{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:06:52Z","timestamp":1730297212258,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023442","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"723-730","source":"Crossref","is-referenced-by-count":1,"title":["Transformer-Based Lip-Reading with Regularized Dropout and Relaxed Attention"],"prefix":"10.1109","author":[{"given":"Zhengyang","family":"Li","sequence":"first","affiliation":[{"name":"Technische Universität Braunschweig, Institute for Communications Technology,Braunschweig,Germany,38106"}]},{"given":"Timo","family":"Lohrenz","sequence":"additional","affiliation":[{"name":"Technische Universität Braunschweig, Institute for Communications Technology,Braunschweig,Germany,38106"}]},{"given":"Matthias","family":"Dunkelberg","sequence":"additional","affiliation":[{"name":"Technische Universität Braunschweig, Institute for Communications Technology,Braunschweig,Germany,38106"}]},{"given":"Tim","family":"Fingscheidt","sequence":"additional","affiliation":[{"name":"Technische Universität Braunschweig, Institute for Communications Technology,Braunschweig,Germany,38106"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref35","article-title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","author":"pereyra","year":"2017","journal-title":"ArXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414920"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref37","article-title":"LRS3-TED: A Large-Scale Dataset for Visual Speech Recognition","author":"afouras","year":"2018","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-343"},{"key":"ref31","first-page":"177","article-title":"Re-laxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition","author":"lohrenz","year":"2021","journal-title":"Proc of ASRU"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref11","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref33","first-page":"1","article-title":"Frater-nal Dropout","author":"zolna","year":"2018","journal-title":"Proc of ICLR"},{"key":"ref10","first-page":"1","article-title":"Reducing Transformer Depth on Demand With Structured Dropout","author":"fan","year":"2020","journal-title":"Proc of ICLR virtual"},{"key":"ref32","first-page":"1","article-title":"Dropout With Expectation-Linear Regularization","author":"ma","year":"2017","journal-title":"Proc of ICLR"},{"key":"ref2","first-page":"87","article-title":"Lip Reading in the Wild","author":"chung","year":"2016","journal-title":"Proc of ACCV"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-019-01006-y"},{"key":"ref17","first-page":"796","article-title":"Audio-Visual Speech Recognition Is Worth 32×32×8 Voxels","author":"serdyuk","year":"2021","journal-title":"Proc of ASRU"},{"key":"ref39","first-page":"109.1","article-title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM Trans-actions on Graphics"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref38","first-page":"3833","article-title":"Rethinking Pre-Training and Self-Training","author":"zoph","year":"2020","journal-title":"Proc of NeurIPS virtual"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref18","article-title":"Transformer-Based Video Front-Ends for Audio-Visual Speech Recog-nition","author":"serdyuk","year":"2022","journal-title":"ArXiv"},{"key":"ref24","article-title":"When Does Label Smoothing Help?","author":"muller","year":"2020","journal-title":"ArXiv"},{"key":"ref23","first-page":"5041","article-title":"Exploring Trans-formers for Large-Scale Speech Recognition","author":"lu","year":"2020","journal-title":"Proc of Interspeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-555"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref21","first-page":"4171","article-title":"BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2019","journal-title":"Proc of NAACL-HLT"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","first-page":"10890","article-title":"R-Drop: Regularized Dropout for Neural Networks","author":"liang","year":"2021","journal-title":"Proc of NeurIPS virtual"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1223"},{"key":"ref29","article-title":"On Using Monolingual Corpora in Neural Machine Translation","author":"g\u00fclcehre","year":"2015","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref7","first-page":"1","article-title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","author":"shi","year":"2022","journal-title":"Proc of ICLR virtual"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref4","first-page":"1","article-title":"Deep Audio-Visual Speech Recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref6","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"ArXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023442.pdf?arnumber=10023442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:53Z","timestamp":1676912933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023442","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}