{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T04:54:44Z","timestamp":1783140884768,"version":"3.54.6"},"reference-count":24,"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\/icassp48485.2024.10446296","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11141-11145","source":"Crossref","is-referenced-by-count":4,"title":["Unifying One-Shot Voice Conversion and Cloning with Disentangled Speech Representations"],"prefix":"10.1109","author":[{"given":"Hui","family":"Lu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haohan","family":"Guo","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent,Tencent AI Lab,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref2","article-title":"Neural voice cloning with a few samples","volume":"31","author":"Arik","year":"2018","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\/ICASSP43922.2022.9747319"},{"key":"ref5","article-title":"Auto-encoding variational bayes","volume-title":"2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings","author":"Kingma"},{"key":"ref6","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","author":"Higgins"},{"key":"ref7","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume-title":"Advances in Neural Information Processing Systems","volume":"2017","author":"Hsu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022787"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747272"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3034994"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10879"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref14","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event","author":"Kim"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-684"},{"key":"ref16","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10054"},{"key":"ref18","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"9th International Conference on Learning Representations, ICLR 2021","volume":"2021","author":"Ren"},{"key":"ref19","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref20","first-page":"17022","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":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref24","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019"}],"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\/10446296.pdf?arnumber=10446296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:09:32Z","timestamp":1722575372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446296\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446296","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}