{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:19:38Z","timestamp":1781713178622,"version":"3.54.5"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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","award":["62071288"],"award-info":[{"award-number":["62071288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1736202"],"award-info":[{"award-number":["U1736202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3057230","type":"journal-article","created":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T11:12:12Z","timestamp":1612869132000},"page":"1079-1092","source":"Crossref","is-referenced-by-count":59,"title":["Audio-Visual Deep Neural Network for Robust Person Verification"],"prefix":"10.1109","volume":"29","author":[{"given":"Yanmin","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1988","article-title":"Deep learning face representation by joint identification-verification","author":"sun","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"1891","article-title":"Deep learning face representation from predicting 10000 classes","author":"sun","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TPAMI.2013.112","article-title":"Learning discriminant face descriptor","volume":"36","author":"lei","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539992"},{"key":"ref30","article-title":"But system description to voxceleb speaker recognition challenge","author":"zeinali","year":"2019"},{"key":"ref37","article-title":"Deepid3: Face recognition with very deep neural networks","volume":"abs 1502 873","author":"sun","year":"2015","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298907"},{"key":"ref35","article-title":"Labeled faces in the wild: A. database forstudying face recognition in unconstrained environments","author":"huang","year":"2008","journal-title":"Workshop on faces in’Real-Life’Images detection alignment and recognition"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2928128"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.07.003"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2229"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2028"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-41"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462122"},{"key":"ref24","first-page":"231","article-title":"Using lip features for multimodal speaker verification","author":"zhang","year":"0","journal-title":"Proc Odyssey 2001 The Speaker and Language Recogn Workshop"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-37"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683477"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref54","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref52","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding no CONF IEEE Signal Process Soc"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240601"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"ref13","article-title":"Cross-modal speaker verification and recognition: A multilingual perspective","author":"saeed","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054180"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref5","first-page":"41.1","article-title":"Deep face recognition","author":"parkhi","year":"0","journal-title":"Proc British Machine Vis Conf (BMVC)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1608"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016498"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706575"},{"key":"ref47","article-title":"Gated multimodal units for information fusion","author":"arevalo","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref43","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09350195.pdf?arnumber=9350195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:54Z","timestamp":1652194434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9350195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3057230","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}