PageSourceSearch

https://yuhanghe01.github.io/assets/js/17.b8eaf81f.js

js yuhanghe01.github.io collected 2026-10-03 10:13:43 UTC 20,721 bytes, 1 lines download raw bytes

1(window.webpackJsonp=window.webpackJsonp||[]).push([[17],{434:function(e,r,t){"use strict";t.r(r);var n=t(2),o=Object(n.a)({},(function(){var e=this,r=e._self._c;return r("ContentSlotsDistributor",{attrs:{"slot-key":e.$parent.slotKey},scopedSlots:e._u([{key:"personalInfo",fn:function(){return[r("p",[e._v("I am currently a "),r("a",{attrs:{href:"https://www.microsoft.com/en-us/research/people/yuhanghe/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Senior Researcher"),r("OutboundLink")],1),e._v(" at Microsoft Research (MSR) in Vancouver, Canada. Before that, I graduated with DPhil (aka Ph.D.) in "),r("a",{attrs:{href:"http://www.cs.ox.ac.uk/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Computer Science Department"),r("OutboundLink")],1),e._v(", "),r("a",{attrs:{href:"https://www.ox.ac.uk/",target:"_blank",rel:"noopener noreferrer"}},[e._v("University of Oxford"),r("OutboundLink")],1),e._v(", where I was co-advised by Prof. "),r("a",{attrs:{href:"https://www.cs.ox.ac.uk/people/andrew.markham/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Andrew Markham"),r("OutboundLink")],1),e._v(" and Prof. "),r("a",{attrs:{href:"https://www.cs.ox.ac.uk/people/niki.trigoni/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Niki Trigoni"),r("OutboundLink")],1),e._v(". I interned at Mitsubishi\nElectric Research Laboratories ("),r("a",{attrs:{href:"https://www.merl.com/",target:"_blank",rel:"noopener noreferrer"}},[e._v("MERL"),r("OutboundLink")],1),e._v("), MA, US from Jun. 2023 to Dec. 2023, Microsoft Applied Sciences Group in Munich, Germany ("),r("a",{attrs:{href:"https://www.microsoft.com",target:"_blank",rel:"noopener noreferrer"}},[e._v("Microsoft"),r("OutboundLink")],1),e._v(") from May 2024 to Aug. 2024. I received B.Eng. from "),r("a",{attrs:{href:"https://www.whu.edu.cn/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Wuhan University"),r("OutboundLink")],1),e._v(", China.")]),e._v(" "),r("p",[e._v("My research interest broadly lies in multimodal 3D spatial intelligence, crossmodal content generation, small language model.")]),e._v(" "),r("p",[e._v("Feel free to drop me an email (yuhanghe[at]microsoft.com) if you want to contact.\n")])]},proxy:!0}])},[r("h1",{attrs:{id:"news"}},[r("a",{staticClass:"header-anchor",attrs:{href:"#news"}},[e._v("#")]),e._v(" News")]),e._v(" "),r("ul",[r("li",[r("a",{attrs:{href:"https://arxiv.org/pdf/2604.07522",target:"_blank",rel:"noopener noreferrer"}},[e._v("XShapeEnc"),r("OutboundLink")],1),e._v(" and "),r("a",{attrs:{href:"https://arxiv.org/pdf/2607.06534",target:"_blank",rel:"noopener noreferrer"}},[e._v("CAIRN"),r("OutboundLink")],1),e._v(" accepted by "),r("a",{attrs:{href:"https://neurips.cc/",target:"_blank",rel:"noopener noreferrer"}},[e._v("NeurIPS 2026"),r("OutboundLink")],1),e._v(". 2026.09.")]),e._v(" "),r("li",[r("a",{attrs:{href:"https://os-marathon.github.io/",target:"_blank",rel:"noopener noreferrer"}},[e._v("OS-Marathon"),r("OutboundLink")],1),e._v(" accepted by "),r("a",{attrs:{href:"https://2026.emnlp.org/",target:"_blank",rel:"noopener noreferrer"}},[e._v("EMNLP 2026"),r("OutboundLink")],1),e._v(" Main, "),r("a",{attrs:{href:"https://arxiv.org/pdf/2605.11212",target:"_blank",rel:"noopener noreferrer"}},[e._v("ReVision"),r("OutboundLink")],1),e._v(" accepted by "),r("a",{attrs:{href:"https://2026.emnlp.org/",target:"_blank",rel:"noopener noreferrer"}},[e._v("EMNLP 2026"),r("OutboundLink")],1),e._v(" Findings. 2026.08.")]),e._v(" "),r("li",[r("a",{attrs:{href:"https://openaccess.thecvf.com/content/CVPR2026/papers/Bai_MoReGen_Multi-Agent_Motion-Reasoning_Engine_for_Code-based_Text-to-Video_Synthesis_CVPR_2026_paper.pdfe",target:"_blank",rel:"noopener noreferrer"}},[e._v("MoReGen"),r("OutboundLink")],1),e._v(" accepted by "),r("a",{attrs:{href:"https://iclr.cc/",target:"_blank",rel:"noopener noreferrer"}},[e._v("CVPR 2026"),r("OutboundLink")],1),e._v(". 