{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:37:49Z","timestamp":1776883069137,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096893","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Robust Audio-Visual ASR with Unified Cross-Modal Attention"],"prefix":"10.1109","author":[{"given":"Jiahong","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenda","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifei","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2128"},{"key":"ref12","first-page":"638","article-title":"Attentive fusion enhanced audio-visual encoding for transformer based robust speech recognition","author":"wei","year":"2020","journal-title":"Signal and Information Processing Association Annual Summit and Conference (AP-SIPA)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref14","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"shi","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243014"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980436"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-412"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.308"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897235"},{"key":"ref19","first-page":"3652","article-title":"Combining residual networks with lstms for lipreading","author":"stafylakis","year":"2017","journal-title":"Proc ISCA Interspeech"},{"key":"ref18","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053954"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref25","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683733"},{"key":"ref4","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415335"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096893.pdf?arnumber=10096893","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:02:51Z","timestamp":1699902171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096893\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096893","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}