, Preslav Nakov', 'AraOffence: Detecting Offensive Speech Across Dialects in Arabic Media', 'nafea24_interspeech', 'nlp labelled text image trail dialectical abuse under-represented content swahili'], ['Yuri Khokhlov, Tatiana Prisyach, Anton Mitrofanov, Dmitry Dutov, Igor Agafonov, Tatiana Timofeeva, Aleksei Romanenko, Maxim Korenevsky', 'Classification of Room Impulse Responses and its application for channel verification and diarization', 'khokhlov24_interspeech', 'rir embeddings rirs libricss acoustic reverb bearing experiment voxceleb reasonable'], ['Alessandro De Luca, Andrew Clark, Volker Dellwo', 'NumberLie: a game-based experiment to understand the acoustics of deception and truthfulness', 'deluca24_interspeech', 'player immediate truth game precise consequence backed trustworthiness lying tailor'], ['Rongshuai Wu, Debasish Ray Mohapatra, Sidney Fels', 'Modeling Vocal Tract Like Acoustic Tubes Using the Immersed Boundary Method', 'wu24o_interspeech', 'solver wave fdtd tube less grid geometry regular lagrangian finite-difference'], ['Johanna Cronenberg, Ioana Chitoran, Lori Lamel, Ioana Vasilescu', 'Crosslinguistic Comparison of Acoustic Variation in the Vowel Sequences /ia/ and /io/ in Four Romance Languages', 'cronenberg24_interspeech', 'hiatus di
11146phthong differ formant prefers respect account romanian mix inclusion'], ['Aleksei Gusev, Anastasia Avdeeva', 'Improvement Speaker Similarity for Zero-Shot Any-to-Any Voice Conversion of Whispered and Regular Speech', 'gusev24_interspeech', 'transfer generated unexplored domain lightweight truth streaming quality ground reconstruct'], ['Haibin Wu, Yuan Tseng, Hung-yi Lee', 'CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems', 'wu24p_interspeech', 'sota counter current detect synthesized unanswered empowers effectively misuse curate'], ['Joseph Coffey, Okko Räsänen, Camila Scaff, Alejandrina Cristia', 'The Difficulty and Importance of Estimating the Lower and Upper Bounds of Infant Speech Exposure', 'coffey24_interspeech', 'estimate unanimous year computational range plausibility language benchmarking discussing well-established'], ['John Murzaku, Adil Soubki, Owen Rambow', 'Multimodal Belief Prediction', 'murzaku24_interspeech', 'bert whisper audio corpus fine-tunes commitment text-only approached task text'], ['Dominik Wagner, Ilja Baumann, Korbinian Riedhammer, Tobias Bocklet', 'Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models', 'wagner24_interspeech', 'gating whisper transformer-based student impede necessitating mechanism tensor mitigation -bit'], ["Allahsera Tapo, Ãric Le Ferrand, Zoey Liu, Christopher Homan, Emily Prud'hommeaux", 'Leveraging Speech Data Diversity to Document Indigenous Heritage and Culture', 'tapo24_interspeech', 'asr history bambara mali mande corpus fieldwork culturally commonality archival'], ['Badr M. Abdullah, Mohammed Maqsood Shaik, Dietrich Klakow', 'Wave to Interlingua: Analyzing Representations of Multilingual Speech Transformers for Spoken Language Translation', 'abdullah24_interspeech', 'encoder shared probing across finding interpretability untranscribed speech-to-text trained transformer-based'], ['Mingshuai Liu, Zhuangqi Chen, Xiaopeng Yan, Yuanjun Lv, Xianjun Xia, Chuanzeng Huang, Yijian Xiao, Lei Xie', 'RaD-Net 2: A causal two-stage repairing and denoising speech enhancement network with knowledge distillation and complex axial self-attention', 'liu24n_interspeech', 'ssi icassp future upgraded dnsmos stage non-causal use challenge receptive'], ['Paula Andrea Pérez-Toro, Tomas Arias-Vergara, Philipp Klumpp, Tobias Weise, Maria Schuster, Elmar Noeth, Juan Rafael Orozco-Arroyave, Andreas Maier', 'Multilingual Speech and Language Analysis for the Assessment of Mild Cognitive Impairment: Outcomes from the Taukadial Challenge', 'pereztoro24_interspeech', 'language-dependent timing hallmark alzheimer dementia neurological uar english manifest decline'], ['Ivan Yakovlev, Rostislav Makarov, Andrei Balykin, Pavel Malov, Anton Okhotnikov, Nikita Torgashov', 'Reshape Dimensions Network for Speaker Recognition', 'yakovlev24_interspeech', 'redimnet block map reshaping aggregation versa vice representation facilitating scalable'], ['Matthew Maciejewski, Dominik Klement, Ruizhe Huang, Matthew Wiesner, Sanjeev Khudanpur', 'Evaluating the Santa Barbara Corpus: Challenges of the Breadth of Conversational Spoken Language', 'maciejewski24_interspeech', 'party speech problem matured overlooking dinner necessitates heterogeneity technology push'], ['Dominik Wagner, Sebastian P. Bayerl, Ilja Baumann, Elmar Noeth, Korbinian Riedhammer, Tobias Bocklet', 'Large Language Models for Dysfluency Detection in Stuttered Speech', 'wagner24b_interspeech', 'multi-label llm dysfluencies finetune stuttering inclusive non-lexical audio processor deployment'], ["Johannah O'Mahony, Catherine Lai, Ãva Székely", 'Well, what can you do with messy data? Exploring the prosody and pragmatic function of the discourse marker "well" with found data and speech synthesis', 'omahony24_interspeech', 'realisation prosodic conversational explore controllable synthesise unlabelled centroid untranscribed subtle'], ['Zhongweiyang Xu, Ali Aroudi, Ke Tan, Ashutosh Pandey, Jung-Suk Lee, Buye Xu, Francesco Nesta', 'FoVNet: Configurable Field-of-View Speech Enhancement with Low Computation and Distortion for Smart Glasses', 'xu24i_interspeech', 'multi-channel efficiency ultra-low
11146solution excels efficient computational designed needing within'], ['Ilja Baumann, Nicole Unger, Dominik Wagner, Korbinian Riedhammer, Tobias Bocklet', 'Automatic Evaluation of a Sentence Memory Test for Preschool Children', 'baumann24_interspeech', 'correctness recited early assessment syntactic capability semantic potential timely childhood'], ['Jinzuomu Zhong, Yang Li, Hui Huang, Korin Richmond, Jie Liu, Zhiba Su, Jing Guo, Benlai Tang, Fengjie Zhu', 'Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of Speech-Silence and Word-Punctuation', 'zhong24c_interspeech', 'prosodic text-speech stage labor-intensive boundary controllable controllability bearing inconsistent sota'], ['Ilja Baumann, Dominik Wagner, Maria Schuster, Korbinian Riedhammer, Elmar Noeth, Tobias Bocklet', 'Towards Self-Attention Understanding for Automatic Articulatory Processes Analysis in Cleft Lip and Palate Speech', 'baumann24b_interspeech', 'clp phoneme interpretability paving diagnostics anomaly multi-head classification long-range characteristic'], ['Pooneh Mousavi, Jarod Duret, Salah Zaiem, Luca Della Libera, Artem Ploujnikov, Cem Subakan, Mirco Ravanelli', 'How Should We Extract Discrete Audio Tokens from Self-Supervised Models?', 'mousavi24_interspeech', 'ssl semantic ideal configuration optimal layer identify attention benchmarked tokenization'], ['Dominika Woszczyk, Ranya Aloufi, Soteris Demetriou', 'Prosody-Driven Privacy-Preserving Dementia Detection', 'woszczyk24_interspeech', 'embeddings -score privacy preserving speaker limited-resource anonymize adresso adress identifiable'], ['Minh Nguyen, Toan Quoc Nguyen, Kishan KC, Zeyu Zhang, Thuy Vu', 'Reinforcement Learning from Answer Reranking Feedback for Retrieval-Augmented Answer Generation', 'nguyen24c_interspeech', 'odqa reward rag misaligned factual open-domain model human retrieving answering'], ['Gasser Elbanna, Zohreh Mostaani, Mathew Magimai.