{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:03:55Z","timestamp":1780761835580,"version":"3.54.1"},"reference-count":43,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889463","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["DFNeRF: Disentangled Facial Neural Radiance Fields for Text-based Editing of Free-view Talking Head"],"prefix":"10.1109","author":[{"given":"Benwang","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University,School of Shenzhen International Graduate School,Shenzhen,China,518071"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China,518071"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China,518071"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China,518071"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,School of Shenzhen International Graduate School,Shenzhen,China,518071"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185563"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3449063"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747380"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02074"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00472"},{"key":"ref8","article-title":"Text-based talking video editing with cascaded conditional diffusion","author":"Han","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645164"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref11","article-title":"Gaia: Zero-shot talking avatar generation","author":"He","year":"2023"},{"key":"ref12","article-title":"Dreamtalk: When expressive talking head generation meets diffusion probabilistic models","author":"Ma","year":"2023"},{"key":"ref13","article-title":"High-fidelity and lip-synced talking face synthesis via landmark-based diffusion model","author":"Zhong","year":"2024"},{"key":"ref14","article-title":"Glditalker: Speech-driven 3d facial animation with graph latent diffusion transformer","author":"Lin","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681627"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_23"},{"key":"ref18","article-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","author":"Xu","year":"2024"},{"key":"ref19","article-title":"Realtalk: Real-time and realistic audio-driven face generation with 3d facial prior-guided identity alignment network","author":"Ji","year":"2024"},{"key":"ref20","article-title":"Vasa-1: Lifelike audio-driven talking faces generated in real time","author":"Xu","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28314"},{"key":"ref22","article-title":"Talk3d: High-fidelity talking portrait synthesis via personalized 3d generative prior","author":"Ko","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05914-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref25","article-title":"Style-preserving lip sync via audio-aware style reference","author":"Zhong","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613753"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref30","article-title":"Dfa-nerf: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01723"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446195"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480487"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596730"},{"key":"ref36","volume-title":"Fundamentals of speech recognition","author":"Rabiner","year":"1993"},{"key":"ref37","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1017\/S0025100306002544"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"}],"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\/10889463.pdf?arnumber=10889463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:44Z","timestamp":1774416344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889463\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889463","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}