{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T23:04:10Z","timestamp":1784847850933,"version":"3.55.0"},"reference-count":18,"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\/icassp43922.2022.9747380","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"2659-2663","source":"Crossref","is-referenced-by-count":32,"title":["Text2video: Text-Driven Talking-Head Video Synthesis with Personalized Phoneme - Pose Dictionary"],"prefix":"10.1109","author":[{"given":"Sibo","family":"Zhang","sequence":"first","affiliation":[{"name":"Baidu Research,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahong","family":"Yuan","sequence":"additional","affiliation":[{"name":"Baidu Research,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Liao","sequence":"additional","affiliation":[{"name":"Baidu Research,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Research,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3306346.3323035","article-title":"Deferred neural rendering: Image synthesis using neural textures","volume":"38","author":"thies","year":"2019","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref13","article-title":"On the Acoustic Structure of Diphthongal Syllables","author":"ren","year":"1986","journal-title":"Ph D thesis"},{"key":"ref14","article-title":"OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields","author":"cao","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.2935783"},{"key":"ref16","article-title":"Video-to-video synthesis","author":"wang","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01793-3_21"},{"key":"ref18","article-title":"Timit acoustic-phonetic continuous speech corpus","author":"garofolo","year":"1992","journal-title":"Linguistic Data Consortium"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008166717597"},{"key":"ref3","article-title":"Speech2video synthesis with 3d skeleton regularization and expressive body poses","author":"liao","year":"2020","journal-title":"Proceedings of the Asian Conference on Computer Vision"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref5","first-page":"275","article-title":"Dynamic units of visual speech","author":"taylor","year":"2012","journal-title":"Proceedings of the 11th ACM SIGGRAPH\/Eurographics conference on Computer Animation"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref2","article-title":"Neural voice puppetry: Audio-driven facial reenactment","author":"thies","year":"2019"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2304"}],"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\/09747380.pdf?arnumber=9747380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:44Z","timestamp":1660594064000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747380","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}