{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T08:19:35Z","timestamp":1787559575057,"version":"build-2736575974"},"reference-count":34,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":2,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Animation &amp; Virtual"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Speech\u2010driven 3D facial animation has achieved remarkable lip\u2010synchronization. However, generating expressive and personalized animations remains a formidable challenge. Existing methods often struggle with the entanglement of emotion and speaking style, as well as semantic conflicts arising from multi\u2010modal inputs. To address these limitations, we propose\n                    <jats:italic>DESTalker<\/jats:italic>\n                    , a framework that disentangles emotion and style to generate expressive facial motion via residual modulation. We introduce an information\u2010theoretic disentanglement strategy utilizing mutual information minimization and orthogonal constraints to robustly separate audio content, motion emotion, and speaking style. Furthermore, we adopt a residual generation strategy where neutral lip\u2010sync motion is synthesized first, followed by the injection of emotion and style as residual components to preserve articulatory precision. Finally, to resolve cross\u2010modal conflicts, we design a semantic consistency\u2010guided soft\u2010gating mechanism that dynamically regulates visual emotion integration under audio dominance. Extensive experiments on the 3DMEAD dataset demonstrate that DESTalker outperforms state\u2010of\u2010the\u2010art methods in emotional expressiveness, style consistency, and lip\u2010synchronization accuracy.\n                  <\/jats:p>","DOI":"10.1002\/cav.70127","type":"journal-article","created":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T05:53:09Z","timestamp":1783144389000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>DESTalker<\/scp>\n                    : Disentangling Emotion and Style for Expressive\n                    <scp>3D<\/scp>\n                    Facial Animation via Residual Generation"],"prefix":"10.1002","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2101-0899","authenticated-orcid":false,"given":"Xu","family":"Yang","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University  Tianjin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2353-5318","authenticated-orcid":false,"given":"Shiguang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University  Tianjin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University  Tianjin China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3677388.3696320"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR58804.2024.00060"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27945"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB65343.2025.11411575"},{"key":"e_1_2_10_16_1","unstructured":"I.ParkandJ.Cho \u201cSAiD: Speech\u2010Driven Blendshape Facial Animation With Diffusion \u201darXiv Preprint arXiv:2401.08655."},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456213"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"e_1_2_10_19_1","unstructured":"Y.Lin L.Peng J.Hu et al. \u201cEmoFace: Emotion\u2010Content Disentangled Speech\u2010Driven 3D Talking Face With Mesh Attention \u201darXiv Preprint arXiv:2408.11518."},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755190"},{"key":"e_1_2_10_21_1","first-page":"7840","volume-title":"ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Lee S.","year":"2024"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP55913.2025.11084454"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32449"},{"key":"e_1_2_10_24_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xie J.","year":"2025"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3409568"},{"key":"e_1_2_10_26_1","unstructured":"A.Yang C.Liu P.Xia andJ.Du \u201cStyleSpeaker: Audio\u2010Enhanced Fine\u2010Grained Style Modeling for Speech\u2010Driven 3D Facial Animation \u201dCoRRabs\/2503.09852."},{"key":"e_1_2_10_27_1","first-page":"1","volume-title":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","author":"Lu X.","year":"2025"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"e_1_2_10_29_1","first-page":"12449","article-title":"Wav2vec 2.0: A Framework for Self\u2010Supervised Learning of Speech Representations","volume":"33","author":"Baevski A.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_10_30_1","first-page":"18794","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Araujo E.","year":"2025"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"key":"e_1_2_10_33_1","first-page":"1779","volume-title":"International Conference on Machine Learning","author":"Cheng P.","year":"2020"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_15"}],"container-title":["Computer Animation and Virtual Worlds"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cav.70127","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cav.70127","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cav.70127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T07:34:43Z","timestamp":1787556883000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cav.70127"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1002\/cav.70127"],"URL":"https:\/\/doi.org\/10.1002\/cav.70127","archive":["Portico"],"relation":{},"ISSN":["1546-4261","1546-427X"],"issn-type":[{"value":"1546-4261","type":"print"},{"value":"1546-427X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"2026-04-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70127"}}