{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:43:10Z","timestamp":1781584990401,"version":"3.54.5"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747427","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7252-7256","source":"Crossref","is-referenced-by-count":8,"title":["VCVTS: Multi-Speaker Video-to-Speech Synthesis Via Cross-Modal Knowledge Transfer from Voice Conversion"],"prefix":"10.1109","author":[{"given":"Disong","family":"Wang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent AI lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[{"name":"Tencent AI lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref32","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1710 09412"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1026"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012588"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1445"},{"key":"ref14","article-title":"End-to-end video-to-speech synthesis using generative adversarial networks","author":"mira","year":"2021","journal-title":"arXiv preprint arXiv 2104 13332"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414040"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616266"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref19","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"arXiv preprint arXiv 1910 05453"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/MVA.2017.7986914"},{"key":"ref27","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":"ref3","article-title":"Lip-to-speech synthesis using locality-constraint non-negative matrix factorization","author":"aihara","year":"2015","journal-title":"Proc MLSLP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2716178"},{"key":"ref8","article-title":"Exemplar-based lip-to-speech synthesis using convolutional neural networks","author":"takashima","year":"2019","journal-title":"Proc IW-FCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.03.005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241911"},{"key":"ref1","first-page":"3355","article-title":"Reconstructing intelligible audio speech from visual speech features","author":"milner","year":"2015","journal-title":"InterSpeech"},{"key":"ref20","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref22","first-page":"4836","article-title":"Vectorquantized neural networks for acoustic unit discovery in the zerospeech 2020 challenge","author":"van niekerk","year":"2020","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317318938"},{"key":"ref23","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv preprint arXiv 1807 03748"},{"key":"ref26","first-page":"1779","article-title":"Club: A contrastive log-ratio upper bound of mutual information","author":"cheng","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85053-3_27"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747427.pdf?arnumber=9747427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:32Z","timestamp":1660593932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747427","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}