{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:53:13Z","timestamp":1776275593773,"version":"3.50.1"},"reference-count":114,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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","award":["62206136"],"award-info":[{"award-number":["62206136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"name":"Inner Mongolia Science and Technology Achievement Transfer and Transformation Demonstration Zone"},{"name":"University Collaborative Innovation Base"},{"name":"University Entrepreneurship Training Base” Construction","award":["21300-231510"],"award-info":[{"award-number":["21300-231510"]}]},{"name":"Internal Project Fund from Shenzhen Research Institute of Big Data","award":["T00120220002"],"award-info":[{"award-number":["T00120220002"]}]},{"name":"Shenzhen Science and Technology Research"},{"name":"Fundamental Research Key","award":["JCYJ20220818103001002"],"award-info":[{"award-number":["JCYJ20220818103001002"]}]}],"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.2024.3378110","type":"journal-article","created":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T20:04:01Z","timestamp":1712001841000},"page":"2188-2201","source":"Crossref","is-referenced-by-count":18,"title":["Controllable Accented Text-to-Speech Synthesis With Fine and Coarse-Grained Intensity Rendering"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4524-7413","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8078-3305","authenticated-orcid":false,"given":"Berrak","family":"Sisman","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5513-1192","authenticated-orcid":false,"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3076369"},{"key":"ref3","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref4","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arik","year":"2017"},{"key":"ref5","first-page":"2966","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Gibiansky","year":"2017"},{"key":"ref6","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":"ref7","article-title":"Char2wav: End-to-end speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Sotelo","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref11","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref13","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2020"},{"key":"ref14","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref15","first-page":"7706","article-title":"WaveFlow: A compact flow-based model for raw audio","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ping","year":"2020"},{"key":"ref16","first-page":"7586","article-title":"Parallel neural text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1212"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.07.006"},{"key":"ref19","article-title":"Accented text-to-speech synthesis with a conditional variational autoencoder","author":"Melechovsky","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10037914"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2330"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2303"},{"key":"ref23","article-title":"The development of accented english synthetic voices","author":"Malatji","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-861"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3363414"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3292740"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-519"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1954"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511611766"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1958.11659660"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318465"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/S0025100305001921"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.12.006"},{"key":"ref34","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 2nd Lang. Speech Concordia Work. Papers Appl. Linguistics","author":"Rognoni","year":"2014"},{"key":"ref35","article-title":"Creating accented text-to-speech english voices to facilitate second language learning","volume-title":"Proc. South Afr. Int. Conf. Educ. Technol.","author":"Malatji","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICABCD.2019.8851055"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref38","first-page":"7748","article-title":"Meta-StyleSpeech: Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Min","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10761"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163947"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2668"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1464"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0265532210364408"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-207"},{"key":"ref45","first-page":"1","article-title":"Automatic error detection in pronunciation training: Where we are and where we need to go","volume-title":"Proc. Int. Symp. Autom. Detection Errors Pronunciation Training","author":"Witt","year":"2012"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00044-8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6337"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17559"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851980"},{"key":"ref51","first-page":"5","article-title":"Diverse and controllable speech synthesis with GMM-based phone-level prosody modelling","volume-title":"Proc. Interspeech","author":"Du","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.06.003"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682654"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413953"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2387413"},{"key":"ref56","article-title":"Computer-assisted pronunciation teaching based on automatic speech recognition","volume-title":"Language Teaching and Language Technology Groningen","author":"Witt","year":"1997"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-458"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-238"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2621675"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-250"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2270"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3060813"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101302"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3270079"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1740"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022506"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-671"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.10.005"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855134"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462258"},{"key":"ref73","first-page":"64","article-title":"Spoken language conversion with accent morphing","volume-title":"Proc. 6th ISCA Workshop Speech Synthesis","author":"Huckvale","year":"2007"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053797"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362120"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1121\/1.4904701"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-145"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2926754"},{"key":"ref79","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2018"},{"key":"ref80","article-title":"Hierarchical generative modeling for controllable speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hsu","year":"2018"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref82","article-title":"Controllable and lossless non-autoregressive end-to-end text-to-speech","author":"Liu","year":"2022"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-307"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747098"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268571"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-838"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746253"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1038"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-318"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266376"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153253"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746579"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3209942"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1259"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.12.008"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053300"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-534"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-866"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1110"},{"key":"ref105","article-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref107","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref108","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414444"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1080\/00223890802107925"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1847"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10487819.pdf?arnumber=10487819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T18:48:32Z","timestamp":1712688512000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10487819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":114,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3378110","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}