{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:45:26Z","timestamp":1771458326878,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"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":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093314","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"1626-1635","source":"Crossref","is-referenced-by-count":5,"title":["Watch to Listen Clearly: Visual Speech Enhancement Driven Multi-modality Speech Recognition"],"prefix":"10.1109","author":[{"given":"Bo","family":"Xu","sequence":"first","affiliation":[]},{"given":"Jacob","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Cheng","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Yandong","family":"Guo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.1121\/1.2229005","article-title":"An audio-visual corpus for speech perception and automatic speech recognition","volume":"120","author":"martin","year":"2006","journal-title":"Journal of the Acoustical Society of America"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366941"},{"key":"ref30","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref37","first-page":"1","article-title":"Learning representations by back-propagating errors","volume":"5","author":"rumelhart","year":"1988","journal-title":"Nature"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref34","author":"petajan","year":"1985","journal-title":"Automatic lipreading to enhance speech recognition (speech reading)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref1","author":"abadi","year":"2016","journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.1104.796"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref23","article-title":"Visual speech enhancement","author":"gabbay","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref15","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref16","first-page":"251","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-016-0438-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3758\/BF03204211"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref5","article-title":"Lrs3-ted: A large-scale dataset for visual speech recognition","author":"afouras","year":"2018"},{"key":"ref8","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref7","article-title":"Lipnet: End-to-end sentence-level lipreading","author":"assael","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.004"},{"key":"ref9","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.0303.212"},{"key":"ref45","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref48","article-title":"Eleatt-rnn: Adding attentiveness to neurons in recurrent neural networks","author":"zhang","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref43","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Snowmass Village, CO, USA","start":{"date-parts":[[2020,3,1]]},"end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093314.pdf?arnumber=9093314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:17:57Z","timestamp":1656602277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093314","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}