{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:40:17Z","timestamp":1785606017748,"version":"3.56.0"},"reference-count":40,"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\/icassp49357.2023.10096889","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":125,"title":["Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels"],"prefix":"10.1109","author":[{"given":"Pingchuan","family":"Ma","sequence":"first","affiliation":[{"name":"Imperial College London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Haliassos","sequence":"additional","affiliation":[{"name":"Imperial College London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adriana","family":"Fernandez-Lopez","sequence":"additional","affiliation":[{"name":"Meta AI,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honglie","family":"Chen","sequence":"additional","affiliation":[{"name":"Meta AI,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"Imperial College London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Imperial College London,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref35","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"English in LREC"},{"key":"ref12","article-title":"Nemo: A toolkit for building ai applications using neural modules","author":"kuchaiev","year":"2019"},{"key":"ref34","first-page":"198","article-title":"TED-LIUM 3: Twice as much data and corpus repartition for experiments on speaker adaptation","volume":"11096","author":"hernandez","year":"2018","journal-title":"SPECOM"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref37","first-page":"4491","article-title":"Leveraging uni-modal self-supervised learning for multimodal audio-visual speech recognition","author":"pan","year":"2022","journal-title":"ACL"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1038\/s42256-022-00550-z","article-title":"Visual Speech Recognition for Multiple Languages in the Wild","author":"ma","year":"2022","journal-title":"Nature Mach Intell"},{"key":"ref11","author":"radford","year":"2022","journal-title":"Introducing whisper"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref32","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref1","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE TPAMI"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10920"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383459"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"3652","DOI":"10.21437\/Interspeech.2017-85","article-title":"Combining residual networks with LSTMs for lipreading","volume":"9","author":"stafylakis","year":"2017","journal-title":"InterSpeech"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref21","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref28","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"afouras","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"shi","year":"2022","journal-title":"ICLRE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref5","first-page":"12 449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"NIPS"},{"key":"ref40","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018","journal-title":"CoRR"}],"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\/10096889.pdf?arnumber=10096889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T13:58:02Z","timestamp":1700488682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096889\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096889","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}