{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:00:19Z","timestamp":1776445219008,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095702","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":11,"title":["Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Takaaki","family":"Saeki","sequence":"first","affiliation":[{"name":"Google,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heiga","family":"Zen","sequence":"additional","affiliation":[{"name":"Google,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhehuai","family":"Chen","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobuyuki","family":"Morioka","sequence":"additional","affiliation":[{"name":"Google,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gary","family":"Wang","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Bapna","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2187195"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-172"},{"key":"ref3","article-title":"Multilingual Byte2Speech models for scalable low-resource speech synthesis","author":"He","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref5","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref7","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.105"},{"key":"ref12","first-page":"1399","article-title":"A3T: Alignment-aware acoustic and text pretraining for speech synthesis and editing","volume-title":"Proc. ICML","author":"Bai"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682890"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053831"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2123"},{"key":"ref17","article-title":"Almost unsupervised text to speech and automatic speech recognition","author":"Ren","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-304"},{"issue":"4","key":"ref19","article-title":"Multilingual text-to-speech synthesis: The Bell labs approach","volume":"24","author":"O\u2019Shaughnessy","year":"1998","journal-title":"Computational Linguistics"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2668"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1163"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746968"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-35"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-152"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref27","article-title":"Hierarchical generative modeling for controllable speech synthesis","volume-title":"Proc. ICLR","author":"Hsu"},{"key":"ref28","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2826"},{"key":"ref32","first-page":"16","article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED","volume-title":"Proc. SLTU","author":"Gales"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023141"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022791"},{"key":"ref35","article-title":"Common Voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref37","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref38","article-title":"Audio samples for Virtuoso"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094909"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095702.pdf?arnumber=10095702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:43:42Z","timestamp":1709246622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095702\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095702","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}