{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:40:27Z","timestamp":1761061227522,"version":"3.37.3"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3050843","type":"journal-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T01:59:41Z","timestamp":1610503181000},"page":"13076-13082","source":"Crossref","is-referenced-by-count":6,"title":["Creating Song From Lip and Tongue Videos With a Convolutional Vocoder"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0693-6809","authenticated-orcid":false,"given":"Jianyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4430-8205","authenticated-orcid":false,"given":"Pierre","family":"Roussel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4572-1656","authenticated-orcid":false,"given":"Bruce","family":"Denby","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Singing voice synthesis based on convolutional neural networks","author":"nakamura","year":"2019","journal-title":"arXiv 1904 06868"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1250\/ast.39.163"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300376"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.1945807"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"article-title":"Développement d’algorithmes neuronaux pour synthétiser la parole á partir d’images échographiques de la langue et vidéo des lèvres","year":"2020","author":"pang","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref35","first-page":"4006","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1119-1"},{"key":"ref29","first-page":"3355","article-title":"Reconstructing intelligible audio speech from visual speech features","author":"le cornu","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178347"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2815268"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"journal-title":"Example Videos of CNN Synthesis and Ground Truth","year":"2020","key":"ref22"},{"key":"ref21","first-page":"128","article-title":"Recursion formula for calculation of mel generalized cepstrum coefficients","volume":"j71 a","author":"tokuda","year":"1988","journal-title":"IEICE Trans"},{"key":"ref24","article-title":"Audio-visual automatic speech recognition: An overview","author":"potamianos","year":"2004","journal-title":"Issues in Visual and Audio-Visual Speech Processing"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.1985.325564"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2738568"},{"key":"ref25","first-page":"2405","article-title":"Real-time control of a DNN-based articulatory synthesizer for silent speech conversion: A pilot study","author":"bocquelet","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2970241"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461732"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-385"},{"key":"ref40","first-page":"5ff","article-title":"Acoustic data analysis from multi-sensor capture in rare singing: Cantu in Paghjella case study","author":"crevier-buchman","year":"2014","journal-title":"Proc 1st Workshop ICT Preservation Transmiss Intangible Cultural Heritage Int Euro-Medit Conf Cultural Heritage (Euromed)"},{"key":"ref12","first-page":"593","article-title":"Statistical mapping between articulatory and acoustic data for an ultrasound-based silent speech interface","author":"hueber","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326078"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660033"},{"key":"ref15","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ab0c59"},{"key":"ref17","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv 1701 07875"},{"key":"ref19","article-title":"Ultrasound-based articulatory-to-acoustic mapping with WaveGlow speech synthesis","author":"csap\u00f3","year":"2020","journal-title":"arXiv 2008 03152"},{"key":"ref4","article-title":"Lip reading sentences in the wild","author":"chung","year":"2016","journal-title":"arXiv 1611 05358"},{"key":"ref3","first-page":"1149","article-title":"Lipreading using convolutional neural network","author":"noda","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2752365"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.4984122"},{"key":"ref7","first-page":"2288","article-title":"Robust articulatory speech synthesis using deep neural networks for BCI applications","author":"bocquelet","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952701"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref45","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"journal-title":"Example Audios of CNN Synthesis and Baseline Methods","year":"2020","key":"ref48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"article-title":"Modélisation et synthèse de voix chantée à partir de descripteurs visuels extraits d’images échographiques et optiques des articulateurs","year":"2016","author":"jaumard-hakoun","key":"ref42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2018.111144858"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref43"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09319643.pdf?arnumber=9319643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T15:12:56Z","timestamp":1643209976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9319643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3050843","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}