{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:19:39Z","timestamp":1781713179133,"version":"3.54.5"},"reference-count":22,"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\/icassp40776.2020.9054376","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"4367-4371","source":"Crossref","is-referenced-by-count":26,"title":["Self-Supervised Learning for Audio-Visual Speaker Diarization"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi-Xiong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yahuan","family":"Cong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806293"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10471","article-title":"Look, listen and learn—a multimodal lstm for speaker identification","author":"ren","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref12","article-title":"Avaactivespeaker: An audio-visual dataset for active speaker detection","author":"roth","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref15","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Workshop on Multi-view Lipreading ACCV"},{"key":"ref16","article-title":"Vox-celeb: a large-scale speaker identification dataset","author":"nagrani","year":"2017"},{"key":"ref17","article-title":"Co-training of audio and video representations from self-supervised temporal synchronization","volume":"3","author":"korbar","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2606661"},{"key":"ref19","article-title":"A large-scale audio-visual corpus for multimodal speaker diarization, speech separation and recognition","year":"0","journal-title":"preparation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5244\/C.20.92"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref8","article-title":"Detecting audio-visual synchrony using deep neural networks","author":"marcheret","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref7","article-title":"Putting a face to the voice: Fusing audio and visual signals across a video to determine speakers","author":"hoover","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285474"},{"key":"ref1","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","article-title":"A toolkit for making real world machine learning and data analysis applications in C++","author":"king","year":"0"}],"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\/09054376.pdf?arnumber=9054376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:27:43Z","timestamp":1696015663000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054376","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}