{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:09:33Z","timestamp":1773414573612,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"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":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093527","type":"proceedings-article","created":{"date-parts":[[2020,5,15]],"date-time":"2020-05-15T03:41:09Z","timestamp":1589514069000},"page":"3279-3287","source":"Crossref","is-referenced-by-count":34,"title":["Animating Face using Disentangled Audio Representations"],"prefix":"10.1109","author":[{"given":"Gaurav","family":"Mittal","sequence":"first","affiliation":[]},{"given":"Baoyuan","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref30","article-title":"End-to-end speech-driven facial animation with temporal gans","author":"vougioukas","year":"2018","journal-title":"arXiv preprint arXiv 1805 09313"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref14","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","author":"ephrat","year":"2018","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"ref16","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"5767","article-title":"Improved training of wasserstein gans","author":"gulrajani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv preprint arXiv 1412 5567"},{"key":"ref19","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1145\/3072959.3073640","article-title":"Synthesizing obama: learning lip sync from audio","volume":"36","author":"suwajanakorn","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref27","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref6","first-page":"520","article-title":"Lip movements generation at a glance","author":"chen","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref5","article-title":"Everybody dance now","author":"chan","year":"2018","journal-title":"arXiv preprint arXiv 1808 02194"},{"key":"ref8","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref7","article-title":"You said that?","author":"chung","year":"2017","journal-title":"BMVC"},{"key":"ref2","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018","journal-title":"arXiv preprint arXiv 1809 00496"},{"key":"ref9","first-page":"251","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1145\/3072959.3073658","article-title":"Audio-driven facial animation by joint end-to-end learning of pose and emotion","volume":"36","author":"karras","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref21","article-title":"Speech-driven facial reenactment using conditional generative adversarial networks","author":"jalalifar","year":"2018","journal-title":"arXiv preprint arXiv 1803 07461"},{"key":"ref24","article-title":"Obamanet: Photo-realistic lip-sync from text","author":"kumar","year":"2017","journal-title":"arXiv preprint arXiv 1801 04144"},{"key":"ref23","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818122"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Snowmass Village, CO, USA","start":{"date-parts":[[2020,3,1]]},"end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093527.pdf?arnumber=9093527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:15:54Z","timestamp":1656602154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093527","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}