-Doss', 'Predicting Heart Activity from Speech using Data-driven and Knowledge-based features', 'elbanna24_interspeech', 'physiological self-supervised acoustic speaker-related underscore speech-related unexplored biological generalizability representation'], ['Jinuk Kwon, David Harwath, Debadatta Dash, Paul Ferrari, Jun Wang', 'Direct Speech Synthesis from Non-Invasive, Neuromagnetic Signals', 'kwon24_interspeech', 'brain neural meg bci neuroimaging magnetoencephalography invasive overt electrode mel-spectrograms'], ['Menglu Li, Xiao-Ping Zhang', 'Interpretable Temporal Class Activation Representation for Audio Spoofing Detection', 'li24oa_interspeech', 'interpretability model fostering t-dcf multi-label trust decision-making transparency bonafide localize'], ['Peter Mihajlik, Yan Meng, Mate S Kadar, Julian Linke, Barbara Schuppler, Katalin Mády', 'On Disfluency and Non-lexical Sound Labeling for End-to-end Automatic Speech Recognition', 'mihajlik24_interspeech', 'label filled pause grunt conversational delete decent backchannels asr disfluent'], ['David Looney, Nikolay D. Gaubitch', 'Robust spread spectrum speech watermarking using linear prediction and deep spectral shaping', 'looney24_interspeech', 'music signal deepfake centre date attack primarily classical implication call'], ['Ashutosh Pandey, Sanha Lee, Juan Azcarreta, Daniel Wong, Buye Xu', 'All Neural Low-latency Directional Speech Extraction', 'pandey24_interspeech', 'doa quickly model embeddings capability scenario frame abrupt hand-crafted grid'], ['Benazir Mumtaz, Miriam Butt', 'Urdu Alternative Questions: A Hat Pattern', 'mumtaz24_interspeech', 'altqs spacing contour realization german accent noting prolonged featuring focus'], ['Kevin Huang, Jack Goldberg, Louis Goldstein, Shrikanth Narayanan', 'Analysis of articulatory setting for L1 and L2 English speakers using MRI data', 'huang24i_interspeech', 'acquired articulation korea posture geographical positional united india china draw'], ['Kuang Yuan, Shuo Han, Swarun Kumar, Bhiksha Raj', 'DeWinder: Single-Channel Wind Noise Reduction using Ultrasound Sensing', 'yuan24_interspeech', 'doppler ultrasonic outdoor deep-learning mitigating characteristic airflow fuse qual
11146ity treat'], ['Mohammad Amaan Sayeed, Hanan Aldarmaki', 'Spoken Word2Vec: Learning Skipgram Embeddings from Speech', 'sayeed24_interspeech', 'encode distributional semantic semantics examine similarity resulting relatedness analogous phonetic'], ['Giulia Sanguedolce, Sophie Brook, Dragos C. Gruia, Patrick A. Naylor, Fatemeh Geranmayeh', 'When Whisper Listens to Aphasia: Advancing Robust Post-Stroke Speech Recognition', 'sanguedolce24_interspeech', 'aphasiabank generalisability intervention asr ai-based wer asrs stroke standardised versatile'], ['Sidi Yaya Arnaud Yarga, Sean U N Wood', 'Neuromorphic Keyword Spotting with Pulse Density Modulation MEMS Microphones', 'yarga24_interspeech', 'spiking device gsc energy kw command bio-inspired ssc snn stage'], ['Yuzhe Wang, Anna Favaro, Thomas Thebaud, Jesus Villalba, Najim Dehak, Laureano Moro-Velazquez', 'Exploring the Complementary Nature of Speech and Eye Movements for Profiling Neurological Disorders', 'wang24ka_interspeech', 'nd disease ocular parkinson differentiated search subject thief visual visit'], ['Amrutha Prasad, Srikanth Madikeri, Driss Khalil, Petr Motlicek, Christof Schuepbach', 'Speech and Language Recognition with Low-rank Adaptation of Pretrained Models', 'prasad24_interspeech', 'xls-r finetuning whisper drop connected fully resource constraint layer training'], ['Kwangyoun Kim, Suwon Shon, Yi-Te Hsu, Prashant Sridhar, Karen Livescu, Shinji Watanabe', 'Convolution-Augmented Parameter-Efficient Fine-Tuning for Speech Recognition', 'kim24s_interspeech', 'peft bottleneck lora low-rank adapter hubert fine-tune method numerous convolution'], ['Jonathan Him Nok Lee, Mark Liberman, Martin Salzmann', 'Do we EXPECT TO find phonetic traces for syntactic traces?', 'lee24l_interspeech', 'intervening contraction theory morpho-phonological regression lenition presence posited contradict multinomial'], ['Chaofei Fan, Jaimie M. Henderson, Chris Manning, Francis R. Willett', 'Towards a Quantitative Analysis of Coarticulation with a Phoneme-to-Articulatory Model', 'fan24c_interspeech', 'ema magnitude extent resistance phoneme comprehensively across sequence replicate trigger'], ['Angelo Ortiz Tandazo, Thomas Schatz, Thomas Hueber, Emmanuel Dupoux', 'Simulating articulatory trajectories with phonological feature interpolation', 'ortiztandazo24_interspeech', 'phonology generative perception-production correlation linear co-articulation biological pearson optimisation loop'], ['Tejes Srivastava, Jiatong Shi, William Chen, Shinji Watanabe', 'EFFUSE: Efficient Self-Supervised Feature Fusion for E2E ASR in Low Resource and Multilingual Scenarios', 'srivastava24_interspeech', 'ssl model fusing ml-superb parameter performance size average superb increase'], ['David Meyer, Eitan Abecassis, Clara Fernandez-Labrador, Christopher Schroers', 'RAST: A Reference-Audio Synchronization Tool for Dubbed Content', 'meyer24b_interspeech', 'translated disengagement sync intermittent defect detection misalignment viewer siamese issue'], ['Natalia Morozova, Guanghao You, Sabine Stoll, Adrian Bangerter', 'Measuring acoustic dissimilarity of hierarchical markers in task-oriented dialogue with MFCC-based dynamic time warping', 'morozova24_interspeech', 'transition horizontal vertical acoustically block interactants unfold navigating okay vertically'], ['Daniel Escobar-Grisales, Cristian David RÃos-Urrego, Ilja Baumann, Korbinian Riedhammer, Elmar Noeth, Tobias Bocklet, Adolfo M. Garcia, Juan Rafael Orozco-Arroyave', 'Itâs Time to Take Action: Acoustic Modeling of Motor Verbs to Detect Parkinsonâs Disease', 'escobargrisales24_interspeech', 'yielded representation pre-trained discrimination non-motor accuracy neurocognitive model well-established frame-by-frame'], ['Abderrahim Fathan, Xiaolin Zhu, Jahangir Alam', 'On the impact of several regularization techniques on label noise robustness of self-supervised speaker verification systems', 'fathan24_interspeech', 'pls sssv investigative loss mixup clustering-based pseudo-labels thorough effect smoothing'], ['Aravind Krishnan, Badr M. Abdullah, Dietric
11146h Klakow', 'On the Encoding of Gender in Transformer-based ASR Representations', 'krishnan24_interspeech', 'layer erasure concentration prospect uncover compromising explaining hubert utilization deeper'], ['Xianrui Zheng, Guangzhi Sun, Chao Zhang, Philip C. Woodland', 'SOT Triggered Neural Clustering for Speaker Attributed ASR', 'zheng24d_interspeech', 'sdnc diarisation eval cascaded assign ami system cpwer parallel label'], ['Ariëlle Reitsema, Chenxin Li, Leanne van Lambalgen, Laura Preining, Saskia Galindo Jong, Qing Yang, Xinyi Wen, Yiya Chen', 'Perceptual Learning in Lexical Tone: Phonetic Similarity vs. Phonological Categories', 'reitsema24_interspeech', 'contour rising pitch exposure interpretation recalibrate recalibration disambiguating listener segmentally'], ['Wonjune Kang, Deb Roy', 'Prompting Large Language Models with Audio for General-Purpose Speech Summarization', 'kang24d_interspeech', 'llm speech-text text reasoning framework processing summarize input cascade summary'], ['Zehua Kcriss Li, Meiying Melissa Chen, Yi Zhong, Pinxin Liu, Zhiyao Duan', 'GTR-Voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis', 'li24pa_interspeech', 'gtr actor professional voice framework dimension tt mastered lens tenseness'], ['Mostafa Shahin, Beena Ahmed', 'Phonological-Level Mispronunciation Detection and Diagnosis', 'shahin24_interspeech', 'mdd phoneme-level pronunciation diagnostic phoneme error false detect rate frr'], ['Tatsunari Takagi, Yukoh Wakabayashi, Atsunori Ogawa, Norihide Kitaoka', 'Text-only Domain Adaptation for CTC-based Speech Recognition through Substitution of Implicit Linguistic Information in the Search Space', 'takagi24_interspeech', 'ctc asr dra