2026.02.")]),e._v(" "),r("li",[r("a",{attrs:{href:"https://openreview.net/pdf?id=LAYCYiIgZ1",target:"_blank",rel:"noopener noreferrer"}},[e._v("Aurelius"),r("OutboundLink")],1),e._v(" accepted by "),r("a",{attrs:{href:"https://iclr.cc/",target:"_blank",rel:"noopener noreferrer"}},[e._v("ICLR 2026"),r("OutboundLink")],1),e._v(". 2026.01.")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"https://2025.emnlp.org/",target:"_blank",rel:"noopener noreferrer"}},[e._v("EMNLP 2025"),r("OutboundLink")],1),e._v(". 2025.08.")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"https://iccv.thecvf.com/",target:"_blank",rel:"noopener noreferrer"}},[e._v("ICCV 2025"),r("OutboundLink")],1),e._v(". 2025.07.")]),e._v(" "),r("li",[e._v("Serve as area chair for "),r("a",{attrs:{href:"https://3dvconf.github.io/2026/",target:"_blank",rel:"noopener noreferrer"}},[e._v("3DV 2026"),r("OutboundLink")],1),e._v(", "),r("a",{attrs:{href:"https://colmweb.org/",target:"_blank",rel:"noopener noreferrer"}},[e._v("COLM 2025"),r("OutboundLink")],1),e._v(". 2025.05.")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"https://2025.ieeeicassp.org/",target:"_blank",rel:"noopener noreferrer"}},[e._v("ICASSP 2025"),r("OutboundLink")],1),e._v(". 2024.12.")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"https://wacv2025.thecvf.com/",target:"_blank",rel:"noopener noreferrer"}},[e._v("WACV 2025"),r("OutboundLink")],1),e._v(". 2024.10.")]),e._v(" "),r("li",[e._v("Serve as "),r("a",{attrs:{href:"https://aaai.org/conference/aaai/aaai-25/",target:"_blank",rel:"noopener noreferrer"}},[e._v("AAAI 2025"),r("OutboundLink")],1),e._v(" program committee, "),r("a",{attrs:{href:"https://2025.ieeeicassp.org/",target:"_blank",rel:"noopener noreferrer"}},[e._v("ICASSP 2025"),r("OutboundLink")],1),e._v(" area chair. 2024.09.")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"http://neurips.cc/",target:"_blank",rel:"noopener noreferrer"}},[e._v("NeurIPS 2024"),r("OutboundLink")],1),e._v(". 2024.09.")]),e._v(" "),r("li",[e._v("One paper accepted by Nature Communications Engineering, "),r("a",{attrs:{href:"https://www.nature.com/articles/s44172-024-00220-5",target:"_blank",rel:"noopener noreferrer"}},[e._v("paper link"),r("OutboundLink")],1),e._v(".")]),e._v(" "),r("li",[e._v("Started internship at Microsoft's Applied Sciences Group (ASG) in Munich, Germany. 2024.05.")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"https://icml.cc/",target:"_blank",rel:"noopener noreferrer"}},[e._v("ICML 2024"),r("OutboundLink")],1),e._v(". 2024.05.")]),e._v(" "),r("li",[e._v("Won student volunteer scholarship for "),r("a",{attrs:{href:"https://aaai.org/aaai-conference/",target:"_blank",rel:"noopener noreferrer"}},[e._v("AAAI 2024"),r("OutboundLink")],1),e._v(". 2023.12.")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"https://aaai.org/aaai-conference/",target:"_blank",rel:"noopener noreferrer"}},[e._v("AAAI 2024"),r("OutboundLink")],1),e._v(". 2023.12.")]),e._v(" "),r("li",[e._v("Accepted by "),r("a",{attrs:{href:"https://wacv2024.thecvf.com/doctoral-consortium/",target:"_blank",rel:"noopener noreferrer"}},[e._v("WACV 2024 Doctoral Consortium"),r("OutboundLink")],1),e._v(". 2023.11.")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"https://wacv2024.thecvf.com/",target:"_blank",rel:"noopener noreferrer"}},[e._v("WACV 2024"),r("OutboundLink")],1),e._v(". 2023.10.")]),e._v(" "),r("li",[e._v("Start internship at Mitsubishi Electric Research Laboratories "),r("a",{attrs:{href:"https://www.merl.com/",target:"_blank",rel:"noopener noreferrer"}},[e._v("MERL"),r("OutboundLink")],1),e._v(". 2023.06;")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"https://roboticsconference.org/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Robotics: Science and Systems RSS 2023"),r("OutboundLink")],1),e._v(". 2023.04;")]),e._v(" "),r("li",[e._v("One paper accepted by "),r("a",{attrs:{href:"http://aistats.org/aistats2023/",target:"_blank",rel:"noopener noreferrer"}},[e._v("AISTATS 2023"),r("OutboundLink")],1),e._v(". 