{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:35:49Z","timestamp":1776886549532,"version":"3.51.2"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317320","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"102-106","source":"Crossref","is-referenced-by-count":1,"title":["CASA-Net: Cross-attention and Self-attention for End-to-End Audio-visual Speaker Diarization"],"prefix":"10.1109","author":[{"given":"Haodong","family":"Zhou","sequence":"first","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Informatics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyang","family":"Hong","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Informatics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Third dihard challenge evaluation plan","author":"Ryant","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007312"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10106"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10466"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10483"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00290"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746706"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00073"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref16","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383490"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102422"},{"key":"ref20","first-page":"1","article-title":"Narawpe: A python package for weighted prediction error dereverberation in numpy and tensor-flow for online and offline processing","volume-title":"Speech Communication; 13th ITG-Symposium","author":"Drude"},{"key":"ref21","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding","author":"Povey"},{"key":"ref22","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_28"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,10,31]]},"end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317320.pdf?arnumber=10317320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:52:05Z","timestamp":1709405525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317320","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}