{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:20:41Z","timestamp":1777656041668,"version":"3.51.4"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054253","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"2143-2147","source":"Crossref","is-referenced-by-count":88,"title":["ASR is All You Need: Cross-Modal Distillation for Lip Reading"],"prefix":"10.1109","author":[{"given":"Triantafyllos","family":"Afouras","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref32","article-title":"Letter- based speech recognition with gated ConvNets","author":"liptchinsky","year":"2017","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682868"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00768"},{"key":"ref36","author":"kuchaiev","year":"2018","journal-title":"Mixed-precision training for nlp and speech recognition with openseq2seq"},{"key":"ref35","first-page":"604","article-title":"Acoustic modelling with CD-CTC-sMBR LSTM RNNs","author":"senior","year":"2015","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682671"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: A speaker-independent audiovisual model for speech separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM Transactions on Graphics"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref15","first-page":"513","article-title":"Audio-Visual Speech Recognition with a Hybrid CTC\/Attention Architecture","author":"petridis","year":"2018","journal-title":"IEEE Spoken Language Technology Workshop"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref18","article-title":"Lexicon-free conversational speech recognition with neural net- works","author":"maas","year":"2015","journal-title":"North American Chapter Of The Association For Computational Linguistics"},{"key":"ref19","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Deep Learning and Representation Learning Workshop NIPS"},{"key":"ref28","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref6","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref8","article-title":"The Spoken Wikipedia Corpus collection: Harvesting, alignment and an application to hyperlistening","author":"baumann","year":"2018","journal-title":"Language Resources and Evaluation"},{"key":"ref7","first-page":"5206","article-title":"Librispeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref2","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Proc ACCV"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref1","article-title":"Lipnet: Sentence-level lipreading","author":"assael","year":"2016"},{"key":"ref20","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref21","article-title":"Learning small- size DNN with output-distribution-based criteria","author":"li","year":"2014","journal-title":"InterSpeech"},{"key":"ref24","author":"kim","year":"2017","journal-title":"Improved training for online end-to-end speech recognition systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682775"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1952"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2182"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054253.pdf?arnumber=9054253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:08:05Z","timestamp":1656360485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054253","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}