{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:47:16Z","timestamp":1776880036678,"version":"3.51.2"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800623","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"284-288","source":"Crossref","is-referenced-by-count":1,"title":["Diffusion-Based Method with TTS Guidance for Foreign Accent Conversion"],"prefix":"10.1109","author":[{"given":"Qibing","family":"Bai","sequence":"first","affiliation":[{"name":"School of Data Science"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Data Science"}]},{"given":"Zhijun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Data Science"}]},{"given":"Mingyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Data Science"}]},{"given":"Wei","family":"Rao","sequence":"additional","affiliation":[{"name":"Tencent Ethereal Audio Lab, Tencent"}]},{"given":"Yannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Ethereal Audio Lab, Tencent"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"School of Data Science"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/icslp.2002-137"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1789"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1043"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038818"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2201474"},{"key":"ref8","first-page":"5314","article-title":"Accent conversion using phonetic posteriorgrams","author":"Guanlong","year":"2018","journal-title":"ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"},{"key":"ref10","article-title":"Improving accent conversion with ref-erence encoder and end-to-end text-to-speech","author":"Li","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101302"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1416"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3060813"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10729"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10664"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317592"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053797"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094737"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3270079"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-612"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447205"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref23","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2021","journal-title":"ICLR"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in NeurIPS"},{"key":"ref25","article-title":"Score-based generative modeling through stochas-tic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref26","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"ICML","author":"Popov","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413889"},{"key":"ref31","first-page":"28492","article-title":"Robust speech recognition via large-scale weak su-pervision","volume-title":"ICML","author":"Radford","year":"2023"},{"key":"ref32","article-title":"Ditto-tts: Efficient and scalable zero-shot text-to-speech with diffusion transformer","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref35","article-title":"Autoregressive diffusion transformer for text -to-speech synthesis","volume-title":"arXiv preprint","author":"Liu","year":"2024"},{"key":"ref36","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023","journal-title":"ICLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1110"},{"key":"ref39","article-title":"BigVGAN: A universal neural vocoder with large-scale training","author":"Gil Lee","year":"2023","journal-title":"ICLR"},{"key":"ref40","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in NeurIPS","volume":"33","author":"Kong","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107337855"},{"key":"ref43","author":"Ravillion","year":"2020","journal-title":"A comparison of best-worst scaling and rating scale for timbre characterisation"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800623.pdf?arnumber=10800623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:37:43Z","timestamp":1736883463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800623","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}