2023.01;")]),e._v(" "),r("li",[e._v("Completed confirmation viva by examiners Prof. "),r("a",{attrs:{href:"https://www.cs.ox.ac.uk/people/alex.rogers/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Alex Rogers"),r("OutboundLink")],1),e._v(" and Asso. Prof. "),r("a",{attrs:{href:"https://www.ronnieclark.co.uk/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Ronald Clark"),r("OutboundLink")],1),e._v(". 2022.10;")]),e._v(" "),r("li",[e._v("Received "),r("a",{attrs:{href:"https://interspeech2022.org/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Interspeech 2022"),r("OutboundLink")],1),e._v(" travel grant. 2022.07;")]),e._v(" "),r("li",[e._v("Paper accepted by "),r("a",{attrs:{href:"https://interspeech2022.org/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Interspeech 2022"),r("OutboundLink")],1),e._v(". 2022.06;")]),e._v(" "),r("li",[e._v("Worked as ICML21 student volunteer. 2021.06;")]),e._v(" "),r("li",[e._v("Paper accepted by "),r("a",{attrs:{href:"https://icml.cc/Conferences/2021",target:"_blank",rel:"noopener noreferrer"}},[e._v("ICML2021"),r("OutboundLink")],1),e._v(". 2021.05;")]),e._v(" "),r("li",[e._v("Completed transfer viva by examiners Prof. "),r("a",{attrs:{href:"http://mnslab.org/tamvu/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Tam Vu"),r("OutboundLink")],1),e._v(" and Prof. "),r("a",{attrs:{href:"https://www.cs.ox.ac.uk/people/alex.rogers/",target:"_blank",rel:"noopener noreferrer"}},[e._v("Alex Rogers"),r("OutboundLink")],1),e._v(".  2021.01;")])]),e._v(" "),r("h1",{attrs:{id:"publications"}},[r("a",{staticClass:"header-anchor",attrs:{href:"#publications"}},[e._v("#")]),e._v(" Publications")]),e._v(" "),r("p",[e._v("For full publication list, please refer to "),r("a",{attrs:{href:"https://scholar.google.com/citations?user=H1p3ve8AAAAJ&hl=en",target:"_blank",rel:"noopener noreferrer"}},[e._v("Google Scholar"),r("OutboundLink")],1),e._v(" or "),r("RouterLink",{attrs:{to:"/publications/"}},[e._v("→ Full list")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/xshapeenc.png",link:"https://arxiv.org/pdf/2604.07522v2"}},[r("p",[r("strong",[e._v("Training-free Spatially Grounded Geometric Shape Encoding")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(".")]),e._v(" "),r("p",[e._v("Annual Conference on Neural Information Processing Systems (NeurIPS), 2026.")]),e._v(" "),r("p",[e._v("I propose a novel training-free framework, called XShapeEnc, to encode spatially grounded 2D geometric shape. The encoding is general-purpose, interpretable and high frequency rich. It accounts for the 2D geometric shape's geometric structure, spatial pose encoding, and can encode them either separately or jointly. An emphasis-adjustable strategy is introduced in you want to emphasize different c
1omponents differents.")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://arxiv.org/pdf/2604.07522v2"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/xshapeenc.bib"}},[e._v("BibTex")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://github.com/yuhanghe01/XShapeEnc"}},[e._v("Code")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/aurelius_contribution.jpg",link:"https://openreview.net/pdf?id=LAYCYiIgZ1"}},[r("p",[r("strong",[e._v("Aurelius: Relation Aware Text-to-Audio Generation At Scale")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(", He Liang, Jain Yash, Andrew Markham, Vibhav Vineet.")]),e._v(" "),r("p",[e._v("International Conference on Learning Representations (ICLR), 2026.")]),e._v(" "),r("p",[e._v("We introduce Aurelius framework, which contains AudioEventSet - a 110 classes audio event corpus across 7 major classes, AudioRelSet - a 100 classes relation corpus across 6 major classes, and a novel <text,audio> pair creation strategy.")