{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:20:23Z","timestamp":1775229623530,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054127","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6984-6988","source":"Crossref","is-referenced-by-count":57,"title":["Audio-Visual Recognition of Overlapped Speech for the LRS2 Dataset"],"prefix":"10.1109","author":[{"given":"Jianwei","family":"Yu","sequence":"first","affiliation":[]},{"given":"Shi-Xiong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Shahram","family":"Ghorbani","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Shiyin","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Shansong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2765834"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1109\/SLT.2018.8639643","article-title":"Audio-visual speech recognition with a hybrid ctc\/attention architecture","author":"petridis","year":"2018","journal-title":"Proceedings of 2018 IEEE Spoken Language Technology Workshop (SLT)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref11","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref12","first-page":"6570","article-title":"Robust audio-visual speech recognition using bimodal dfsmn with multi-condition training and dropout regularization","author":"zhang","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref13","first-page":"2130","article-title":"Deep multi-modal learning for audio-visual speech recognition","author":"mroueh","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref16","article-title":"Speaker separation using visually-derived binary masks","author":"khan","year":"2013","journal-title":"Auditory-Visual Speech Processing (AVSP) 2013"},{"key":"ref17","article-title":"Looking to listen at the cocktail party: A speaker-independent audiovisual model for speech separation","author":"ephrat","year":"2018","journal-title":"arXiv preprint arXiv 1804 03583"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2853566"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2815268"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1536"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2444659"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref29","article-title":"Robust speech recognition with speech enhanced deep neural networks","author":"du","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/78.902111"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref2","author":"wertheimer","year":"1938","journal-title":"Laws of Organization in Perceptual Forms"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1109\/TNN.2007.913988","article-title":"Computational auditory scene analysis: Principles, algorithms, and applications","volume":"19","author":"rouat","year":"2006","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2284"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2928140"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835719"},{"key":"ref24","article-title":"Speaker-targeted audiovisual models for speech recognition in cocktail-party environments","author":"chao","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref23","first-page":"3264","article-title":"Speaker separation using visual speech features and single-channel audio","author":"khan","year":"2013","journal-title":"InterSpeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054127.pdf?arnumber=9054127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:26:11Z","timestamp":1656375971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054127","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}