{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:32:37Z","timestamp":1784399557128,"version":"3.55.0"},"reference-count":102,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AME Programmatic Funding Scheme","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]},{"name":"Science and Engineering Research Council, A*STAR, Singapore"},{"name":"National Robotics Program","award":["192 25 00054"],"award-info":[{"award-number":["192 25 00054"]}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Germany’s Excellence Strategy"},{"name":"University Allowance"},{"DOI":"10.13039\/501100007837","name":"Universit\u00e4t Bremen","doi-asserted-by":"publisher","award":["EXC 2077"],"award-info":[{"award-number":["EXC 2077"]}],"id":[{"id":"10.13039\/501100007837","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Chinese University of Hong Kong, Shenzhen","award":["UDF01002333"],"award-info":[{"award-number":["UDF01002333"]}]},{"name":"The Chinese University of Hong Kong, Shenzhen","award":["UF02002333"],"award-info":[{"award-number":["UF02002333"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3153258","type":"journal-article","created":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T20:31:28Z","timestamp":1645734688000},"page":"1650-1664","source":"Crossref","is-referenced-by-count":41,"title":["Selective Listening by Synchronizing Speech With Lips"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8106-1176","authenticated-orcid":false,"given":"Zexu","family":"Pan","sequence":"first","affiliation":[{"name":"Integrative Sciences and Engineering Programme, Institute of Data Science, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruijie","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1584-6282","authenticated-orcid":false,"given":"Chenglin","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"issue":"1","key":"ref2","first-page":"117","article-title":"The cocktail party phenomenon: A review of research on speech intelligibility in multiple-talker conditions","volume":"86","author":"Bronkhorst","year":"2000","journal-title":"Acta Acustica United Acustica"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/1073858413514136"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1167\/13.3.16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1814"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1410"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3100682"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3143036"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688031"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004035"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413776"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3010163"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3125142"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462471"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref21","first-page":"334","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","volume-title":"Proc. 19th Int. Soc. Music Inf. Retrieval Conf.","author":"Stoller","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054222"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682245"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2418"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054683"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383539"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1513"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1939"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2260"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-5842.2004.00685.x"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuropsychologia.2020.107530"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3675-12.2013"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.1396-16.2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1065"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1697"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596406"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054180"},{"key":"ref50","article-title":"USEV: Universal speaker extraction with visual cue for sparsely overlapped multi-talker speech","author":"Pan","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2928140"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682061"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2853566"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.10.002"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.07.001"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhp124"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004016"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268910"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683874"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414133"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746421"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_2"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.827503"},{"key":"ref77","first-page":"813","article-title":"Audio-vision: Locating sounds via audio-visual synchrony","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hershey","year":"1999"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-201"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093490"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref83","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref86","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Gutmann","year":"2010"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1653"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.001"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref92","volume-title":"Theory and Application of Digital Signal Processing","author":"Oppenheim","year":"1978"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413359"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref97","article-title":"Adam, A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref102","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09721129.pdf?arnumber=9721129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:25:46Z","timestamp":1705533946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9721129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3153258","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}