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://openreview.net/pdf?id=LAYCYiIgZ1"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/aurelius.bib"}},[e._v("BibTex")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://yuhanghe01.github.io/Aurelius-Proj/"}},[e._v("Project Site")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://github.com/yuhanghe01/Aurelius"}},[e._v("Code")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/ritta_teasing_fig.png",link:"https://aclanthology.org/2025.emnlp-main.173.pdf"}},[r("p",[r("strong",[e._v("RiTTA: Modeling Event Relations in Text-to-Audio Generation")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(", Jain Yash, Xubo Liu, Andrew Markham, Vibhav Vineet.")]),e._v(" "),r("p",[e._v("Conference on Empirical Methods in Natural Language Processing (EMNLP Main), 2025.")]),e._v(" "),r("p",[e._v("We contribute audio events relation modeling in text-to-audio (TTA) generation task by proposing a new benchmark and a novel evaluation protocol.")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://aclanthology.org/2025.emnlp-main.173.pdf"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/ritta.bib"}},[e._v("BibTex")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://yuhanghe01.github.io/RiTTA-Proj/"}},[e._v("Project Site")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://github.com/yuhanghe01/RiTTA"}},[e._v("Code")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/deepnerap_icml24.png",link:"https://icml.cc/virtual/2024/poster/33608"}},[r("p",[r("strong",[e._v("Deep Neural Room Acoustics Primitive")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(", Anoop Cherian, Gordon Wichern, Andrew Markham.")]),e._v(" "),r("p",[e._v("The 41st International Conference on Machine Learning (ICML), 2024.")]),e._v(" "),r("p",[e._v("We introduce a novel framework to learn a continuous neural room acoustics field that implicitly encodes all essential sound propagation primitives for each enclosed 3D space.")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://proceedings.mlr.press/v235/he24b.html"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/deepnerap.bib"}},[e._v("BibTex")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://icml.cc/media/icml-2024/Slides/33608.pdf"}},[e._v("Poster")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/soundcount.png",link:"https://arxiv.org/pdf/2312.16149.pdf"}},[r("p",[r("strong",[e._v("SoundCount: Sound Counting from Raw Audio with Dyadic Decomposition Neural Network")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(", Zhuangzhuang Dai, Long Chen, Niki Trigoni, Andrew Markham.")]),e._v(" "),r("p",[e._v("The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024.")]),e._v(" "),r("p",[e._v("We introduce a learnable dyadic decomposition framework that learns more representative time-frequency representation from highly polyphonic and loudness\nvarying sound waveform. It dyadically decomposes the waveform in multi-stage hierarchical manner.")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://arxiv.org/pdf/2312.16149.pdf"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/soundcount.bib"}},[e._v("BibTex")]),e._v(" "),r("LinkBtn",{attrs:{href:"/projects/soundcount-poster.pdf"}},[e._v("Poster")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/sound3dvdet.png",link:"https://openaccess.thecvf.com/content/WACV2024/html/He_Sound3DVDet_3D_Sound_Source_Detection_Using_Multiview_Microphone_Array_and_WACV_2024_paper.html"}}
1,[r("p",[r("strong",[e._v("Sound3DVDet: 3D Sound Source Detection Using Multiview Microphone Array and RGB Images")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(", Sangyun Shin, Anoop Cherian, Niki Trigoni, Andrew Markham.")]),e._v(" "),r("p",[e._v("IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.")]),e._v(" "),r("p",[e._v("We introduce a novel 3D sound source localization and classification from multiview acoustic-camera recordings task. The sound source\nlies on object's physical surface but visually non-observable, which reflects some application cases like gas leaking.")