{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T04:01:11Z","timestamp":1775448071718,"version":"3.50.1"},"reference-count":15,"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\/icassp43922.2022.9747284","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4848-4852","source":"Crossref","is-referenced-by-count":7,"title":["Meta Talk: Learning To Data-Efficiently Generate Audio-Driven Lip-Synchronized Talking Face With High Definition"],"prefix":"10.1109","author":[{"given":"Yuhan","family":"Zhang","sequence":"first","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China"}]},{"given":"Weihua","family":"He","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China"}]},{"given":"Minglei","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Language & Speech Innovation Lab,China"}]},{"given":"Kun","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China"}]},{"given":"Ziyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China"}]},{"given":"Jie","family":"Cheng","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China"}]},{"given":"Yaoyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China"}]},{"given":"Jianxing","family":"Liao","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2837742"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1109\/TVCG.2013.249","article-title":"Facewarehouse: A 3d facial expression database for visual computing","volume":"20","author":"cao","year":"2014","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383317"},{"key":"ref15","article-title":"Image-to-image translation with conditional adversarial networks","author":"isola","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3117484"},{"key":"ref5","first-page":"1","article-title":"Makelttalk","volume":"39","author":"zhou","year":"2020","journal-title":"ACM Transactions on Graphics"},{"key":"ref8","article-title":"FA-CIAL: synthesizing dynamic talking face with implicit attribute learning","volume":"abs 2108 7938","author":"zhang","year":"2021","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023573"},{"key":"ref1","first-page":"95.1","article-title":"Synthesizing obama: Learning lip sync from audio","volume":"36","year":"2017","journal-title":"ACM Transactions on Graphics"},{"key":"ref9","first-page":"1","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"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\/09747284.pdf?arnumber=9747284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:10Z","timestamp":1661199070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747284","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}