{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T06:38:53Z","timestamp":1775716733245,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747237","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6042-6046","source":"Crossref","is-referenced-by-count":7,"title":["Audio-Visual Multi-Channel Speech Separation, Dereverberation and Recognition"],"prefix":"10.1109","author":[{"given":"Guinan","family":"Li","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Yu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1256","article-title":"Convtasnet: Surpassing ideal time– frequency magnitude masking for speech separation","volume":"27","author":"luo","year":"2019","journal-title":"IEEE-ACM Trans Audio Spe"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"key":"ref30","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE T Pattern Anal"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987209"},{"key":"ref36","article-title":"Audio-visual multi-channel recognition of over-lapped speech","author":"yu","year":"2020","journal-title":"InterSpeech"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3078883"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682566"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682470"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472778"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2284"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462081"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.898456"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4517552"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-733","article-title":"Neural network-based spectrum estimation for online wpe dereverberation","author":"kinoshita","year":"2017","journal-title":"InterSpeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM T Graphic"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.898454"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700814"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2009.09.005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3181"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521255"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053610"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2696307"},{"key":"ref42","article-title":"Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","author":"recommendation","year":"2001","journal-title":"Rec ITU-TP 862"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054393"},{"key":"ref41","first-page":"1","article-title":"Room impulse response generator","volume":"2","author":"habets","year":"2006","journal-title":"Technische Universiteit Eindhoven Tech Rep"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462080"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747237.pdf?arnumber=9747237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:58Z","timestamp":1660594078000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747237","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}