{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:16:38Z","timestamp":1777655798237,"version":"3.51.4"},"reference-count":34,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448428","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10391-10395","source":"Crossref","is-referenced-by-count":5,"title":["LITEVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data"],"prefix":"10.1109","author":[{"given":"Hendrik","family":"Laux","sequence":"first","affiliation":[{"name":"University Hospital RWTH Aachen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emil","family":"Mededovic","sequence":"additional","affiliation":[{"name":"University Hospital RWTH Aachen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Hallawa","sequence":"additional","affiliation":[{"name":"Clinomic Medical GmbH,Aachen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lukas","family":"Martin","sequence":"additional","affiliation":[{"name":"Clinomic Medical GmbH,Aachen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arne","family":"Peine","sequence":"additional","affiliation":[{"name":"Clinomic Medical GmbH,Aachen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anke","family":"Schmeink","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Chair of Information Theory and Data Analytics,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-26155-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688191"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-13015-5_39"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref7","article-title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","author":"Shi","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01803"},{"key":"ref9","first-page":"5152","article-title":"Subword Level Lip Reading With Visual Attention","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Prajwal"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.155"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref12","article-title":"LipNet: End-to-End Sentence-level Lipreading","author":"Assael","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref15","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1360"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref26","article-title":"NeMo: A toolkit for building AI applications using Neural Modules","author":"Kuchaiev","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","first-page":"1755","article-title":"Dlib-ml: A Machine Learning Toolkit","volume":"10","author":"King","year":"2009","journal-title":"The Journal of Machine Learning Research"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref32","article-title":"Mixed Precision Training","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Micikevicius"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"}],"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\/10448428.pdf?arnumber=10448428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:53:38Z","timestamp":1722660818000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448428","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}