{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T11:50:48Z","timestamp":1769601048724,"version":"3.49.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["62076144"],"award-info":[{"award-number":["62076144"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["WDZC20220816140515001"],"award-info":[{"award-number":["WDZC20220816140515001"]}]},{"name":"Shenzhen Key Laboratory of next generation interactive media innovative technology","award":["ZDSYS20210623092001004"],"award-info":[{"award-number":["ZDSYS20210623092001004"]}]},{"name":"AMiner.Shenzhen SciBrain fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3301217","type":"journal-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:47:01Z","timestamp":1690998421000},"page":"3290-3303","source":"Crossref","is-referenced-by-count":7,"title":["MSStyleTTS: Multi-Scale Style Modeling With Hierarchical Context Information for Expressive Speech Synthesis"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3597-3913","authenticated-orcid":false,"given":"Shun","family":"Lei","sequence":"first","affiliation":[{"name":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6363-891X","authenticated-orcid":false,"given":"Yixuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6985-8281","authenticated-orcid":false,"given":"Liyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8533-0524","authenticated-orcid":false,"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-1572","authenticated-orcid":false,"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8304-5260","authenticated-orcid":false,"given":"Shiyin","family":"Kang","sequence":"additional","affiliation":[{"name":"Skywork AI Pte. Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref57","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref59","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"0","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref14","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","first-page":"6588","article-title":"FastPitch: Parallel text-to-speech with pitch prediction","author":"?a?cucki","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref53","article-title":"Using previous acoustic context to improve text-to-speech synthesis","author":"oplustil-gallegos","year":"2020"},{"key":"ref52","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref11","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref55","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"0","journal-title":"Proc Annu Conf Neural Inf Process Syst Workshop Deep Learn Representation Learn"},{"key":"ref10","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"ze","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref54","first-page":"205","article-title":"Comparing acoustic and textual representations of previous linguistic context for improving text-to-speech","author":"gallegos","year":"0","journal-title":"Proc 11th ISCA Speech Synth Workshop"},{"key":"ref17","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref19","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11171"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747438"},{"key":"ref46","first-page":"249","article-title":"On stress and linguistic rhythm","volume":"8","author":"liberman","year":"1977","journal-title":"Linguistic Inquiry"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1017\/S0952675700000695"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414102"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-37"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3202126"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.30"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2000-290"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1894-4_22"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1999-513"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-219"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-686"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-984"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746883"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-802"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1129"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054337"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3074757"},{"key":"ref32","article-title":"Towards transfer learning for end-to-end speech synthesis from deep pre-trained language models","author":"fang","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1977.1170350"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-18"},{"key":"ref38","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref23","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746744"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003859"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref29","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"0","journal-title":"Proc Annu Conf Neural Inf Process Syst"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10202208.pdf?arnumber=10202208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:34:48Z","timestamp":1695666888000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10202208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3301217","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}