{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T02:30:49Z","timestamp":1775010649715,"version":"3.50.1"},"reference-count":34,"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\/icassp49357.2023.10095029","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":5,"title":["Self-Supervised Audio-Visual Speech Representations Learning by Multimodal Self-Distillation"],"prefix":"10.1109","author":[{"given":"Jing-Xuan","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Genshun","family":"Wan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, iFLYTEK Co. Ltd.,China"}]},{"given":"Jianqing","family":"Gao","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, iFLYTEK Co. Ltd.,China"}]},{"given":"Cong","family":"Liu","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, iFLYTEK Co. Ltd.,China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref15","article-title":"BEiT: BERT pre-training of image transformers","author":"bao","year":"2022","journal-title":"ICLRE"},{"key":"ref14","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref31","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556571"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref33","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref32","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.brainres.2007.01.074"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"shi","year":"2022","journal-title":"ICLRE"},{"key":"ref23","first-page":"7025","article-title":"Contrastive learning of global and local video representations","volume":"34","author":"ma","year":"2021","journal-title":"NeurIPS"},{"key":"ref26","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"2017","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref20","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume":"162","author":"baevski","year":"2022","journal-title":"ICML"},{"key":"ref22","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume":"33","author":"alwassel","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume":"31","author":"korbar","year":"2018","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref27","first-page":"726","article-title":"Momentum pseudo-labeling for semi-supervised speech recognition","author":"higuchi","year":"2021","journal-title":"InterSpeech"},{"key":"ref29","article-title":"Image BERT pre-training with online tokenizer","author":"zhou","year":"2022","journal-title":"ICLRE"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref9","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472852"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"14402","DOI":"10.1609\/aaai.v35i16.17693","article-title":"TaL-Net: Voice reconstruction from tongue and lip articulation with transfer learning from text-to-speech synthesis","volume":"35","author":"zhang","year":"2021","journal-title":"AAAI"},{"key":"ref5","first-page":"3652","article-title":"Combining residual networks with LSTMs for lipreading","author":"georgios","year":"2017","journal-title":"InterSpeech"}],"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\/10095029.pdf?arnumber=10095029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:58:51Z","timestamp":1699883931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095029","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}