{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:50:05Z","timestamp":1785603005972,"version":"3.56.0"},"reference-count":34,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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\/icassp49660.2025.10889839","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":3,"title":["RQTalker: Speech-driven 3D Facial Animation via Region-aware Vector Quantization"],"prefix":"10.1109","author":[{"given":"Yingying","family":"Fan","sequence":"first","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaisiyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc.,VIS,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Baidu Inc.,VIS,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengyi","family":"He","sequence":"additional","affiliation":[{"name":"Baidu Inc.,VIS,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511843891.014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2312\/SCA\/SCA12\/275-284"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2522628.2522904"},{"key":"ref5","article-title":"Learning audio-driven viseme dynamics for 3d face animation","author":"Bao","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01821"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01891"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2017.287"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27945"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3409568"},{"key":"ref20","article-title":"Dillspeaker: Speech-driven 3d lacial animation with dillusion translormer","author":"Ma","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3522615"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32449"},{"key":"ref23","first-page":"348","article-title":"Resyncer: Rewiring style-based generator lor unified audio-visually synced lacial perlormer","volume-title":"European Conference on Computer Vision","author":"Guan"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3521701"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446842"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581920"},{"key":"ref27","article-title":"Emolace: Emotion-content disentangled speech-driven 3d talking lace with mesh attention","author":"Lin","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657413"},{"key":"ref29","article-title":"Revisit weakly-supervised audio-visual video parsing lrom the language perspective","volume":"36","author":"Fan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591509"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25354"},{"key":"ref33","first-page":"12 449","article-title":"wav2vec 2.0: A lramework lor sell-supervised learning ol speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/83.623193"}],"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\/10889839.pdf?arnumber=10889839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:03Z","timestamp":1774416123000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889839","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}