{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:11:12Z","timestamp":1765357872103,"version":"build-2065373602"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3597267","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T18:39:39Z","timestamp":1754678379000},"page":"10361-10377","source":"Crossref","is-referenced-by-count":3,"title":["Dubbing Movies via Hierarchical Phoneme Modeling and Acoustic Diffusion Denoising"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8437-4824","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1239-8119","authenticated-orcid":false,"given":"Gaoxiang","family":"Cong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4312-5682","authenticated-orcid":false,"given":"Yuankai","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning (AIML), School of Computer Science, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3326-4147","authenticated-orcid":false,"given":"Quan Z.","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"EECS, University of California at Merced, Merced, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02056"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref5","first-page":"3165","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548081"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548194"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746421"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01822"},{"article-title":"VASA-1: Lifelike audio-driven talking faces generated in real time","year":"2024","author":"Xu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"article-title":"LLaSM: Large language and speech model","year":"2023","author":"Shu","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01411"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"article-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref17"},{"key":"ref18","first-page":"7748","article-title":"Meta-StyleSpeech: Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Min"},{"key":"ref19","first-page":"10040","article-title":"Neural voice cloning with a few samples","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Arik"},{"key":"ref20","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref22","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Casanova"},{"key":"ref23","first-page":"19594","article-title":"StyleTTS 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","year":"2024","author":"Ju","key":"ref24"},{"article-title":"MaskGCT: Zero-shot text-to-speech with masked generative codec transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.01.008"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3651311"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3625100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3180995"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257878"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3203630"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475415"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095582"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357808"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339964"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446049"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01033"},{"key":"ref42","first-page":"16582","article-title":"Neural dubber: Dubbing for videos according to scripts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094745"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2179"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25998"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327677"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414727"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref54","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"article-title":"DiffGAN-TTS: High-fidelity and efficient text-to-speech with denoising diffusion GANs","year":"2022","author":"Liu","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"article-title":"Phase-aware speech enhancement with deep complex U-net","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choi","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10054"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref67","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2004-668"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096370"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.30"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6337"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","key":"ref76"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref77"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.404"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1751"},{"key":"ref81","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kong"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11121533.pdf?arnumber=11121533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:37:18Z","timestamp":1759772238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11121533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":81,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3597267","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}