{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T13:30:39Z","timestamp":1777901439020,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":["U1736202"],"award-info":[{"award-number":["U1736202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771461"],"award-info":[{"award-number":["61771461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2019B090915002"],"award-info":[{"award-number":["2019B090915002"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Fundamental Research Program","award":["JCYJ20160429184226930"],"award-info":[{"award-number":["JCYJ20160429184226930"]}]},{"name":"Shenzhen Fundamental Research Program","award":["JCYJ20170413161611534"],"award-info":[{"award-number":["JCYJ20170413161611534"]}]},{"name":"Shenzhen Fundamental Research Program","award":["KQJSCX20170731163308665"],"award-info":[{"award-number":["KQJSCX20170731163308665"]}]},{"DOI":"10.13039\/501100004853","name":"Chinese University of Hong Kong","doi-asserted-by":"publisher","award":["4055065"],"award-info":[{"award-number":["4055065"]}],"id":[{"id":"10.13039\/501100004853","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006355","name":"Shun Hing Institute of Advanced Engineering","doi-asserted-by":"publisher","award":["MMT-p1-19"],"award-info":[{"award-number":["MMT-p1-19"]}],"id":[{"id":"10.13039\/501100006355","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong Research Grants Council General Research","award":["14200218"],"award-info":[{"award-number":["14200218"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2019.2950602","type":"journal-article","created":{"date-parts":[[2019,10,31]],"date-time":"2019-10-31T21:41:16Z","timestamp":1572558076000},"page":"185-197","source":"Crossref","is-referenced-by-count":17,"title":["Cross-Domain Deep Visual Feature Generation for Mandarin Audio\u2013Visual Speech Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7228-5768","authenticated-orcid":false,"given":"Rongfeng","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6725-1160","authenticated-orcid":false,"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5092-6739","authenticated-orcid":false,"given":"Jingzhou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref38","first-page":"190","article-title":"Training and analysing deep recurrent neural networks","author":"hermans","year":"0","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918453"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1063"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1121\/1.4781490"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/cav.80"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2815268"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462028"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.03.003"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.1498851"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"ref20","first-page":"1482","article-title":"Audio-to-visual speech conversion using deep neural networks","author":"taylor","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","first-page":"1497","article-title":"Deep neural network based acoustic-to-articulatory inversion using phone sequence information","author":"xie","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178812"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639049"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2103058"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953149"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854154"},{"key":"ref50","first-page":"3145","article-title":"The Cambridge University 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translation","author":"liu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415245"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.07.010"},{"key":"ref52","first-page":"3224","article-title":"Parameterised sigmoid and RELU hidden activation functions for DNN acoustic modeling","author":"zhang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2010.5662075"},{"key":"ref11","first-page":"51","article-title":"Audio-visual speech recognition for people with speech disorders","volume":"96","author":"salama","year":"2014","journal-title":"Int J Comput Appl"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2197\/ipsjtcva.7.64"},{"key":"ref13","first-page":"77","article-title":"Audio-visual speech recognition for a person with severe hearing loss using deep canonical correlation analysis","author":"takashima","year":"0","journal-title":"Proc 1st Int Workshop Challenges Hear Assist Technol"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1038\/264746a0","article-title":"Hearing lips and seeing voices","volume":"264","author":"mcgurk","year":"1976","journal-title":"Nature"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-412"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-015-0499-9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424210"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011171430700"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.843341"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"key":"ref3","first-page":"689","article-title":"Integration of deep bottleneck features for audio-visual speech recognition","author":"ninomiya","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2018.06.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683733"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682566"},{"key":"ref49","first-page":"3221","article-title":"Accelerating t-SNE using tree-based algorithms","volume":"15","author":"maaten","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref9","first-page":"185","article-title":"A robust speech disorders correction system for Arabic language using visual speech recognition","volume":"24","author":"farag","year":"2013","journal-title":"Biomed Res"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430155"},{"key":"ref45","first-page":"3366","article-title":"Exploring convolutional neural network structures and optimization techniques for speech recognition","author":"abdel-hamid","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518613"},{"key":"ref42","author":"young","year":"2009","journal-title":"The HTK Book"},{"key":"ref41","first-page":"2345","article-title":"Sequence-discriminative training of deep neural networks","author":"vesel\u00fd","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref44","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08888180.pdf?arnumber=8888180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:23Z","timestamp":1651080683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8888180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2950602","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}