{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T20:54:54Z","timestamp":1767992094166,"version":"3.49.0"},"reference-count":30,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"JST CREST","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}]},{"name":"Nagoya University Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3482701","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:56:40Z","timestamp":1729187800000},"page":"2995-2999","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Speaker Text-to-Speech Training With Speaker Anonymized Data"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3172-3335","authenticated-orcid":false,"given":"Wen-Chin","family":"Huang","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4390-1354","authenticated-orcid":false,"given":"Yi-Chiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Information Technology Center, Nagoya University, Nagoya, Aichi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Base TTS: Lessons from building a billion-parameter text-to-speech model on 100k hours of data","author":"ajszczak","year":"2024"},{"key":"ref2","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Ju","year":"2024"},{"key":"ref3","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023"},{"key":"ref4","article-title":"Quantifying memorization across neural language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Carlini","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101362"},{"key":"ref6","article-title":"The voiceprivacy 2024 challenge evaluation plan","author":"Tomashenko","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/SPSC.2022-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1070"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2023.3344375"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3430530"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-28"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096607"},{"key":"ref17","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Wang","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","volume-title":"CSTR VCTK Corpus: English Multi-Speaker Corpus for CSTR Voice Cloning Toolkit","author":"Veaux","year":"2017"},{"key":"ref22","first-page":"2709","article-title":"Your TTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Casanova","year":"2022"},{"key":"ref23","article-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref28","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":"ref29","article-title":"ESPNet2-TTS: Extending the edge of tts research","author":"Hayashi","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref31","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref32","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10380231\/10720809.pdf?arnumber=10720809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:52:23Z","timestamp":1732668743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10720809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3482701","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}