{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:08:24Z","timestamp":1775228904092,"version":"3.50.1"},"reference-count":28,"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\/icassp39728.2021.9414553","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"3430-3434","source":"Crossref","is-referenced-by-count":12,"title":["Fusing Information Streams in End-to-End Audio-Visual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Wentao","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steffen","family":"Zeiler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorothea","family":"Kolossa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref11","first-page":"23","article-title":"Audio-visual automatic speech recognition: An overview","volume":"22","author":"potamianos","year":"2004","journal-title":"Issues in Visual and Audio-Visual Speech Processing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953172"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2172427"},{"key":"ref14","article-title":"Ro-bust audiovisual speech recognition using noise-adaptive linear discriminant analysis","author":"zeiler","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref15","article-title":"Multimodal integration for large-vocabulary audio-visual speech recognition","author":"yu","year":"2020","journal-title":"Proc EUSIPCO"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853589"},{"key":"ref18","article-title":"Combining residual net-works with LSTMs for lipreading","author":"stafylakis","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/357311.357312"},{"key":"ref28","first-page":"5206","article-title":"Lib-riSpeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref27","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref7","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.1396-16.2016"},{"key":"ref1","article-title":"RWTH ASR systems for LibriSpeech: Hybrid vs attention-w\/o data augmentation","author":"l\u00fcscher","year":"2019"},{"key":"ref20","first-page":"1","article-title":"Openface: an open source facial behavior analysis toolkit","author":"baltru\u0161aitis","year":"2016","journal-title":"IEEE Winter Conference on Applications of Computer Vision"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.06.002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980436"},{"key":"ref24","article-title":"A study on the effect of pitch on LPCC and PLPC features for children’s ASR in comparison to MFCC","author":"ghai","year":"2011","journal-title":"Twelfth Annual Conference of ISCA"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876776"},{"key":"ref26","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854049"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"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\/09414553.pdf?arnumber=9414553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:02Z","timestamp":1652197262000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414553","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}