{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:04:45Z","timestamp":1781366685595,"version":"3.54.1"},"reference-count":28,"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\/icassp48485.2024.10445804","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10571-10575","source":"Crossref","is-referenced-by-count":18,"title":["Promptvc: Flexible Stylistic Voice Conversion in Latent Space Driven by Natural Language Prompts"],"prefix":"10.1109","author":[{"given":"Jixun","family":"Yao","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuguang","family":"Yang","sequence":"additional","affiliation":[{"name":"Ximalaya Inc,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Lei","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqian","family":"Ning","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanni","family":"Hu","sequence":"additional","affiliation":[{"name":"Ximalaya Inc,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Pan","sequence":"additional","affiliation":[{"name":"Ximalaya Inc,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingjing","family":"Yin","sequence":"additional","affiliation":[{"name":"Ximalaya Inc,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ximalaya Inc,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Lu","sequence":"additional","affiliation":[{"name":"Ximalaya Inc,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095960"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-686"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095120"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2048"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683865"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095842"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746179"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746405"},{"key":"ref13","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687906"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3402088"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1779"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","first-page":"7748","article-title":"Meta-stylespeech : Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. ICML","author":"Min"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref21","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","author":"Ren"},{"key":"ref22","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref23","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00296-0_5"}],"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\/10445804.pdf?arnumber=10445804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:55:12Z","timestamp":1722574512000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445804","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}