{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:55:17Z","timestamp":1777128917593,"version":"3.51.4"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446191","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12697-12701","source":"Crossref","is-referenced-by-count":12,"title":["PAVITS: Exploring Prosody-Aware VITS for End-to-End Emotional Voice Conversion"],"prefix":"10.1109","author":[{"given":"Tianhua","family":"Qi","sequence":"first","affiliation":[{"name":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"}]},{"given":"Wenming","family":"Zheng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"}]},{"given":"Cheng","family":"Lu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"}]},{"given":"Yuan","family":"Zong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"}]},{"given":"Hailun","family":"Lian","sequence":"additional","affiliation":[{"name":"Key Laboratory of Child Development and Learning Science (Southeast University),Ministry of Education,Nanjing,China,210096"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3175578"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413398"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2021.3056421"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2480741.2480751"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.09.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687906"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1253"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222646"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.07.001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3461615.3491106"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414489"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-781"},{"key":"ref16","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref17","article-title":"End-to-end adversarial text-to-speech","volume-title":"International Conference on Learning Representations","author":"Donahue"},{"key":"ref18","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096480"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2009578"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747664"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446191.pdf?arnumber=10446191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:05:58Z","timestamp":1722575158000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446191","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}