{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T15:19:45Z","timestamp":1791904785948,"version":"4.3.4"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3393714","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T17:56:58Z","timestamp":1714067818000},"page":"2590-2604","source":"Crossref","is-referenced-by-count":15,"title":["USAT: A Universal Speaker-Adaptive Text-to-Speech Approach"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9710-0136","authenticated-orcid":false,"given":"Wenbin","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1283-1672","authenticated-orcid":false,"given":"Yang","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1844-1520","authenticated-orcid":false,"given":"Sanjay","family":"Jha","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Kensington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Arik","year":"2017"},{"key":"ref2","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2020"},{"key":"ref5","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Popov","year":"2021"},{"key":"ref6","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1745"},{"key":"ref9","article-title":"Residual adapters for few-shot text-to-speech speaker adaptation","author":"Morioka","year":"2022"},{"key":"ref10","article-title":"Adaspeech: Adaptive text to speech for custom voice","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1936"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746875"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-901"},{"key":"ref15","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref16","article-title":"Mega-TTS: Zero-shot text-to-speech at scale with intrinsic inductive bias","author":"Jiang","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511667206"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413880"},{"key":"ref20","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. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-304"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2070"},{"key":"ref25","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","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-225"},{"key":"ref27","article-title":"NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Shen","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3358913"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053371"},{"key":"ref30","first-page":"273","article-title":"Speaker adaptation for HMM-based speech synthesis system using MLLR","volume-title":"Proc. 3rd Int. COCOSDA","author":"Tamura","year":"1998"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325908"},{"key":"ref32","first-page":"10040","article-title":"Neural voice cloning with a few samples","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Arik","year":"2018"},{"key":"ref33","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1590"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3167258"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414872"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2326"},{"key":"ref40","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3356232"},{"key":"ref42","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Skerry-Ryan","year":"2018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/628"},{"key":"ref46","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Ganin","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref51","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref52","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref53","first-page":"5353","article-title":"AccentDB: A database of non-native english accents to assist neural speech recognition","volume-title":"Proc. 12th Lang. Resourc. Eval. Conf.","author":"Ahamad"},{"key":"ref54","article-title":"Google crowdsourced speech corpora and related open-source resources for low-resource languages and dialects: An overview","author":"Butryna","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1110"},{"key":"ref56","first-page":"356","article-title":"ALLSSTAR: Archive of l1 and l2 scripted and spontaneous transcripts and recordings","volume-title":"Proc. Int. Congr. Phonetic Sci.s","author":"Bradlow","year":"2010"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-644"},{"key":"ref58","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11074"},{"key":"ref61","first-page":"7748","article-title":"Meta-stylespeech : Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Min","year":"2021"},{"key":"ref62","article-title":"Clova baseline system for the voxceleb speaker recognition challenge 2020","author":"Heo","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.01.002"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref67","article-title":"How generalizable are deepfake detectors? An empirical study","author":"Li","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref70","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-479"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461719"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491.MR0022058.Zbl0041.26103"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_16"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2895923"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096431"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10508477.pdf?arnumber=10508477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T04:50:24Z","timestamp":1715230224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3393714","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}