{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:22:29Z","timestamp":1774419749285,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889108","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model"],"prefix":"10.1109","author":[{"given":"Jialong","family":"Zuo","sequence":"first","affiliation":[{"name":"Zhejiang University"}]},{"given":"Shengpeng","family":"Ji","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Minghui","family":"Fang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Ziyue","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Xize","family":"Cheng","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Qian","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Wenrui","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Guangyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Zehai","family":"Tu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Yiwen","family":"Guo","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref2","first-page":"294","article-title":"Voicemixer: Adversarial voice style mixup","volume":"34","author":"Lee","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref5","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref6","first-page":"16 251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"Choi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096057"},{"key":"ref8","first-page":"18 003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2326"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445804"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-817"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.593"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746278"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-2091"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446160"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3439996"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892405"},{"key":"ref23","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref25","article-title":"Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling","author":"Ji","year":"2024"},{"key":"ref26","article-title":"Ace: A generative cross-modal retrieval framework with coarse-to-fine semantic modeling","author":"Fang","year":"2024"},{"key":"ref27","article-title":"Mega-tts: Zero-shot text-to-speech at scale with intrinsic inductive bias","author":"Jiang","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref29","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022"},{"key":"ref31","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889108.pdf?arnumber=10889108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:26Z","timestamp":1774416266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889108","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}