method japanese practicality english-language character-level accommodated model'], ['Rishi Jain, Bohan Yu, Peter Wu, Tejas Prabhune, Gopala Anumanchipalli', 'Multimodal Segmentation for Vocal Tract Modeling', 'jain24_interspeech', 'rt-mri articulator mri internal labeling video occluded label dataset -speaker'], ['Gowtham Premananth, Yashish M. Siriwardena, Philip Resnik, Sonia Bansal, Deanna L.Kelly, Carol Espy-Wilson', 'A Multimodal Framework for the Assessment of the Schizophrenia Spectrum', 'premananth24_interspeech', 'fusion weighted modality bi-modal unit -score gated bimodal unimodal symptom'], ['Orchid Chetia Phukan, Gautam Siddharth Kashyap, Arun Balaji Buduru, Rajesh Sharma', 'Are Paralinguistic Representations all that is needed for Speech Emotion Recognition?', 'phukan24b_interspeech', 'ptm ser sota trillsson ml-superb ptms superb fill facilitated attributed'], ['Justin Lovelace, Soham Ray, Kwangyoun Kim, Kilian Q. Weinberger, Felix Wu', 'Sample-Efficient Diffusion for Text-To-Speech Synthesis', 'lovelace24_interspeech', 'sesd less latent vall-e speech regime synthesizes auto-regressive modest impressive'], ['Tomas Arias-Vergara, Paula Andrea Pérez-Toro, Xiaofeng Liu, Fangxu Xing, Maureen Stone, Jiachen Zhuo, Jerry L. Prince, Maria Schuster, Elmar Noeth, Jonghye Woo, Andreas Maier', 'Contrastive Learning Approach for Assessment of Phonological Precision in Patients with Tongue Cancer Using MRI Data', 'ariasvergara24_interspeech', 'class clinical recognition assess high-resolution frame-wise unavailable synchronized magnetic application'], ['Manila Kodali, Sudarsana Reddy Kadiri, Paavo Alku', 'Fine-tuning of Pre-trained Models for Classification of Vocal Intensity Category from Speech Signals', 'kodali24_interspeech', 'regulate spl loud wav vec arbitrary amplitude scale label occasion'], ['Prad Kadambi, Tristan Mahr, Lucas Annear, Henry Nomeland, Julie Liss, Katherine Hustad, Visar Berisha', "How Does Alignment Error Affect Automated Pronunciation Scoring in Children's Speech?", 'kadambi24_interspeech', 'pllr deviation forced phoneme score manual computed effect magnified using'], ['Chenzi Xu, Jessica Wormald, Paul Foulkes, Philip Harrison, Vincent Hughes, Poppy Welch, Finnian Kelly, David van der Vloed', 'Voice quality in telephone speech: Comparing acoustic measures between VoIP telephone and high-quality recordings', 'xu24j_interspeech', 'cpp studio forensic condition recording harmonics-to-noise susceptible differentiation creaky breathy'], ['Yongyi Zang, Jiatong Shi, You Zhang, Ryuichi Yamamoto, Jionghao Han, Yuxun Tang, Shengyuan Xu, Wenxiao Zhao, Jing Guo, Tomoki Toda, Zhiyao Duan', 'CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection', 'zang24_interspeech', 'bonafide accessible vocal publicly hour licensing method necessitate datasets controllability'], ['Xi Liu, John H.L. Hansen', 'DNN-based monaural speech enhancement using alternate analysis windows for phase and magnitude modification', 'liu24o_interspeech', 'hanning window stft enhancing phase-aware chebyshev apollo fearless quefrency evolves'], ['Dena Mujtaba, Nihar R. Mahapatra, Megan Arney, J. Scott Yaruss, Caryn Herring, Jia Bin', 'Inclusive ASR for Disfluent Speech: Cascaded Large-Scale Self-Supervised Learning with Targeted Fine-Tuning and Data Augmentation', 'mujtaba24_interspeech', 'inclusivity involuntary enriches datasets stutter curated asrs pave dataset barrier'], ['May Pik Yu Chan, Jianjing Kuang', 'Pitch-driven adjustments in tongue positions: Insights from ultrasound imaging', 'chan24_interspeech', 'pitch adjust participant range resonance sing space higher semitone production'], ['Jiatong Shi, Shih-Heng Wang, William Chen, Martijn Bartelds, Vanya Bannihatti Kumar, Jinchuan Tian, Xuankai Chang, Dan Jurafsky, Karen Livescu, Hung-yi Lee, Shinji Watanabe', 'ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets', 'shi24g_interspeech', 'downstream ssl setup benchmark performance find asr shallow targeted treat'], ['Khai Le-Duc, Khai-Nguyen Nguyen, Long Vo-Dang, Truong-Son Hy', 'Real-time Speech Summarization for Medical Conversations', 'leduc24_interspeech', 'summary conversation doctor-patient deployable first collaboratively standpoint posing thirdly gold'], ['Jiatong Shi, Xutai Ma, Hirofumi Inaguma, Anna Sun, Shinji Watanabe', 'MMM: Multi-Layer Multi-Residual Multi-Stream Discrete Speech Representation from Self-supervised Learning Model', 'shi24h_interspeech', 'ssl unit on-par compatibility surpass resynthesis lag various k-means codec'], ['Hazim Bukhari, Soham Deshmukh, Hira Dhamyal, Bhiksha Raj, Rita Singh', 'SELM: Enhancing Speech Emotion Recognition for Out-of-Domain Scenarios', 'bukhari24_interspeech', 'ser ood ravdess formulation situation crema-d curated inspiration performance formulate'], ['Paul Best, Santiago Cuervo, Ricard Marxer', 'Transfer Learning from Whisper for Microscopic Intelligibility Prediction', 'best24_interspeech', 'macroscopic response deep model scale predict lexical speech-in-noise word-error-rate listener'], ['Irene Smith, Morgan Sonderegger, The Spade Consortium', 'Modelled Multivariate Overlap: A method for measuring vowel merger', 'smith24_interspeech', 'distribution tension empirical modelling univariate affinity bhattacharyya extraneous unbalanced measure'], ['Tejumade Afonja, Tobi Olatunji, Sew
11146ade Ogun, Naome A. Etori, Abraham Owodunni, Moshood Yekini', 'Performant ASR Models for Medical Entities in Accented Speech', 'afonja24_interspeech', 'clinical wer drug rigorously error posing stride healthcare accelerated safety'], ['Prakash Kumar, Ye Tian, Yongwan Lim, Sophia X. Cui, Christina Hagedorn, Dani Byrd, Uttam K. Sinha, Shrikanth Narayanan, Krishna S. Nayak', 'State-of-the-art speech production MRI protocol for new 0.55 Tesla scanners', 'kumar24b_interspeech', 'rt-mri imaging platform real-time tract blurring biofeedback vocal safe slice'], ['Yiwen Shao, Shi-Xiong Zhang, Dong Yu', 'RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios', 'shao24_interspeech', 'reflection wave asr all-neural overlooking rir hinders speaker overcoming multi-talker'], ['Margaret Kroll, Kelsey Kraus', 'Optimizing the role of human evaluation in LLM-based spoken document summarization systems', 'kroll24_interspeech', 'llm paradigm replicability bertscore human-in-the-loop abstractive rouge content trustworthiness ability'], ['Robin Netzorg, Alyssa Cote, Sumi Koshin, Klo Vivienne Garoute, Gopala Krishna Anumanchipalli', 'Speech After Gender: A Trans-Feminine Perspective on Next Steps for Speech Science and Technology', 'netzorg24_interspeech', 'voice speaker texture modification vocal fail notion categorical static identity'], ['Irina-Elena Veliche, Zhuangqun Huang, Vineeth Ayyat Kochaniyan, Fuchun Peng, Ozlem Kalinli, Michael L. Seltzer', 'Towards measuring fairness in speech recognition: Fair-Speech dataset', 'veliche24_interspeech', 'demographic asr ethnicity submit geographic self-reported saying across united untranscribed'], ['Yiwen Shao, Shi-Xiong Zhang, Yong Xu, Meng Yu, Dong Yu, Daniel Povey, Sanjeev Khudanpur', 'Multi-Channel Multi-Speaker ASR Using Target Speakerâs Solo Segment', 'shao24b_interspeech', 'solo-sf array microphone circumventing alimeeting voiceprint layout discerning formidable effective'], ['Eunice Akani, Frederic Bechet, Benoît Favre, Romain Gemignani', 'Unified Framework for Spoken Language Understanding and Summarization in Task-Based Human Dialog processing', 'akani24_interspeech', 'summary dialogue task-related decoda goal-oriented summarizing information concise multitask process'], ['Sewade Ogun, Abraham T. Owodunni, Tobi Olatunji, Eniola Alese, Babatunde Oladimeji, Tejumade Afonja, Kayode