{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T02:26:24Z","timestamp":1783650384311,"version":"3.55.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62171427"],"award-info":[{"award-number":["62171427"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3390148","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T17:35:25Z","timestamp":1713375325000},"page":"9358-9371","source":"Crossref","is-referenced-by-count":6,"title":["Collaborative Viseme Subword and End-to-End Modeling for Word-Level Lip Reading"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0904-8946","authenticated-orcid":false,"given":"Hang","family":"Chen","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3843-3920","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2387-0389","authenticated-orcid":false,"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5813-9430","authenticated-orcid":false,"given":"Gen-Shun","family":"Wan","sequence":"additional","affiliation":[{"name":"iFlytek Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4759-147X","authenticated-orcid":false,"given":"Shi-Fu","family":"Xiong","sequence":"additional","affiliation":[{"name":"iFlytek Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4164-6647","authenticated-orcid":false,"given":"Bao-Ci","family":"Yin","sequence":"additional","affiliation":[{"name":"iFlytek Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7073-1744","authenticated-orcid":false,"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFlytek Research, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1892-2551","authenticated-orcid":false,"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242599"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0b013e31812f7185"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746683"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10483"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10433931"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.06.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9456014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-723"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.10.003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2210952"},{"key":"ref18","first-page":"1","article-title":"Audio-visual speech recognition","volume-title":"Proc. Workshop Final Rep.","author":"Neti","year":"2000"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-281"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2030637"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.877528"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF00133570"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2520091"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414659"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging7050091"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747729"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref30","first-page":"1","article-title":"Multi-grained spatio-temporal modeling for lip-reading","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Wang","year":"2019"},{"key":"ref31","first-page":"1","article-title":"Learning spatiotemporal features with two-stream deep 3D CNNs for lipreading","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Weng","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00132"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3146"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3102433"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00010"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00134"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00290"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00133"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3210761"},{"key":"ref44","first-page":"1","article-title":"Synchronous bidirectional learning for multilingual lip reading","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Luo","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.4324\/9780203784969"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.1104.796"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1121\/1.389537"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45683-X_60"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.2007.143040"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"ref54","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kendall","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943604"},{"issue":"175","key":"ref57","first-page":"118","article-title":"The HTK book","volume":"3","author":"Young","year":"2002","journal-title":"Cambridge Univ. Eng. Dept."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref59","first-page":"1","article-title":"The kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref60","first-page":"1","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref61","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00281"},{"issue":"11","key":"ref63","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10504606.pdf?arnumber=10504606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T04:05:23Z","timestamp":1725163523000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3390148","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}