{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:48:54Z","timestamp":1777164534532,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683733","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6565-6569","source":"Crossref","is-referenced-by-count":52,"title":["Modality Attention for End-to-end Audio-visual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Pan","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","first-page":"971","article-title":"Self-normalizing neural networks","author":"klambauer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543246"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2001.1237849"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1327261"},{"key":"ref15","article-title":"Lipreading using convolutional neural network","author":"noda","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952701"},{"key":"ref17","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472852"},{"key":"ref19","article-title":"Lipnet: Sentence-level lipreading","author":"assael","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1536"},{"key":"ref4","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1301"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref29","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"e king","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref8","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1109\/ASRU.2017.8268935","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer","author":"rao","year":"2017","journal-title":"IEEE Autom Speech Recognition Understanding Workshop (ASRU)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref9","article-title":"End-to-end continuous speech recognition using attention-based recurrent nn: first results","author":"chorowski","year":"2014"},{"key":"ref1","article-title":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chiu","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2459017"},{"key":"ref21","author":"david petajan","year":"1984","journal-title":"Automatic lipreading to enhance speech recognition (speech reading)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683733.pdf?arnumber=8683733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:16:10Z","timestamp":1657854970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683733","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}