{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:27:57Z","timestamp":1753601277691,"version":"3.37.3"},"reference-count":46,"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":["U23B2053"],"award-info":[{"award-number":["U23B2053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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.2024.3449148","type":"journal-article","created":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T18:01:02Z","timestamp":1724436062000},"page":"4199-4210","source":"Crossref","is-referenced-by-count":4,"title":["PE-Wav2vec: A Prosody-Enhanced Speech Model for Self-Supervised Prosody Learning in TTS"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0102-6527","authenticated-orcid":false,"given":"Zhao-Ci","family":"Liu","sequence":"first","affiliation":[{"name":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9421-1049","authenticated-orcid":false,"given":"Liping","family":"Chen","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya-Jun","family":"Hu","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7073-1744","authenticated-orcid":false,"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, iFLYTEK Company Ltd., Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1292"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref4","first-page":"2021","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Ren"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"Oord","key":"ref5"},{"key":"ref6","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong","year":"2020"},{"key":"ref7","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref8","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Casanova","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.06.006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2861"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-411"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2918"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414413"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413864"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1049"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-802"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133205"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746883"},{"key":"ref22","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref24","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC52510.2021.9621175"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10797"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2574"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096905"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3278184"},{"volume-title":"Theory and Applications of Digital Speech Processing","year":"2010","author":"Rabiner","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"issue":"2","key":"ref34","first-page":"134","article-title":"Glottal-excited linear prediction(GELP) model for low-bit-rate speech coding","volume-title":"Proc Natlscicouncrepub China Part Phys. Sci. Eng.","volume":"24","author":"Hu","year":"2000"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1972.1162410"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1973.1162472"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607882"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2012-6"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0477(1998)079<0061:APGTWA>2.0.CO;2"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1757"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Blizzard.2019-1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-984"},{"year":"2022","key":"ref46","article-title":"Pearson correlation coefficient"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10645206.pdf?arnumber=10645206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T04:37:40Z","timestamp":1727411860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645206\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3449148","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}