{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:45:25Z","timestamp":1784133925806,"version":"3.55.0"},"reference-count":64,"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\/4.0\/legalcode"}],"funder":[{"name":"Guangdong Provincial Key Laboratory of Big Data Computing"},{"DOI":"10.13039\/501100004853","name":"Chinese University of Hong Kong","doi-asserted-by":"publisher","award":["B10120210117-KP02"],"award-info":[{"award-number":["B10120210117-KP02"]}],"id":[{"id":"10.13039\/501100004853","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Natural Science Foundation Key Project","award":["JCYJ20220818103001002"],"award-info":[{"award-number":["JCYJ20220818103001002"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271432"],"award-info":[{"award-number":["62271432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376237"],"award-info":[{"award-number":["62376237"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AME Programmatic Funding Scheme","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3363414","type":"journal-article","created":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:06:47Z","timestamp":1708110407000},"page":"1699-1711","source":"Crossref","is-referenced-by-count":19,"title":["Accented Text-to-Speech Synthesis With Limited Data"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4367-2053","authenticated-orcid":false,"given":"Xuehao","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7945-0535","authenticated-orcid":false,"given":"Mingyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8520-8227","authenticated-orcid":false,"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1192-9857","authenticated-orcid":false,"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref7","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ren","year":"2019"},{"key":"ref8","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2020"},{"key":"ref9","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref11","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Jia","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2985"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1075\/sibil.36.10mun"},{"key":"ref16","first-page":"233","article-title":"Second language speech learning: Theory, findings, and problems","volume":"92","author":"Flege","year":"1995","journal-title":"Speech Perception Linguistic Experience: Issues Cross-Lang. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2387.003.0011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1044\/2014_AJSLP-13-0074"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1268"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.07.006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1159\/000097308"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318465"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1958.11659660"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/S0025100305001921"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.12.006"},{"key":"ref26","first-page":"547","article-title":"Testing the effects of segmental and suprasegmental phonetic cues in foreign accent rating: An experiment using prosody transplantation","volume-title":"Proc. Int. Symp. Acquisition Second Lang. Speech, Concordia Work. Papers Appl. Linguistics","volume":"5","author":"Rognoni","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1038"},{"key":"ref28","first-page":"6903","article-title":"Speech synthesis system for Indian accent using festvox","volume":"03","author":"Waseem","year":"2014","journal-title":"Int. J. Sci. Eng. Technol. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2015907024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-318"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638997"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-264"},{"key":"ref33","article-title":"Controllable accented text-to-speech synthesis","author":"Liu","year":"2022"},{"key":"ref34","article-title":"Accented text-to-speech synthesis with a conditional variational autoencoder","author":"Melechovsky","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3190672"},{"key":"ref37","article-title":"The festvox indic frontend for grapheme to phoneme conversion","volume-title":"Proc. WILDRE: Workshop Indian Lang. Data- Resour. Eval.","author":"Parlikar","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053390"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2654"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1954"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746447"},{"key":"ref43","article-title":"Grapheme-to-phoneme transformer model for transfer learning dialects","author":"Engelhart","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472738"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-37"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SMC52423.2021.9658830"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-3176"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","article-title":"Adadurian: Few-shot adaptation for neural text-to-speech with durian","author":"Zhang","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-230"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref53","article-title":"The CMU arctic speech databases","volume-title":"Proc. 5th ISCA Workshop Speech Synth.","author":"Kominek","year":"2004"},{"key":"ref54","article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","author":"Du","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Kingma","year":"2014"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_327"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885923"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref61","first-page":"69","article-title":"Dynamic time warping","author":"Mller","year":"2007"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1080\/00223890802107925"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10439064.pdf?arnumber=10439064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T22:24:07Z","timestamp":1710195847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10439064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3363414","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}