{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:36:04Z","timestamp":1785501364976,"version":"3.56.0"},"reference-count":101,"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\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/M507878\/1"],"award-info":[{"award-number":["EP\/M507878\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N509486\/1"],"award-info":[{"award-number":["EP\/N509486\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3382500","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T19:32:22Z","timestamp":1711567942000},"page":"2255-2268","source":"Crossref","is-referenced-by-count":3,"title":["Large-Scale Unsupervised Audio Pre-Training for Video-to-Speech Synthesis"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4414-5768","authenticated-orcid":false,"given":"Triantafyllos","family":"Kefalas","sequence":"first","affiliation":[{"name":"Department of Computing, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0153-5210","authenticated-orcid":false,"given":"Yannis","family":"Panagakis","sequence":"additional","affiliation":[{"name":"Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3162495"},{"issue":"4","key":"ref7","first-page":"270","article-title":"Silent speech interfaces","volume-title":"Speech Commun.","volume":"52","author":"Denby","year":"2010"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-139"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref12","first-page":"2758","article-title":"Lip to speech synthesis with visual context attentional GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kim","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414040"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616266"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10770"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3548636.3548648"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00718"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1445"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3191677"},{"key":"ref21","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ardila","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-017-9410-y"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref26","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"Univ. Edinburgh, Centre Speech Technol. Res."},{"key":"ref27","first-page":"6532","article-title":"Open-source multi-speaker corpora of the english accents in the british isles","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Demirsahin","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","first-page":"5903","article-title":"100,000 podcasts: A spoken english document corpus","volume-title":"Proc. 28th Int. Conf. Comput. Linguistics","author":"Clifton","year":"2020"},{"key":"ref30","first-page":"1","article-title":"The Boston University radio news corpus","author":"Ostendorf","year":"1995","journal-title":"Linguistic Data Consortium"},{"key":"ref31","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mache Learn.","author":"Arjovsky","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref33","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref36","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref40","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2019"},{"key":"ref41","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Ioffe","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2026513"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1998.999008"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ChiCC.2016.7554449"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2012.192"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2030637"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-293"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.69"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472172"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-721"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472088"},{"key":"ref56","article-title":"LipNet: End-to-end sentence-level lipreading","author":"Assael","year":"2016"},{"key":"ref57","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952625"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.01.022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1669"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-85"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3107946"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02511-4"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2716178"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1026"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref72","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3126925"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref75","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref76","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref77","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 33: Annu. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref78","article-title":"Denoising diffusion implicit models","volume-title":"Proc. 9th Int. Conf. Learn. Representations, Virtual Event","author":"Song","year":"2021"},{"key":"ref79","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia","year":"2018"},{"key":"ref80","article-title":"Real-time-voice-cloning","author":"Jemine","year":"2019"},{"key":"ref81","article-title":"Real-time voice cloning","year":"2018"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref83","doi-asserted-by":"crossref","DOI":"10.5244\/C.28.6","article-title":"Return of the devil in the details: Delving deep into convolutional nets","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chatfield","year":"2014"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref85","article-title":"VGG-M face","year":"2020"},{"key":"ref86","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref88","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref89","article-title":"Training speech enhancement systems with noisy speech datasets","author":"Saito","year":"2021"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.30"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref92","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022766"},{"key":"ref94","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref95","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10480633.pdf?arnumber=10480633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T18:09:29Z","timestamp":1716919769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10480633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":101,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3382500","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}