{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:23:08Z","timestamp":1761582188677},"reference-count":24,"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\/icassp43922.2022.9746036","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6047-6051","source":"Crossref","is-referenced-by-count":9,"title":["Best of Both Worlds: Multi-Task Audio-Visual Automatic Speech Recognition and Active Speaker Detection"],"prefix":"10.1109","author":[{"given":"Otavio","family":"Braga","sequence":"first","affiliation":[{"name":"Google, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Siohan","sequence":"additional","affiliation":[{"name":"Google, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053974"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414160"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref15","first-page":"3","article-title":"Group normalization","author":"wu","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref16","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 San Diego CA USA May 7-9 2015 Conference Track Proceedings"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2006.326841"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref7","article-title":"Audio-visual speech recognition is worth 32x32x8 voxels","author":"serdyuk","year":"2021","journal-title":"CoRR"},{"key":"ref2","first-page":"1","article-title":"Deep audiovisual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref1","article-title":"Recurrent neural network transducer for audiovisual speech recognition","author":"makino","year":"2019","journal-title":"ASRU"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 San Diego CA USA May 7-9 2015 Conference Track Proceedings"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","year":"2018","author":"afouras","key":"ref23"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09746036.pdf?arnumber=9746036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:06:58Z","timestamp":1660594018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746036","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}