{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T17:30:25Z","timestamp":1783791025046,"version":"3.55.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446720","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10471-10475","source":"Crossref","is-referenced-by-count":15,"title":["Visual Speech Recognition for Languages with Limited Labeled Data Using Automatic Labels from Whisper"],"prefix":"10.1109","author":[{"given":"Jeong Hun","family":"Yeo","sequence":"first","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minsu","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"KAIST,Integrated Vision and Language Lab,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3328283"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref4","volume-title":"Openai: Introducing chatgpt","year":"2022"},{"key":"ref5","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"},{"key":"ref6","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"ICML","author":"Amodei","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref10","article-title":"Lipnet: End-to-end sentence-level lipreading","author":"Assael","year":"2016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095582"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-194"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6174"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094693"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3352388"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446532"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909819"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01409"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref28","article-title":"Lrs3-ted: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094585"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2011.941081"},{"key":"ref35","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref36","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. ICLR","author":"Shi"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.141"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref42","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446720.pdf?arnumber=10446720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:25:28Z","timestamp":1722576328000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446720\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446720","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}