{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T00:33:43Z","timestamp":1725496423538},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icmew63481.2024.10645425","type":"proceedings-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T17:43:36Z","timestamp":1724953416000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["The Whu Wake Word Lipreading System for the 2024 Chat-Scenario Chinese Lipreading Challenge"],"prefix":"10.1109","author":[{"given":"Haoxu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cancan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Suo","sequence":"additional","affiliation":[{"name":"AI Center, OPPO,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462964"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746683"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10650"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747216"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096858"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095459"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446074"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc ICLR, 2022","author":"Shi","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.367"},{"journal-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","year":"2018","author":"Afouras","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-480"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-352"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-56"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414777"},{"key":"ref29","first-page":"15490","article-title":"Visual Voice: Audio-Visual Speech Separation with Cross-Modal Consistency","volume-title":"Proc. CVPR","author":"Gao","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448079"},{"article-title":"Seeing Wake Words: Audio-Visual Keyword Spotting","volume-title":"Proc. BMVC, 2020","author":"Momeni","key":"ref31"},{"key":"ref32","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NIPS","author":"Baevski","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref37","first-page":"11863","article-title":"Simam: A simple, parameter-free attention module for convolutional neural networks","volume-title":"International conference on machine learning","author":"Yang","year":"2021"},{"article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","volume-title":"Proc. ICLR, 2021","author":"Dosovitskiy","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00229"},{"key":"ref40","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proc. NAACL-HLT, Jill Burstein, Christy Doran, and Thamar Solorio, Eds","author":"Devlin","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref43","first-page":"17627","article-title":"Branch-former: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding","volume-title":"Proc. ICML. PMLR","author":"Peng","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-563"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10645349\/10645352\/10645425.pdf?arnumber=10645425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T05:46:04Z","timestamp":1725428764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icmew63481.2024.10645425","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}