Olaleye, Naome A. Etori, Tosin Adewumi', '1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis', 'ogun24_interspeech', 'persona creation automated geography data-rich continent under-represented content accent like'], ['Minxue Niu, Mimansa Jaiswal, Emily Mower Provost', 'From Text to Emotion: Unveiling the Emotion Annotation Capabilities of LLMs', 'niu24d_interspeech', 'gpt- human model impact underestimate training potential assisting automating underscore'], ['Dawei Liang, Alice Zhang, David Harwath, Edison Thomaz', 'Improving Audio Classification with Low-Sampled Microphone Input: An Empirical Study Using Model Self-Distillation', 'liang24_interspeech', 'khz panns sampling mobile high-quality traction lower rate low-quality wearable'], ['Emily P. Ahn, Eleanor Chodroff, Myriam Lapierre, Gina-Anne Levow', 'The Use of Phone Categories and Cross-Language Modeling for Phone Alignment of Panãra', 'ahn24d_interspeech', 'forced granularity model pretrained language-specific low-resource acoustic language amazonian broadening'], ['Ioana Colgiu, Laura Spinu, Rajiv Rao, Yasaman Rafat', 'Bilingual Rhotic Production Patterns: A Generational Comparison of Spanish-English Bilingual Speakers in Canada', 'colgiu24_interspeech', 'cli trill late early drift approximant tap alveolar phonemic producing'], ['Nana Lin, Youxiang Zhu, Xiaohui Liang, John A. Batsis, Caroline Summerour', 'Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection', 'lin24l_interspeech', 'mci intent task fusion in-home subdomains read progressing dementia classification'], ['K R Prajwal, Triantafyllos Afouras, Andrew Zisserman', 'Speech Recognition Models are Strong Lip-readers', 'prajwal24_interspeech', 'lip-reading pre-trained asr lip video mapping perform model lr regime'], ['Yuxun Tang, Yuning Wu, Jiatong Shi, Qin Jin', 'SingOMD: Singing Oriented Multi-resolution Discrete Representation Construction from Speech Models', 'tang24c_interspeech', 'ssl generation discretizing discretized resampling necessitates wherein feature resynthesis encounter'], ['Vrushank Changawala, Frank Rudzicz', 'Whister: Using Whisperâs representations for Stuttering detection', 'changawala24_interspeech', 'split data dysfluency cross-corpora specifically generalizable surpassing segment -second frozen'], ['Krishna C. Puvvada, Piotr Å»elasko, He Huang, Oleksii Hrinchuk, Nithin Rao Koluguri, Kunal Dhawan, Somshubra Majumdar, Elena Rastorgueva, Zhehuai Chen, Vitaly L
11146avrukhin, Jagadeesh Balam, Boris Ginsburg', 'Less is More: Accurate Speech Recognition & Translation without Web-Scale Data', 'puvvada24_interspeech', 'model canary owsm training dynamic blending open-sourced state-of-the noise-robust whisper'], ['Junming Yuan, Ying Shi, LanTian Li, Dong Wang, Askar Hamdulla', 'Few-Shot Keyword Spotting from Mixed Speech', 'yuan24b_interspeech', 'pre-training fine-tuning solve keywords phase blended ssl-based effective struggle hubert'], ['Xintong Wang, Mingqian Shi, Ye Wang', 'Pitch-Aware RNN-T for Mandarin Chinese Mispronunciation Detection and Diagnosis', 'wang24la_interspeech', 'mdd stateless stage model pitch hubert scarcity acceptance two-stage solely'], ['Annika Heuser, Tyler Kendall, Miguel del Rio, Quinn McNamara, Nishchal Bhandari, Corey Miller, Migüel Jetté', 'Quantification of stylistic differences in human- and ASR-produced transcripts of African American English', 'heuser24_interspeech', 'aae verbatim transcriber asr human compounded underrepresented speech assess morphosyntactic'], ['James Tavernor, Yara El-Tawil, Emily Mower Provost', 'The Whole Is Bigger Than the Sum of Its Parts: Modeling Individual Annotators to Capture Emotional Variability', 'tavernor24_interspeech', 'emotion distribution label omits inter-annotator nuanced lose cross-corpus address nuance'], ['Pavan Kalyan, Preeti Rao, Preethi Jyothi, Pushpak Bhattacharyya', 'Emotion Arithmetic: Emotional Speech Synthesis via Weight Space Interpolation', 'kalyan24_interspeech', 'vector behaviour task idea negation generation steer subtracting steering model'], ['Rui Liu, Jiatian Xi, Ziyue Jiang, Haizhou Li', 'FluentEditor: Text-based Speech Editing by Considering Acoustic and Prosody Consistency', 'liu24p_interspeech', 'fluency tse edited region -lab consistent constraint original vctk segment'], ['Yiru Zhang, Linyu Yao, Qun Yang', 'OR-TSE: An Overlap-Robust Speaker Encoder for Target Speech Extraction', 'zhang24p_interspeech', 'tse reference overlap embeddings pre-enrolled disregarding mixture non-overlapping attentive mainstream'], ['Hyung Yong Kim, Byeong-Yeol Kim, Yunkyu Lim, Jihwan Park, Shukjae Choi, Yooncheol Ju, Jinseok Park, Youshin Lim, Seung Woo Yu, Hanbin Lee, Shinji Watanabe', 'Self-training ASR Guided by Unsupervised ASR Teacher', 'kim24t_interspeech', 'pseudo-target vec dataset labeled uasr pseudo-targets asr-related layer test-other test-clean'], ['Suyuan Liu, Molly Babel, Jian Zhu', 'A comparison of voice similarity through acoustics, human perception and deep neural network (DNN) speaker verification systems', 'liu24q_interspeech', 'listener perceptual judgment assessed acoustic made dis generated happens score'], ['Zuheyra Tokac, Jennifer Cole', 'Phonological Symmetry Does Not Predict Generalization of Perceptual Adaptation to Vowels', 'tokac24_interspeech', 'lowered inventory variant -vowel identification lasting boundary symmetrical assess biasing'], ['Jingyi Feng, Yusuke Yasuda, Tomoki Toda', 'Exploring the Robustness of Text-to-Speech Synthesis Based on Diffusion Probabilistic Models to Heavily Noisy Transcriptions', 'feng24d_interspeech', 'tt volume transcription data flow-based diffusion-based mitigating suffers autoregressive extremely'], ['Annika Heuser, Jianjing Kuang', 'Information-theoretic hypothesis generation of relative cue weighting for the voicing contrast', 'heuser24b_interspeech', 'sae context child gleaned perceptual different obstruent coda helpful validated'], ['Anton de la Fuente, Dan Jurafsky', 'A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models', 'delafuente24_interspeech', 'wav vec representation layer suprasegmental later contextual stress represent mainly'], ['Linhan Ma, Dake Guo, Kun Song, Yuepeng Jiang, Shuai Wang, Liumeng Xue, Weiming Xu, Huan Zhao, Binbin Zhang, Lei Xie', 'WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark', 'ma24d_interspeech', 'segment subset huggingface text-to-speech open-sourced audio-text multi-domain fair data eliminating'], ['Sri Harsha Dumpala, Katerina Dikaios, Abraham Nunes, Frank Rudzicz, Rudolf Uher, Sageev Oore', 'Self-Supervised Embeddings for Detecting Individual Symptoms of Depression', 'dumpala24b_interspeech', 'ssl severity predicting identifying small-sized depressive elucidate speech impacting learning'], ['Nan Chen, Yonghe Wang, Feilong Bao', 'Knowledge-Preserving Pluggable Modules for Multilingual Speech Translation Tasks', 'chen24w_interspeech', 'existing resampling retraining language regularization new performance cost model increase'], ['Oguzhan Baser, Kaan Kale, Sandeep P. Chinchali', 'SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures', 'baser24_interspeech', 'misinformation irreversible unauthorized strike mozilla datasets delicate deepfake defense authentication'], ['Xiaohan Shi, Xingfeng Li, Tomoki Toda', 'Multimodal Fusion of Music Theory-Inspired and Self-Supervised Representations for Improved Emotion Recognition', 'shi24i_interspeech', 'mer modality modality-specific deepen effectiveness comprehensively hinder challenge underscore handcrafted'], ['Max Morrison, Cameron Churchwell, Nathan Pruyne, Bryan Pardo', 'Fine-Grained and Interpretable Neural Speech Editing', 'morrison24_interspeech', 'disentangled volume attribute representation identity dialogue imperfection timbral pronunciation fixing'], ['Matthew McNeill, Rivka Levitan', 'Autoregressive cross-interlocutor attention scores meaningfully capture conversational dynamics', 'mcneill24_interspeech', 'dialogue entrainment organize historical human-human analyzes human-machine partner qual
