{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:21:30Z","timestamp":1761582090320,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673030,U1613209"],"award-info":[{"award-number":["61673030,U1613209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412817","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"7580-7586","source":"Crossref","is-referenced-by-count":9,"title":["Robust Audio-Visual Speech Recognition Based on Hybrid Fusion"],"prefix":"10.1109","author":[{"given":"Hong","family":"Liu","sequence":"first","affiliation":[]},{"given":"Wenhao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Bing","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_32"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.389"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2017-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683733"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"journal-title":"Hearing lips Improving lip reading by distilling speech recognizers","year":"2019","author":"zhao","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5120\/1384-1864"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2057231"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"journal-title":"Mutual information maximization for effective lip reading","year":"2020","author":"zhao","key":"ref27"},{"key":"ref3","first-page":"ii?2013","article-title":"A coupled hmm for audio-visual speech recognition","volume":"2","author":"nefian","year":"0","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2250954"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5772\/6364"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2520091"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.004"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","article-title":"Recent advances in the automatic recognition of audiovisual speech","volume":"91","author":"potamianos","year":"0","journal-title":"Proceedings of the IEEE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243014"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"journal-title":"LipNet End-to-End Sentence-level Lipreading","year":"2016","author":"assael","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451096"},{"journal-title":"Combining residual networks with lstms for lipreading","year":"2017","author":"stafylakis","key":"ref23"},{"journal-title":"Multi-grained spatio-temporal modeling for lip-reading","year":"2019","author":"wang","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.10.003"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412817.pdf?arnumber=9412817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:52Z","timestamp":1652197252000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412817","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}