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://openaccess.thecvf.com/content/WACV2024/papers/He_Sound3DVDet_3D_Sound_Source_Detection_Using_Multiview_Microphone_Array_and_WACV_2024_paper.pdf"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/sound3dvdet.bib"}},[e._v("BibTex")]),e._v(" "),r("LinkBtn",{attrs:{href:"/projects/sound3dvdet-poster.pdf"}},[e._v("Poster")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://github.com/yuhanghe01/Sound3DVDet"}},[e._v("Code")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/deepexplorer.png",link:"https://www.roboticsproceedings.org/rss19/p099.pdf"}},[r("p",[r("strong",[e._v("Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(", "),r("strong",[e._v("Irving Fang")]),e._v(", Yiming Li, Rushi Bhavesh Shah, Chen Feng.")]),e._v(" "),r("p",[e._v("Robotics: Science and Systems (RSS), 2023.")]),e._v(" "),r("p",[e._v("We propose metric-free DeepExplorer to efficiently construct topological map to represent an environment. DeepExplorers\nexhibits strong sim2sim and sim2real generalization capability.")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://www.roboticsproceedings.org/rss19/p099.pdf"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/deepexplorer.bib"}},[e._v("BibTex")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://ai4ce.github.io/DeepExplorer/"}},[e._v("Project")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://github.com/ai4ce/DeepExplorer"}},[e._v("Code")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/soundsynp.png",link:"https://proceedings.mlr.press/v206/he23c/he23c.pdf"}},[r("p",[r("strong",[e._v("SoundSynp: Sound Source Detection from Raw Waveforms with Multi-Scale Synperiodic Filterbanks")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(", Andrew Markham")]),e._v(" "),r("p",[e._v("International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.")]),e._v(" "),r("p",[e._v("We propose a novel framework to construct learnable sound signal processing filter banks that achieve multi-scale processing in both time and frequency domain.")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://proceedings.mlr.press/v206/he23c/he23c.pdf"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/SoundSynp.bib"}},[e._v("BibTex")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://github.com/yuhanghe01/SoundSynp"}},[e._v("Code")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/SoundDoA.png",link:""}},[r("p",[r("strong",[e._v("SoundDoA: Learn Sound Source Direction of Arrival and Semantics from Sound Raw Waveforms")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(", Andrew Markham")]),e._v(" "),r("p",[e._v("Interspeech, 2022.")]),e._v(" "),r("p",[e._v("We propose a novel sound event direction of arrival (DoA) estimation framework with a novel filter bank to jointly learn sound event semantics and spatial location relevant representations.")]),e._v(" "),r("LinkBtn",{attrs:{href:"https://www.isca-archive.org/interspeech_2022/he22_interspeech.pdf"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/SoundDoA.bib"}},[e._v("BibTex")])],1),e._v(" "),r("PublicationCard",{attrs:{image:"/projects/SoundDet_ICML21_Thumbnail.png",link:"http://proceedings.mlr.press/v139/he21b/he21b.pdf"}},[r("p",[r("strong",[e._v("SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform")])]),e._v(" "),r("p",[r("strong",[e._v("Yuhang He")]),e._v(", Niki Trigoni, Andrew Markham")]),e._v(" "),r("p",[e._v("International Conference on Machine Learning (ICML), 2021.")]),e._v(" "),r("p",[e._v("We propose a novel sound event detection framework for polyphonic and moving sound event detection. We also propose novel object-based evaluation metrics to evaluate performance more objectively.")]),e._v(" "),r("LinkBtn",{attrs:{href:"http://proceedings.mlr.press/v139/he21b/he21b.pdf"}},[e._v("PDF")]),e._v(" "),r("LinkBtn",{attrs:{type:"dialog",href:"/publications/SoundDet.bib"}},[e._v("BibTex")])],1),e._v(" "),r("h1",{attrs:{id:"public-office-hours"}},[r("a",{staticClass:"header-anchor",attrs:{href:"#public-office-hours"}},[e._v("#")]),e._v(" PUBLIC OFFICE HOURS")]),e._v(" "),r("p",[e._v("I am always happy to chat with people who are interested in my work. You can check the following office hour I keep update\nto book a time slot if you want to chat.")]),e._v(" "),r("OfficeHours",{attrs:{src:"https://calendly.com/yuhanghe01/30min"}})],1)}),[],!1,null,null,null);r.default=o.exports}}]);

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.