{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T05:03:24Z","timestamp":1790399004258,"version":"4.1.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682970","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"8633-8637","source":"Crossref","is-referenced-by-count":62,"title":["Wav2Pix: Speech-conditioned Face Generation Using Generative Adversarial Networks"],"prefix":"10.1109","author":[{"given":"Amanda","family":"Duarte","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisco","family":"Roldan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miquel","family":"Tubau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janna","family":"Escur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Santiago","family":"Pascual","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amaia","family":"Salvador","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eva","family":"Mohedano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"McGuinness","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordi","family":"Torres","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Giro-i-Nieto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Wasserstein generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"ICML"},{"key":"ref11","article-title":"Began: boundary equilibrium generative adversarial networks","author":"berthelot","year":"2017","journal-title":"arXiv preprint arXiv 1703 10717"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref13","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2016","journal-title":"ICLRE"},{"key":"ref14","article-title":"Conditional image synthesis with auxiliary classifier gans","author":"odena","year":"2017","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref19","article-title":"End-to-end speech-driven facial animation with temporal gans","author":"vougioukas","year":"2018","journal-title":"BMVC"},{"key":"ref28","article-title":"Vggface2: A dataset for recognizing faces across pose and age","volume":"abs 1710 8092","author":"cao","year":"2017"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref27","article-title":"Deep face recognition","author":"parkhi","year":"2015","journal-title":"BMVC"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref6","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014","journal-title":"arXiv preprint arXiv 1411 1784"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.241"},{"key":"ref5","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref7","article-title":"Generative adversarial text to image synthesis","author":"reed","year":"2016","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref9","article-title":"Large scale gan training for high fidelity natural image synthesis","author":"brock","year":"2019","journal-title":"ICLRE"},{"key":"ref1","article-title":"You said that?","author":"chung","year":"2017","journal-title":"BMVC"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref24","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017"},{"key":"ref23","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018","journal-title":"ICLRE"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref25","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"heusel","year":"2017","journal-title":"NIPS"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682970.pdf?arnumber=8682970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:11:37Z","timestamp":1657840297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682970","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}