{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:10:25Z","timestamp":1776885025574,"version":"3.51.2"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888195","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion"],"prefix":"10.1109","author":[{"given":"Sho","family":"Inoue","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanxing","family":"Wang","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengcheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengxiao","family":"Bi","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0601-3_17"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317592"},{"key":"ref3","article-title":"Voiceshop: A unified speech-to-speech framework for identity-preserving zero-shot voice editing","author":"Anastassiou","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10729"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095773"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref8","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref9","article-title":"Mega-tts 2: Boosting prompting mechanisms for zero-shot speech synthesis","volume-title":"International Conference on Learning Representations","author":"Jiang"},{"key":"ref10","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","volume":"abs\/2303.03926","author":"Zhang","year":"2023","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/976909.979634"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1922649.1922654"},{"key":"ref13","article-title":"Training language models to follow instructions with human feedback","volume":"abs\/2203.02155","author":"Ouyang","year":"2022","journal-title":"ArXiv"},{"key":"ref14","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1044\/2014_AJSLP-13-0074"},{"key":"ref16","first-page":"229","author":"Flege","year":"1995","journal-title":"Second language speech learning: Theory, findings and problems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1110"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095057"},{"key":"ref19","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2017","journal-title":"sound"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-70"},{"key":"ref21","article-title":"The cmu arctic speech databases","volume-title":"Speech Synthesis Workshop","author":"Kominek"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3060813"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053797"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447205"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10664"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101302"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362120"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094737"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIDCA56705.2023.10099632"},{"key":"ref30","article-title":"gpt-3.5-turbo-1106","year":"2022"},{"key":"ref31","article-title":"gpt-4o-2024-05-13","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1066"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"abs\/2010.05646","author":"Kong","year":"2020","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref37","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2419"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888195.pdf?arnumber=10888195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:18Z","timestamp":1774416258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888195","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}