{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:16Z","timestamp":1775229916520,"version":"3.50.1"},"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888332","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":2,"title":["AccentBox: Towards High-Fidelity Zero-Shot Accent Generation"],"prefix":"10.1109","author":[{"given":"Jinzuomu","family":"Zhong","sequence":"first","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]},{"given":"Korin","family":"Richmond","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]},{"given":"Zhiba","family":"Su","sequence":"additional","affiliation":[{"name":"Transsion,Department of AI Technology,China"}]},{"given":"Siqi","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Edinburgh,Centre for Speech Technology Research,UK"}]}],"member":"263","reference":[{"key":"ref1","article-title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","author":"Ju","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3530270"},{"key":"ref3","article-title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Jia","year":"2018"},{"key":"ref4","article-title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","author":"Wang","year":"2023"},{"key":"ref5","volume-title":"English with an Accent: Language Ideology and Discrimination in the United States.","author":"Rosina","year":"1997"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1088868309359288"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-019-09955-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT45670.2019.8944754"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.47476\/jat.v4i1.2021.166"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3363414"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0601-3_17"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023072"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-154"},{"key":"ref16","article-title":"Multi-Scale Accent Modeling with Disentangling for Multi-Speaker Multi-Accent TTS Synthesis","author":"Zhou","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2270"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3378110"},{"key":"ref19","first-page":"2709","article-title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Casanova"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413386"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2419"},{"key":"ref24","first-page":"4218","article-title":"Common Voice: A Massively-Multilingual Speech Corpus","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3292740"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317526"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref28","article-title":"Natural Language Guidance of High-Fidelity Text-to-Speech with Synthetic Annotations","author":"Lyth","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref30","first-page":"73","article-title":"Data Mining for Direct marketing: Problems and Solutions","volume-title":"Proceedings of the 4th International Conference on Knowledge Discovery and Data Mining","volume":"98","author":"Ling"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2558"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref36","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92)","author":"Yamagishi","year":"2012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095057"}],"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\/10888332.pdf?arnumber=10888332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:53Z","timestamp":1774416293000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888332\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888332","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}