{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:03:19Z","timestamp":1780635799957,"version":"3.54.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006180","name":"Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006180","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1109\/ijcb65343.2025.11411575","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:50:39Z","timestamp":1772571039000},"page":"1-10","source":"Crossref","is-referenced-by-count":5,"title":["DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Ma","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,MAIS, Institute of Automation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Qian","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shukai","family":"Chen","sequence":"additional","affiliation":[{"name":"ZKTeco Co., Ltd"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Gao","sequence":"additional","affiliation":[{"name":"China Mobile Financial Technology Co., Ltd"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guojun","family":"Qi","sequence":"additional","affiliation":[{"name":"WestLake University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,MAIS, Institute of Automation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,MAIS, Institute of Automation"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Diffusiontalker: Personalization and acceleration for speech-driven 3d face diffuser","author":"Chen","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref7","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01821"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref17","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511843891.014"},{"key":"ref20","article-title":"Df-3dface: One-to-many speech synchronized 3d face animation with diffusion","author":"Park","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref22","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","author":"Press","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612307"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref31","article-title":"3di-face: Diffusion-based speech-driven 3d facial animation and editing","author":"Thambiraja","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"}],"event":{"name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","location":"Osaka, Japan","start":{"date-parts":[[2025,9,8]]},"end":{"date-parts":[[2025,9,11]]}},"container-title":["2025 IEEE International Joint Conference on Biometrics (IJCB)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11410556\/11410616\/11411575.pdf?arnumber=11411575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T07:26:31Z","timestamp":1772609191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11411575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcb65343.2025.11411575","relation":{},"subject":[],"published":{"date-parts":[[2025,9,8]]}}}