11146itative history'], ['Yuning Wu, Chunlei Zhang, Jiatong Shi, Yuxun Tang, Shan Yang, Qin Jin', 'TokSing: Singing Voice Synthesis based on Discrete Tokens', 'wu24q_interspeech', 'melody svs token mel intermediate spectrogram offer selfsupervised witness discretization'], ['Viyazonuo Terhiija, Priyankoo Sarmah', 'Voiced and voiceless laterals in Angami', 'terhiija24_interspeech', 'distinction voicing delf cross-linguistically aspirated hnr exception context rare trait'], ['Linhan Ma, Xinfa Zhu, Yuanjun Lv, Zhichao Wang, Ziqian Wang, Wendi He, Hongbin Zhou, Lei Xie', 'Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy', 'ma24e_interspeech', 'training-inference content process multi-codebook mismatch prompt-based semantic similarity loss decoupling'], ['Jehyun Kyung, Serin Heo, Joon-Hyuk Chang', 'Enhancing Multimodal Emotion Recognition through ASR Error Compensation and LLM Fine-Tuning', 'kyung24_interspeech', 'mer asr-generated inaccuracy text cmt counteract blend system compromised nuance'], ['Slava Shechtman, Avihu Dekel', 'Low Bitrate High-Quality RVQGAN-based Discrete Speech Tokenizer', 'shechtman24_interspeech', 'tokenizers audio open-source reconstruction publicly token pcm speech-only tokenization bps'], ['Junghun Kim, Ka Hyun Park, Hoyoung Yoon, U Kang', 'Domain-Aware Data Selection for Speech Classification via Meta-Reweighting', 'kim24u_interspeech', 'domain instance source utilizing disorder target accurate softly specific given'], ['Jiali Cheng, Mohamed Elgaar, Nidhi Vakil, Hadi Amiri', 'CogniVoice: Multimodal and Multilingual Fusion Networks for Mild Cognitive Impairment Assessment from Spontaneous Speech', 'cheng24c_interspeech', 'mci mmse taukadial mini-mental point shortcut mitigates reliance decline rmse'], ['Shaowen Chen, Tomoki Toda', 'QHM-GAN: Neural Vocoder based on Quasi-Harmonic Modeling', 'chen24x_interspeech', 'qhm consumption vocoders speech quality network signal hifi-gan prominently black-box'], ['Tian-Hao Zhang, Xinyuan Qian, Feng Chen, Xu-Cheng Yin', 'Transmitted and Aggregated Self-Attention for Automatic Speech Recognition', 'zhang24q_interspeech', 'map attention layer transformer respectively information outstanding aishell- previous cer'], ['Bohan Li, Feiyu Shen, Yiwei Guo, Shuai Wang, Xie Chen, Kai Yu', 'On the Effectiveness of Acoustic BPE in Decoder-Only TTS', 'li24qa_interspeech', 'token slm speech setting semantic discretizing byte-pair libritts shorten favorable'], ['Tahir Javed, Janki Nawale, Sakshi Joshi, Eldho George, Kaushal Bhogale, Deovrat Mehendale, Mitesh M. Khapra', 'LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systems', 'javed24_interspeech', 'india diverse extempore north-east district accent sourced find existing terminology'], ['Alexis DeMaere, Nicole van Rootselaar, Fangfang Li, Robbin Gibb, Claudia L. R. Gonzalez', 'On the relationship between speech production and vocabulary size in 3-5 year olds', 'demaere24_interspeech', 'six-month multifaceted preschool complimentary null receptive versa vice sex comprehension'], ['Jens Heitkaemper, Joe Caroselli, Arun Narayanan, Nathan Howard', 'TfCleanformer: A streaming, array-agnostic, full- and sub-band modeling front-end for robust ASR', 'heitkaemper24_interspeech', 'enhancement upon non-causal agnostic multiple publication ablation multi-channel outperforming array'], ['Jaeuk Lee, Sohee Jang, Joon-Hyuk Chang', 'Neural ATSM: Fully Neural Network-based Adaptive Time-Scale Modification Using Sentence-Specific Dynamic Control', 'lee24m_interspeech', 'mfa phoneme sentence rate speaking networks-based scale tailoring phoneme-specific montreal'], ['Sara Ng, Gina-Anne Levow, Mari Ostendorf, Richard Wright', 'Investigating the Influence of Stance-Taking on Conversational Timing of Task-Oriented Speech', 'ng24b_interspeech', 'behavior stance turn-taking conversation northwest measurably pacific negotiation known speaker'], ['Darshan Prabhu, Yifan Peng, Preethi Jyothi, Shinji Watanabe', 'MULTI-CONVFORMER: Extending Conformer with Multiple Convolution Kernels', 'prabhu24_interspeech', 'module variant reexamined modelling e-branchformer local conformers rival eff
11146icient asr'], ['Yuan Gao, Hao Shi, Chenhui Chu, Tatsuya Kawahara', 'Speech Emotion Recognition with Multi-level Acoustic and Semantic Information Extraction and Interaction', 'gao24f_interspeech', 'ser extractor emotional asr system embeddings learn module existing feature'], ['Junwen Duan, Fangyuan Wei, Hong-Dong Li, Jin Liu', 'Pre-trained Feature Fusion and Matching for Mild Cognitive Impairment Detection', 'duan24_interspeech', 'mci language-agnostic diagnosis challenge taukadial delaying diagnose expressivity chinese-english progression'], ['Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo', 'FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation', 'kaneko24_interspeech', 'multi-step inference reconsidering any-to-any one-shot dozen reverse performance high attracted'], ['Sangwon Ryu, Heejin Do, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok', 'Key-Element-Informed sLLM Tuning for Document Summarization', 'ryu24_interspeech', 'llm proprietary key relevance high-quality element instructs fee hallucination low'], ['Haechan Kim, Junho Myung, Seoyoung Kim, Sungpah Lee, Dongyeop Kang, Juho Kim', 'LearnerVoice: A Dataset of Non-Native English Learnersâ Spontaneous Speech', 'kim24v_interspeech', 'ungrammatical vanilla disfluency consisting expression learner self-repairs datasets transcription attributable'], ['Kalvin Chang, Yi-Hui Chou, Jiatong Shi, Hsuan-Ming Chen, Nicole Holliday, Odette Scharenborg, David R. Mortensen', 'Self-supervised Speech Representations Still Struggle with African American Vernacular English', 'chang24d_interspeech', 'aave ssl variety mae asr gap model welldocumented marginalized xls-r'], ['Kaushal Santosh Bhogale, Deovrat Mehendale, Niharika Parasa, Sathish Kumar Reddy G, Tahir Javed, Pratyush Kumar, Mitesh M. Khapra', 'Empowering Low-Resource Language ASR via Large-Scale Pseudo Labeling', 'bhogale24_interspeech', 'pseudo-labeling benchmark youtube multiple labeled pseudo-labeled data existing evaluator augmenting'], ['Sai Harshitha Aluru, Jhansi Mallela, Chiranjeevi Yarra', 'Post-Net: A linguistically inspired sequence-dependent transformed neural architecture for automatic syllable stress detection', 'aluru24_interspeech', 'sota dependency supervised unsupervised isle existing model word syllable-level time-delay'], ['Conor Atkins, Ian Wood, Mohamed Ali Kaafar, Hassan Asghar, Nardine Basta, Michal Kepkowski', 'ConvoCache: Smart Re-Use of Chatbot Responses', 'atkins24_interspeech', 'prefetching coherence find prompt latency generative reuses chatbots caching reduce'], ['Liisa Rätsep, Rasmus Lellep, Mark Fishel', 'Enabling Conversational Speech Synthesis using Noisy Spontaneous Data', 'ratsep24_interspeech', 'lack stylistically read style text-to-speech datasets sample multi-style estonian compromise'], ['Jhansi Mallela, Sai Harshitha Aluru, Chiranjeevi Yarra', 'A comparative analysis of sequential models that integrate syllable dependency for automatic syllable stress detection', 'mallela24_interspeech', 'grus non-sequential stress-related overlook isle operated sequence lstms rnns identifies'], ['Yuanjun Lv, Hai Li, Ying Yan, Junhui Liu, Danming Xie, Lei Xie', 'FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter', 