{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:59:39Z","timestamp":1783040379624,"version":"3.54.6"},"reference-count":73,"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":[{"name":"National Key R&D Program of China","award":["2020AAA0108600"],"award-info":[{"award-number":["2020AAA0108600"]}]}],"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.2024.3363444","type":"journal-article","created":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T18:55:48Z","timestamp":1707332148000},"page":"1506-1518","source":"Crossref","is-referenced-by-count":38,"title":["METTS: Multilingual Emotional Text-to-Speech by Cross-Speaker and Cross-Lingual Emotion Transfer"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9275-523X","authenticated-orcid":false,"given":"Xinfa","family":"Zhu","sequence":"first","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9256-9311","authenticated-orcid":false,"given":"Yi","family":"Lei","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5578-3960","authenticated-orcid":false,"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0526-5778","authenticated-orcid":false,"given":"Yongmao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7569-1197","authenticated-orcid":false,"given":"Hongbin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ximalaya Inc., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9236-8825","authenticated-orcid":false,"given":"Heng","family":"Lu","sequence":"additional","affiliation":[{"name":"Ximalaya Inc., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref4","article-title":"AdaSpeech: Adaptive text to speech for custom voice","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"ref7","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747032"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2668"},{"key":"ref12","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Min","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746858"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414872"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-294"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3203888"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268571"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11275"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2021-14","article-title":"DelightfulTTs: The microsoft speech synthesis system for blizzard challenge 2021","author":"Liu","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1520340.1520483"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-379"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9127-7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03070-3_45"},{"key":"ref25","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Wang","year":"2018"},{"key":"ref26","first-page":"26","article-title":"Pronunciation problems of Chinese learners of English","volume":"30","author":"Han","year":"2013","journal-title":"Ortesol J."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5539\/elt.v9n10p90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-13"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3191"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683519"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-172"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-831"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2070"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414226"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2679"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1265"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10572"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746914"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096929"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3164181"},{"key":"ref41","article-title":"Cross-speaker emotion transfer based on speaker condition layer normalization and semi-supervised training in text-to-speech","author":"Wu","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282282"},{"key":"ref43","article-title":"Emotional end-to-end neural speech synthesizer","author":"Lee","year":"2017"},{"key":"ref44","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Skerry-Ryan","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1990"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2985"},{"key":"ref50","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choi","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747763"},{"key":"ref52","article-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 35: Annu. Conf. Neural Inf. Process. Syst.","author":"Huang","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.07.005"},{"key":"ref54","first-page":"2917","article-title":"Style equalization: Unsupervised learning of controllable generative sequence models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chang","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095131"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747801"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746744"},{"key":"ref58","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/SMC52423.2021.9658830"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2476762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref64","first-page":"93","article-title":"An HMM-based system for automatic segmentation and alignment of speech","volume-title":"Proc. Fonetik","volume":"2003","author":"Sjlander","year":"2003"},{"key":"ref65","first-page":"14881","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1265"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145297"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref72","article-title":"Domain adversarial training: A game perspective","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Acuna","year":"2022"},{"key":"ref73","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10423864.pdf?arnumber=10423864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T19:46:03Z","timestamp":1731267963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10423864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3363444","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}