{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:32Z","timestamp":1775230052828,"version":"3.50.1"},"reference-count":32,"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\/icassp48485.2024.10448473","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11431-11435","source":"Crossref","is-referenced-by-count":9,"title":["BRAVEn: Improving Self-supervised pre-training for Visual and Auditory Speech Recognition"],"prefix":"10.1109","author":[{"given":"Alexandros","family":"Haliassos","sequence":"first","affiliation":[{"name":"Imperial College London"}]},{"given":"Andreas","family":"Zinonos","sequence":"additional","affiliation":[{"name":"Imperial College London"}]},{"given":"Rodrigo","family":"Mira","sequence":"additional","affiliation":[{"name":"Imperial College London"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"Imperial College London"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Imperial College London"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref3","article-title":"Audio-visual speech recognition is worth 32x32x8 voxels","volume-title":"ASRU Workshop","author":"Serdyuk"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10920"},{"key":"ref5","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01803"},{"key":"ref10","article-title":"Jointly learning visual and auditory speech representations from raw data","volume-title":"ICLR","author":"Haliassos"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref12","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"ICLR","author":"Shi"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3275873"},{"key":"ref14","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"ICML","volume":"162","author":"Baevski"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389642"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref20","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"ref21","first-page":"9650","article-title":"Emerging properties in selfsupervised vision transformers","volume-title":"Proceedings of the 18th IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Caron"},{"key":"ref22","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref27","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref30","first-page":"21157","article-title":"U-hubert: Unified mixed-modal speech pretraining and zero-shot transfer to unlabeled modality","volume-title":"NeurIPS","volume":"35","author":"Hsu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"}],"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\/10448473.pdf?arnumber=10448473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:46:27Z","timestamp":1722660387000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448473","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}