'lv24_interspeech', 'apnet initialization inference speed amplitude parameter pursuing checkpoint streamlined mitigates'], ['Jiayan Lin, Shenghui Lu, Hukai Huang, Wenhao Guan, Binbin Xu, Hui Bu, Qingyang Hong, Lin Li', 'MinSpeech: A Corpus of Southern Min Dialect for Automatic Speech Recognition', 'lin24m_interspeech', 'hour hokkien diversely sourced encompassing audio hubert kaldi conformer cultural'], ['Chetan Sharma, Vaishnavi Chandwanshi, Prasanta Kumar Ghosh', 'A comparative study of the impact of voiceless alveolar and palato-alveolar sibilants in English on lip aperture and protrusion during VCV production', 'sharma24_interspeech', 'sibilant case usc change rounding higher vowel classification displacement irrespective'], ['Srija Anand, Praveen Srinivasa Varadhan, Ashwin Sankar, Giri Raju, Mitesh M. Khapra', 'Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies', 'anand24_interspeech', 'oov tamil hindi word benchmark containing code-mixing economically vocabulary artist'], ['Changli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Jun Zhang, Lu Lu, Zejun Ma, Yuxuan Wang, Chao Zhang', 'Can Large Language Models Understand Spatial Audio?', 'tang24d_interspeech', 'llm fsr lse ssl amidst inferential llm-based via paving mae'], ['Praveen Srinivasa Varadhan, Ashwin Sankar, Giri Raju, Mitesh M Khapra', 'Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings', 'srinivasavaradhan24_interspeech', 'neutral hour emotion data expressiveness prioritizing ekman assamese mushra resource-constrained'], ['Haotian Tan, Sakriani Sakti', 'Contrastive Feedback Mechanism for Simultaneous Speech Translation', 'tan24b_interspeech', 'sst cfm policy unstable prediction decision delaying overlook must-c undesired'], ['Marvin Tammen, Tsubasa Ochiai, Marc Delcroix, Tomohiro N
11146akatani, Shoko Araki, Simon Doclo', 'Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers', 'tammen24_interspeech', 'asa module tuning manual transform-average-concatenate microphone aggregator channel necessitating mask-based'], ['Yi Lu, Yuankun Xie, Ruibo Fu, Zhengqi Wen, Jianhua Tao, Zhiyong Wang, Xin Qi, Xuefei Liu, Yongwei Li, Yukun Liu, Xiaopeng Wang, Shuchen Shi', 'Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio', 'lu24f_interspeech', 'generation vocoder add codec neural process waveform multi-step skipping final'], ['Darshan Prabhu, Abhishek Gupta, Omkar Nitsure, Preethi Jyothi, Sriram Ganapathy', 'Improving Self-supervised Pre-training using Accent-Specific Codebooks', 'prabhu24b_interspeech', 'accent asr mozilla seldom invariance finetuning learnable learning trainable refined'], ['Mohamed Osman, Daniel Z. Kaplan, Tamer Nadeem', 'SER Evals: In-domain and Out-of-domain benchmarking for speech emotion recognition', 'osman24_interspeech', 'benchmark ssl model generalization diverse logit stride assess generalizable advent'], ['Socrates Vakirtzian, Chara Tsoukala, Stavros Bompolas, Katerina Mouzou, Vivian Stamou, Georgios Paraskevopoulos, Antonios Dimakis, Stella Markantonatou, Angela Ralli, Antonios Anastasopoulos', 'Speech Recognition for Greek Dialects: A Challenging Benchmark', 'vakirtzian24_interspeech', 'variety language overlooked encompassing non-standard asr convention arising impressive cross-lingual'], ['Vivian G. Li', 'In search of structure and correspondence in intra-speaker trial-to-trial variability', 'li24ra_interspeech', 'repetition point measurement position regulated distribution regulation study actively distributional'], ['Martino Ciaperoni, Athanasios Katsamanis, Aristides Gionis, Panagiotis Karras', 'Beam-search SIEVE for low-memory speech recognition', 'ciaperoni24_interspeech', 'beam memory overhead eliminates runtime search via linearly bottleneck viterbi'], ['Joonas Kalda, Tanel Alumae, Martin Lebourdais, Hervé Bredin, Séverin Baroudi, Ricard Marxer', 'TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024', 'kalda24_interspeech', 'track ensemble team submission challenge separation embedding vbx pyannote ahc'], ['Zhenxiong Tan, Xinyin Ma, Gongfan Fang, Xinchao Wang', 'LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis', 'tan24c_interspeech', 'clip -second attention latent longer tta complicates diffusion-based model designated'], ['Tianhao Wang, Lantian Li, Dong Wang', 'SE/BN Adapter: Parametric Efficient Domain Adaptation for Speaker Recognition', 'wang24ma_interspeech', 'fine-tuning pre-trained well-optimized inefficiency competes cn-celeb freezing ample squeeze-and-excitation inspiration'], ['Zhenyu Zhou, Shibiao Xu, Shi Yin, Lantian Li, Dong Wang', 'A Comprehensive Investigation on Speaker Augmentation for Speaker Recognition', 'zhou24f_interspeech', 'vtlp perturbation potential hinting delve cn-celeb new pivotal underscore proficient'], ['Vrunda N. Sukhadia, Shammur Absar Chowdhury', 'Childrenâs Speech Recognition through Discrete Token Enhancement', 'sukhadia24_interspeech', 'privacy single-view data multi-view asr degrading transforming scarcity low-resource approximate'], ['Dehua Tao, Tan Lee, Harold Chui, Sarah Luk', 'Learning Representation of Therapist Empathy in Counseling Conversation Using Siamese Hierarchical Attention Network', 'tao24b_interspeech', 'embeddings contrastive rating encoder turn learn loss two-level positively subjectively'], ['Marianne de Heer Kloots, Willem Zuidema', 'Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0', 'deheerkloots24_interspeech', 'bias controlled stimulus phonotactically individual amplified sound unit localize embed'], ['Ajinkya Kulkarni, Atharva Kulkarni, Miguel Couceiro, Isabel Trancoso', 'Unveiling Biases while Embracing Sustainability: Assessing the Dual Challenges of Automatic Speech Recognition Systems', 'kulkarni24_interspeech', 'asr bias carbon mm massively sota consumption emission offering whisper'], ['Franziska Braun, Sebastian P. Bayerl, Florian Hönig, Hartmut Lehfeld, Thomas Hillemacher, Tobias Bocklet, Korbinian Riedhammer', 'Infusing Acoustic Pause Context into Text-Based Dementia Assessment', 'braun24_interspeech', 'cognitive impairment test biomarker exclusion alzheimer cross-attention mild non-invasive alongside'], ['Xiaolou Li, Zehua Liu, Chen Chen, Lantian Li, Li Guo, Dong Wang', 'Zero-Shot Fake Video Detection by Audio-Visual Consistency', 'li24ta_interspeech', 'genuine audio the-art delineated state-of vsr content one-class anchored advocated'], ['Heejin Do, Wonjun Lee, Gary Geunbae Lee', 'Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment', 'do24_interspeech', 'tailor non-linearly speechocean error-rate hint interpolating suit enriched imbalance mispronunciation'], ['Ashish Mittal, Darshan Prabhu, Sunita Sarawagi, Preethi Jyothi', 'SALSA: Speedy ASR-LLM Synchronous Aggregation', 'mittal24_interspeech', 'llm decoder asr coupling low-resource mismatch tokenizers layer harnessing fleurs'], ['Takuma Okamoto, Yamato Ohtani, Sota Shimizu, Tomoki Toda, Hisashi Kawai', 'Challenge of Singing Voice Synthesis Using Only Text-To-Speech Corpus With FIRNet Source-Filter Neural Vocoder', 'okamoto24_interspeech', 'svs tt phoneme shift duration input prototyped hifi-gan acoustic lyric'], ['Yuepeng Jiang, Tao Li, Fengyu Yang, Lei Xie, Meng Meng, Yujun Wang', 'Towards Expressive Zero-Shot Speech Synthesis with Hierarchical Prosody Modeling', 'jiang24d_interspeech', 'timbre expressiveness global model naturalness synthesized adaptor introduce diffusion hierarchically'], ['Chen Chen, Zehua Liu, Xiaolou Li, Lantian Li, Dong Wang', 'CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge', 'chen24y_interspeech', 'vsr single-speaker
