{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T16:42:52Z","timestamp":1788540172237,"version":"build-2803163510"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1718944"],"award-info":[{"award-number":["IIS-1718944"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.2975922","type":"journal-article","created":{"date-parts":[[2020,2,28]],"date-time":"2020-02-28T22:19:51Z","timestamp":1582928391000},"page":"1-11","source":"Crossref","is-referenced-by-count":78,"title":["End-to-End Audiovisual Speech Recognition System With Multitask Learning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4834-8949","authenticated-orcid":false,"given":"Fei","family":"Tao","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4075-4072","authenticated-orcid":false,"given":"Carlos","family":"Busso","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486455"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2459017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3015783.3015797"},{"key":"ref37","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846321"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2405481"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-446"},{"key":"ref27","first-page":"1500","article-title":"Audio-visual isolated digit recognition for whispered speech","author":"fan","year":"2011","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-406"},{"key":"ref2","article-title":"Audio-visual speech recognition","author":"neti","year":"2000"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1391"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461617"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461750"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-500"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-81"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2815268"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639243"},{"key":"ref57","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref56","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref55","first-page":"1","article-title":"SailAlign: Robust long speech-text alignment","author":"katsamanis","year":"2011","journal-title":"Proc Workshop New Tools Methods Very-Large Scale Phonetics Res"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.07.003"},{"key":"ref53","article-title":"Python speech features","author":"lyons","year":"2016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.75"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2017.07.006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2520091"},{"key":"ref13","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref15","first-page":"1","article-title":"Robust end-to-end deep audiovisual speech recognition","author":"sanabria","year":"2016","journal-title":"arXiv 1611 06986"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2464"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2867099"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.21437\/Interspeech.2017-1494","article-title":"Jointly predicting arousal, valence and dominance with multi-task learning","author":"parthasarathy","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2875510"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2859590"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2557721"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482228"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2490"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2241416"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"3652","DOI":"10.21437\/Interspeech.2017-85","article-title":"Combining residual networks with LSTMs for lipreading","author":"stafylakis","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472088"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref47","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","first-page":"151","article-title":"Voice activity detection based on fusion of audio and visual information","author":"takeuchi","year":"2009","journal-title":"Proc Int Conf Audio-Visual Speech Process"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CIDM.2013.6597233"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1573"},{"key":"ref43","first-page":"1","article-title":"Using audio-visual features for robust voice activity detection in clean and noisy speech","author":"almajai","year":"2008","journal-title":"Proc Eur Signal Process Conf"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6046\/9296985\/9018185-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09018185.pdf?arnumber=9018185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T18:36:21Z","timestamp":1671734181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9018185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.2975922","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}