{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:48:35Z","timestamp":1787165315414,"version":"3.56.0"},"reference-count":25,"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\/icassp40776.2020.9053900","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"4492-4496","source":"Crossref","is-referenced-by-count":107,"title":["Ava Active Speaker: An Audio-Visual Dataset for Active Speaker Detection"],"prefix":"10.1109","author":[{"given":"Joseph","family":"Roth","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sourish","family":"Chaudhuri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ondrej","family":"Klejch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radhika","family":"Marvin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Gallagher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liat","family":"Kaver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sharadh","family":"Ramaswamy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arkadiusz","family":"Stopczynski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhonghua","family":"Xi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caroline","family":"Pantofaru","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref11","article-title":"Speaker adaptation techniques for automatic speech recognition","author":"shinoda","year":"2011","journal-title":"Proc APSIPA ASC"},{"key":"ref12","article-title":"Putting a face to the voice: Fusing audio and visual signals across a video to determine speakers","author":"hoover","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref14","first-page":"2018","article-title":"Looking to listen at the cocktail party: A speakerindependent audio-visual model for speech separation","volume":"37","author":"ephrat","year":"0","journal-title":"ACT Transactions on Graphics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88693-8_12"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.04.018"},{"key":"ref17","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2018","journal-title":"Proc INTERSPEECH"},{"key":"ref18","first-page":"1","article-title":"Who’s speaking? audio-supervised classification of active speakers in video","author":"chakravarty","year":"2015","journal-title":"Proc Int Conf Multimodal Interact"},{"key":"ref19","first-page":"1","article-title":"Cross-modal supervision for learning active speaker detection in video","author":"chakravarty","year":"2016","journal-title":"Proc European Conference on Computer Vision"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref3","first-page":"814","article-title":"Facesync: A linear operator for measuring synchronization of video facial images and audio tracks","author":"slaney","year":"0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683318"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3005467.3005470"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/GLU.2017-10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2011515"},{"key":"ref1","article-title":"Audio vision: Using audio-visual synchrony to locate sounds","author":"hershey","year":"1999","journal-title":"Proceedings of NIPS"},{"key":"ref9","article-title":"Out of time: Automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Proc Workshop Multi-View Lip Reading Asian Conference on Computer Vision"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993172"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2028"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"ref25","first-page":"2017","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"0","journal-title":"CoRR"}],"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\/09053900.pdf?arnumber=9053900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:21:05Z","timestamp":1656361265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053900","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}