11146cnceleb summarises encompassing comprehensively task registered org probe'], ['Joyshree Chakraborty, Leena Dihingia, Priyankoo Sarmah, Rohit Sinha', 'On Comparing Time- and Frequency-Domain Rhythm Measures in Classifying Assamese Dialects', 'chakraborty24_interspeech', 'quot assam district amplitude-modulated wind variety sun quadratic domain comprise'], ['Rui Liu, Zening Ma', 'Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge', 'liu24r_interspeech', 'emotion masking speech-emotion -lab prior npc overlook emotion-related neglecting prevailing'], ['Vasista Sai Lodagala, Abhishek Biswas, Shoutrik Das, Jordan F, S Umesh', 'All Ears: Building Self-Supervised Learning based ASR models for Indian Languages at scale', 'lodagala24_interspeech', 'ssl downstream benchmark speech signifies out-perform curate abundance superb pre-train'], ['Yo-Han Park, Wencke Liermann, Yong-Seok Choi, Seung Hi Kim, Jeong-Uk Bang, Seung Yun, Kong Joo Lee', 'Backchannel prediction, based on who, when and what', 'park24b_interspeech', 'talk counseling backchanneling conversation model information backchannels interpersonal piece amp'], ['Haoqin Sun, Shiwan Zhao, Xiangyu Kong, Xuechen Wang, Hui Wang, Jiaming Zhou, Yong Qin', 'Iterative Prototype Refinement for Ambiguous Speech Emotion Recognition', 'sun24e_interspeech', 'ipr label ser precise ambiguity subtlety daunting reinforcing urgent proving'], ['Bao Thang Ta, Minh Tu Le, Van Hai Do, Huynh Thi Thanh Binh', 'Enhancing No-Reference Speech Quality Assessment with Pairwise, Triplet Ranking Losses, and ASR Pretraining', 'ta24_interspeech', 'sqa mse sample distinction relative nisqa symmetrically enforcing garnered among'], ['Kumar Neelabh, Vishnu Sreekumar', 'From Sound to Meaning in the Auditory Cortex: A Neuronal Representation and Classification Analysis', 'neelabh24_interspeech', 'semantic category understood informative neural acoustic repertoire vocalization incoming listened'], ['Roland Hartanto, Sakriani Sakti, Koichi Shinoda', 'MSDET: Multitask Speaker Separation and Direction-of-Arrival Estimation Training', 'hartanto24_interspeech', 'location sms-wsj location-based estoi si-sdr point azimuth doa permutation angle'], ['Bao Thang Ta, Van Hai Do, Huynh Thi Thanh Binh', 'Enhancing Non-Matching Reference Speech Quality Assessment through Dynamic Weight Adaptation', 'ta24b_interspeech', 'fixed rigidly pristine roll nisqa sqa training assigns multitask accommodate'], ['Bonian Jia, Huiyao Chen, Yueheng Sun, Meishan Zhang, Min Zhang', 'LLM-Driven Multimodal Opinion Expression Identification', 'jia24_interspeech', 'oei dataset text subtlety underlining encompass delivering depression mirror advancing'], ['Takayuki Arai, Ryohei Suzuki, Chandler Earp, Shinya Tsuji, Keiko Ochi', 'Production of phrases by mechanical models of the human vocal tract', 'arai24_interspeech', 'cam model umeda rotating movable successfully pipe japanese three-tube morning'], ['Vishal Gourav, Ankit Tyagi, Phanindra Mankale', 'Faster Vocoder: a multi threading approach to achieve low latency during TTS Inference', 'gourav24_interspeech', 'cpl customer time fast text get service processing buy ssml'], ['Aanchan Mohan, Monideep Chakraborti, Katelyn Eng, Nailia Kushaeva, Mirjana Prpa, Jordan Lewis, Tianyi Zhang, Vince Geisler, Carol Geisler', 'A powerful and modern AAC composition tool for impaired speakers', 'mohan24_interspeech', 'message contextually software empowering large-language relevant communication augmentative authenticity able'], ['Grzegorz P. Mika, Konrad Zieli´nski, PaweÅ Cyrta, Marek Grzelec', 'VoxFlow AI: wearable voice converter for atypical speech', 'mika24_interspeech', 'interaction loudspeaker neurological tell amp demonstration real-life daily usability lie'], ['Sai Akarsh, Vamshiraghusimha Narasinga, Anil Kumar Vuppala', 'Stress transfer in speech-to-speech machine translation', 'akarsh24_interspeech', 'file speech inclusivity diminishing content sector hindering give monotonous reproducing'], ['Takuma Okamoto, Yamato Ohtani, Hisashi Kawai', 'Mobile PresenTra: NICT fast neural text-to-speech system on smartphones with incremental inference of MS-FC-HiFi-GAN for law-latency synthesis', 'okamoto24b_interspeech', 'vocoder smartphone high-fidelity transformer encoder decoder prototyped convnext attendee low-latency'], ['Alex Peiró-Lilja, José Giraldo, Martà Llopart-Font, Carme Armentano-Oller, Baybars Külebi, Mireia Farrús', 'Multi-speaker and multi-dialectal Catalan TTS models for video gaming', 'peirolilja24_interspeech', 'multi-accent demo game exported export unity reply architecture reproduced execution'], ['Juliana Francis, Ãva Székely, Joakim Gustafson', 'ConnecTone: a modular AAC system prototype with contextual generative text prediction and style-adaptive conversational TTS', 'francis24_interspeech', 'implement testing transformative adjustable augmentative anticipate technology language context-sensitive delivery'], ['Mahdin Rohmatillah, Bryan Gautama Ngo, Willianto Sulaiman, Po-Chuan Chen, Jen-Tzung Chien', 'Reliable dialogue system for facilitating student-counselor communication', 'rohmatillah24_interspeech', 'counselor student mental waiting health history period university dashboard in-person'], ['Yashwardhan Chaudhuri, Paridhi Mundra, Arnesh Batra, Orchid Chetia Phukan, Arun Balaji Buduru', 'ASGIR: audio spectrogram transformer guided classification and information retrieval for birds', 'chaudhuri24_interspeech', 'bird ecological sound habitat conservation wikipedia pivotal localize geographical judging'], ['Devyani Koshal, Orchid Chetia Phukan, Sarthak Jain, Arun Balaji Buduru, Rajesh Sharma', 'PERSONA: an application for emotion recognition, gender recognition and age estimation', 'koshal24_interspeech', 'ptm task obviates model stride concurrently deploying less comparatively learning'], ['Kesavaraj V, Charan Devarkonda, Vamshiraghusimha Narasinga, Anil Kumar Vuppala', 'Custom wake word detection', 'v24_interspeech', 'keyword open-vocabulary audio-text text embedding personalizing suffered preventing knowledge audio'], ['Song Chen, Mandar Gogate, Kia Dashtipour, Jasper Kirton-Wingate, Adeel Hussain, Faiyaz Doctor, Tughrul Arslan, Amir Hussain', 'Edged based audio-visual speech enhancement demonstrator', 'chen24z_interspeech', 'hearing aid customizing phone noisy anticipate assistive smartphone healthcare advancing'], ['Arif Reza Anway, Bryony Buck, Mandar Gogate, Kia Dashtipour, Michael Akeroyd, Amir Hussain', 'Real-Time Gaze-directed speech enhancement for audio-visual hearing-aids', 'anway24_interspeech', 'avse gaze eye nose estimation angle pose enhancing head hearing'], ['Abhishek Kumar, Srikanth Konjeti, Jithendra Vepa', 'Detection of background agents speech in contact centers', 'kumar24c_interspeech', 'conversation call inadvertently unintended utilise nearby mitigating proximity security quality'], ['Sarthak Jain, Orchid Chetia Phukan, Arun Balaji Buduru, Rajesh Sharma', 'The reasonable effectiveness of speaker embeddings for violence detection', 'jain24b_interspeech', 'avd ssl model sota ptms recognition harm preventing hinder environment'], ['Giovanni Morrone, Enrico Zovato, Fabio Brugnara, Enrico Sartori, Leonardo Badino', 'A toolkit for joint speaker diarization and identification with application to speaker-attributed ASR', 'morrone24_interspeech', 'configuration use-case institutional analytics speaker-related multiple registered user-friendly web-based modular'], ['Leonie Schade, Nico Dallmann, Olcay Tük, Stefan Lazarov, Petra Wagner', 'Understanding âunderstandingâ: presenting a richly annotated multimodal corpus of dyadic interaction', 'schade24_interspeech', 'annotation non-verbal explanation behaviour past modality gaze explaining several level'], ['Joao Vitor Possamai de Menezes, Arne-Lukas Fietkau, Tom Diener, Steffen Kurb
