{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:03:17Z","timestamp":1777888997773,"version":"3.51.4"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014188","name":"MSIT","doi-asserted-by":"publisher","award":["RS-2024-00457882"],"award-info":[{"award-number":["RS-2024-00457882"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2021R1C1C1006799"],"award-info":[{"award-number":["NRF-2021R1C1C1006799"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01357","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14623-14632","source":"Crossref","is-referenced-by-count":0,"title":["VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models"],"prefix":"10.1109","author":[{"given":"Kim","family":"Sung-Bin","sequence":"first","affiliation":[{"name":"POSTECH,Department of Electrical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeongsoo","family":"Choi","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puyuan","family":"Peng","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tae-Hyun","family":"Oh","sequence":"additional","affiliation":[{"name":"School of Computing, KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Harwath","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1298"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","article-title":"Vall-e 2: Neural codec language models are human parity zero-shot text to speech synthesizers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-194"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01411"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.404"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2066"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2066"},{"key":"ref14","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Vampnet: Music generation via masked acoustic token modeling","author":"Garcia","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01033"},{"key":"ref17","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"The curious case of neural text degeneration","author":"Holtzman","year":"2019","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Neural dubber: Dubbing for videos according to scripts","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Hu","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref22","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1779"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746421"},{"key":"ref25","article-title":"Sayanything: Audiodriven lip synchronization with conditional video diffusion","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref27","article-title":"Emotion2Vec: Selfsupervised pre-training for speech emotion representation","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Svts: scalable video-tospeech synthesis","volume-title":"Conference of the International Speech Communication Association (INTERSPEECH)","author":"Mira","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"},{"key":"ref31","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"},{"key":"ref33","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Ren","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref35","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"International Conference on Learning Representations (ICLR)","author":"Shi","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00280-0"},{"key":"ref37","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"ref38","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00607"},{"key":"ref40","article-title":"Audio-driven talking face generation with stabilized synchronization loss","volume-title":"European Conference on Computer Vision (ECCV)","author":"Yaman","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01422"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3129994"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680777"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_38"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445483.pdf?arnumber=11445483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:46Z","timestamp":1777611886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01357","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}