{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T14:42:20Z","timestamp":1783608140916,"version":"3.55.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746706","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8472-8476","source":"Crossref","is-referenced-by-count":50,"title":["Training Strategies for Improved Lip-Reading"],"prefix":"10.1109","author":[{"given":"Pingchuan","family":"Ma","sequence":"first","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stavros","family":"Petridis","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Shen","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Imperial College London,Department of Computing,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00290"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref13","first-page":"1602","article-title":"Born-again neural networks","author":"furlanello","year":"2018","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref16","article-title":"Decoupled Weight Decay Regularization","author":"loshchilov","year":"2019","journal-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR)"},{"key":"ref17","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-1386805\/v1","article-title":"Visual Speech Recognition for Multiple Languages in the Wild","author":"ma","year":"2022"},{"key":"ref19","first-page":"269","article-title":"Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading","author":"weng","year":"2019","journal-title":"Proceedings of the British Machine Vision Conference (BMVC)"},{"key":"ref4","article-title":"Learn an Effective Lip Reading Model without Pains","author":"feng","year":"2020","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00134"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.cviu.2018.10.003","article-title":"Pushing the Boundaries of Audiovisual Word Recognition using Residual Networks and LSTMs","volume":"176?177","author":"stafylakis","year":"2018","journal-title":"Computer Vision and Image Understanding"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref1","first-page":"87","article-title":"Lip Reading in the Wild","volume":"10112","author":"chung","year":"2016","journal-title":"Proceedings of the 13th Asian Conference on Computer Vision (ACCV)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746706.pdf?arnumber=9746706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:08:32Z","timestamp":1660594112000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746706","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}