{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:36:14Z","timestamp":1776886574606,"version":"3.51.2"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448398","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10666-10670","source":"Crossref","is-referenced-by-count":9,"title":["Audio-Visual Active Speaker Extraction for Sparsely Overlapped Multi-Talker Speech"],"prefix":"10.1109","author":[{"given":"Junjie","family":"Li","sequence":"first","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruijie","family":"Tao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zexu","family":"Pan","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Ge","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-015-0882-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref4","article-title":"Disentangling voice and content with self-supervision for speaker recognition","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"LIU"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01408"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-91"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414998"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413411"},{"key":"ref12","article-title":"Sparsely overlapped speech training in the time domain: Joint learning of target speech separation and personal vad benefits","volume-title":"2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Lin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205759"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2545"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153258"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3199109"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094306"},{"key":"ref22","article-title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","volume-title":"Proc. ACM Multimedia","author":"Tao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-574"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1939"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746757"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref31","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448398.pdf?arnumber=10448398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:53:16Z","timestamp":1722660796000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448398","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}