11146is, Peter Birkholz', 'A demonstrator for articulation-based command word recognition', 'possamaidemenezes24_interspeech', 'software classification device record recording measuring operating articulation system single'], ['Nigel G. Ward, Andres Segura', 'Pragmatically similar utterance finder demonstration', 'ward24b_interspeech', 'similarity participant retrieves listens letting viewer model prospect hear identifies'], ['Elena Ryumina, Dmitry Ryumin, Alexey Karpov', 'OCEAN-AI: open multimodal framework for personality traits assessment and HR-processes automatization', 'ryumina24_interspeech', 'pta module behaving responsibility siamese thinking feeling including automate human'], ['Paridhi Mundra, Manik Sharma, Yashwardhan Chaudhuri, Orchid Chetia Phukan, Arun Balaji Buduru', 'VoxMed: one-step respiratory disease classifier using digital stethoscope sounds', 'mundra24_interspeech', 'patient github classify icbhi ast portugal greece illness recording repository'], ['Sarthak Sharma, Orchid Chetia Phukan, Drishti Singh, Arun Balaji Buduru, Rajesh Sharma', 'AVR: synergizing foundation models for audio-visual humor detection', 'sharma24b_interspeech', 'textual reliance asr circumvents hinge lean necessitating centered intricate eliminating'], ['Harm Lameris, Joakim Gustafson, Ãva Székely', 'CreakVC: a voice conversion tool for modulating creaky voice', 'lameris24_interspeech', 'one-shot creak phonation representation level plotting human-in-the-loop cue finetuned modulate'], ['Yu-Sheng Tsao, Yung-Chang Hsu, Jiun-Ting Li, Siang-Hong Weng, Tien-Hong Lo, Berlin Chen', 'EZTalking: English assessment platform for teachers and students', 'tsao24_interspeech', 'feedback capt learning exercise pronunciation streamlines portfolio mock ai-powered empowers'], ['Bramhendra Koilakuntla, Prajesh Rana, Paras Ahuja, Srikanth Konjeti, Jithendra Vepa', 'Leveraging large language models for post-transcription correction in contact centers', 'koilakuntla24_interspeech', 'anchor downstream context brand correct compounded skilled transcription analytics pinpoint'], ['Dmitrii Obukhov, Marcel de Korte, Andrey Adaschik', 'ATTEST: an analytics tool for the testing and evaluation of speech technologies', 'obukhov24_interspeech', 'metric released powerful framework acknowledging need user-friendly alongside encourage large'], ['Margot Masson, Erfan A. Shams, Iona Gessinger, Julie Carson-Berndsen', 'PhoneViz: exploring alignments at a glance', 'masson24_interspeech', 'phone spanish-accented chart substituted showcase helping user ipa phonetic concrete'], ['Clément Pages, Hervé Bredin', 'Gryannote open-source speaker diarization labeling tool', 'pages24_interspeech', 'pyannote pipeline export ecosystem upload hyper-parameters customize visualize component custom'], ['Kai Liu, Ziqing Du, Zhou Huan, Xucheng Wan, Naijun Zheng', 'Real-time scheme for rapid extraction of speaker embeddings in challenging recording conditions', 'liu24s_interspeech', 'speaker-related enrollment target task embedding pristine three-stage realm compromising non-target'], ['Meenakshi Sirigiraju, Arjun Rajasekar, Abhishikth Meejuri, Chiranjeevi Yarra', 'IIITH Ucchar e-Sudharak: an automatic English pronunciation corrector for school-going children with a teacher in the loop', 'sirigiraju24_interspeech', 'tool skill practice student word-level gap sentence language catering empowers'], ['Boon Peng Yap, Kok Liang Tan, Zhenghao Li, Rong Tong', 'Speech enabled visual acuity test', 'yap24_interspeech', 'user posture eye system self-paced sight communicates automatically assess private'], ['Mayuko Aiba, Daisuke Saito, Nobuaki Minematsu', 'A ChatGPT-based oral Q&A practice system for first-time student participants in international conferences', 'aiba24_interspeech', 'question chatgpt configuration affirmed generation reference upload uploaded orally practicing'], ['Szu-Yu Chen, Tien-Hong Lo, Yao-Ting Sung, Ching-Yu Tseng, Berlin Chen', 'TEEMI: a speaking practice tool for L2 English learners', 'chen24aa_interspeech', 'foreign user automated assessment globalization surpassed laptop tablet language english-speaking'], ['Karthik Venkat Sridaran, Raja Praveen, Reuben T Varghese, Ajish K Abraham, Shankar R, Winnie Rachel Cheri
11146an', 'Visual scene display application for augmentative and alternative communication', 'sridaran24_interspeech', 'aac individual development ability language enhance icon webpage ensured limited'], ['Ikuyo Masuda-Katsuse, Ayako Shirose', 'CALL system using pitch-accent feature representations reflecting listenersâ subjective adequacy', 'masudakatsuse24_interspeech', 'quantitatively accepted implement evaluating learner japanese accent native automatically pitch'], ['Jonathan L Preston, Nina R Benway, Nathan Prestopnik, Nathan Preston', 'The speech motor chaining web app for speech motor learning', 'preston24_interspeech', 'principle invoke apps design computerized underlie illustrates therapy highlighting game'], ['Charlotte Yoder, Karrie Karahalios, Mark Hasegawa-Johnson, Shreyansh Agrawal', 'Visualization for improving foreign language pronunciation', 'yoder24_interspeech', 'chart vowel coherently seldom calibrated tutorial execution learning page emphasized'], ['Nhan Phan, Anna von Zansen, Maria Kautonen, Tamás Grósz, Mikko Kurimo', 'CaptainA self-study mobile app for practising speaking: task completion assessment and feedback with generative AI', 'phan24b_interspeech', 'language learner finnish providing picture-based automatic visual nlg grading asa'], ['Mohd Mujtaba Akhtar, Girish, Orchid Chetia Phukan, Muskaan Singh', 'NeuRO: an application for code-switched autism detection in children', 'akhtar24_interspeech', 'asd individual disorder conversation communication code-switch posing challenge repetitive code-switching'], ['Orchid Chetia Phukan, Sarthak Jain, Shubham Singh, Muskaan Singh, Arun Balaji Buduru, Rajesh Sharma', 'ComFeAT: combination of neural and spectral features for improved depression detection', 'phukan24c_interspeech', 'ptms extracted sota decline previous trained individually speech-based paralinguistic cnn'], ['Isabel Trancoso', 'Towards Responsible Speech Processing', 'trancoso24_interspeech', 'pillar sustainability fairness explainability urgent uniquely nonetheless attempting inform inclusion'], ['Shoko Araki', 'Frontier of Frontend for Conversational Speech Processing', 'araki24_interspeech', 'conversation technology distant diarization evolution decade talk progress microphone enhancement'], ['Elmar Noeth', 'Analysis of Pathological Speech â Pitfalls along the Way', 'noeth24_interspeech', 'congenital aspect biomarker explainability defect less various privacy disease motivation'], ['Barbara Tillmann', 'Perception of music and speech: Focus on rhythm processing', 'tillmann24_interspeech', 'rhythmic research language cognitive disorder early revealed dyslexia hypothesis neuroscience']], 11147 stateSave: true, 11148 columnDefs: [ 11149 { targets: [0], 11150 className: 'dt-left', 11151 "mRender": function (data, type, full) { 11152 return '<a class="w3-text" href="' + full[2] + '.html' + '">' + full[1] + '<br><span class="w3-text w3-text-theme">' + full[0] + '</span></a>'; 11153 } 11154 }, 11155 { targets: [1, 2, 3], 11156 visible: false, 11157 }, 11158 ], 11159 "lengthMenu": [7, 10, 20, 50, 100, 200, 500], 11160 "pageLength": 50, 11161 "order": [[ 0, 'asc' ]], 11162 scrollY: '60vh', 11163 "dom": '<"top"l>rft<"bottom"ip><"clear">', 11164 "pagingType": "full_numbers", 11165 paging: true 11166 }); 11167 11168 }); 11169 11170 </script>
11170 11171 11172 </body> 11173</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.