{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:15:40Z","timestamp":1740100540191,"version":"3.37.3"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2018YFB1305200"],"award-info":[{"award-number":["2018YFB1305200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771333"],"award-info":[{"award-number":["61771333"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688240","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"122-129","source":"Crossref","is-referenced-by-count":2,"title":["DeepLip: A Benchmark for Deep Learning-Based Audio-Visual Lip Biometrics"],"prefix":"10.1109","author":[{"given":"Meng","family":"Liu","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Zeng","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","first-page":"2873","article-title":"Large margin softmax loss for speaker verification","author":"yi","year":"0","journal-title":"Interspeech 2019"},{"key":"ref33","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1121\/1.5042758"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref34","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref10","first-page":"2242","article-title":"Audio-visual speaker recognition with a cross-modal discrim-inative network","author":"tao","year":"0","journal-title":"Proc Interspeech 2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3057230"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414260"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319892"},{"key":"ref14","first-page":"3662","article-title":"Im-proving speaker-independent lipreading with domain-adversarial training","author":"wand","year":"0","journal-title":"Proc Interspeech 2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472172"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.02.016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607030"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CCST.2002.1049223"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embed-dings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"InterSpeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3045937"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8721.2008.00615.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref5","article-title":"Lipnet: End-to-end sentence-level lipreading","author":"assael","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref8","first-page":"1","article-title":"Video multimodal emotion recognition based on bi-gru and attention fusion","author":"huan","year":"2020","journal-title":"Multimedia Tools and Applications"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cock-tail party: a speaker-independent audio-visual model for speech separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-37"},{"key":"ref9","article-title":"Speaker and speech recognition by audio-visual lip biometrics","author":"faraj","year":"2007","journal-title":"The 2nd International Conference on Biometrics"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.886017"},{"key":"ref20","article-title":"But system description to voxceleb speaker recognition challenge 2019","author":"zeinali","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-019-01630-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461347"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2891733"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2013.2293025"},{"key":"ref25","first-page":"1572","article-title":"Lvid: A multimodal biometrics au-thentication system on smartphones","volume":"15","author":"libing","year":"2019","journal-title":"IEEE Transactions on Information Forensics and Security"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688240.pdf?arnumber=9688240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:54Z","timestamp":1652733714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688240\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688240","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}