{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:21:32Z","timestamp":1761582092356},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414160","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6863-6867","source":"Crossref","is-referenced-by-count":8,"title":["A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection"],"prefix":"10.1109","author":[{"given":"Otavio","family":"Braga","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Siohan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Artificial Intelligence at Google Our Principles","year":"0","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref12","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"0","author":"bahdanau","key":"ref13"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ICML"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","year":"2018","author":"afouras","key":"ref19"},{"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":"10.1109\/ICASSP.2019.8682524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref2","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053974"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"article-title":"Adam: A method for stochastic optimization","year":"0","author":"kingma","key":"ref21"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414160.pdf?arnumber=9414160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:58Z","timestamp":1652197258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414160","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}