{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:24:21Z","timestamp":1774419861831,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887982","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Diffused Poses and Distilled Expressions for Controllable Audio-driven Talking Face Generation"],"prefix":"10.1109","author":[{"given":"Ziqi","family":"Zhou","sequence":"first","affiliation":[{"name":"CAS University of Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weize","family":"Quan","sequence":"additional","affiliation":[{"name":"CAS University of Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaojin","family":"Lu","sequence":"additional","affiliation":[{"name":"Tellhow Group Co., LTD,Jiangxi Tellhow Animation College,Nanchang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong-Ming","family":"Yan","sequence":"additional","affiliation":[{"name":"CAS University of Chinese Academy of Sciences,MAIS, Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"You said that?","volume-title":"British Machine Vision Conference (BMVC)","author":"Chung"},{"key":"ref2","article-title":"End-to-end speech-driven realistic facial animation with temporal gans","volume-title":"Proc. of the IEEE International Conference on Computer Vision Workshops","author":"Vougioukas"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00416"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00703"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref9","article-title":"Vasa-1: Lifelike audio-driven talking faces generated in real time","author":"Xu","year":"2024"},{"key":"ref10","article-title":"Gaia: Zero-shot talking avatar generation","volume-title":"ICLR 2024","author":"He"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00049"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"International Conference on Learning Representations","author":"Simonyan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref23","first-page":"6629","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Heusel"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122293"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887982.pdf?arnumber=10887982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:05Z","timestamp":1774416305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887982","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}