{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:43:33Z","timestamp":1785336213212,"version":"3.55.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022498","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"920-927","source":"Crossref","is-referenced-by-count":10,"title":["Styletts-VC: One-Shot Voice Conversion by Knowledge Transfer From Style-Based TTS Models"],"prefix":"10.1109","author":[{"given":"Yinghao Aaron","family":"Li","sequence":"first","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Han","sequence":"additional","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nima","family":"Mesgarani","sequence":"additional","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2663"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1693"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref7","article-title":"Avqvc: One-shot voice con-version by vector quantization with applying contrastive learning","author":"Tang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414137"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066047"},{"key":"ref11","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for every-one","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747239"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053842"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688088"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1542"},{"key":"ref17","article-title":"Styletts: A style-based generative model for natural and diverse text-to-speech synthesis","author":"Aaron","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-319"},{"key":"ref21","article-title":"Lib-ritts: A corpus derived from librispeech for text-to-speech","author":"Zen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/app9071324"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref24","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_33"},{"key":"ref27","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 In-formation Processing Systems"},{"key":"ref28","author":"Yamagishi","year":"2019","journal-title":"Cstr vctk corpus: English multi-speaker cor-pus for cstr voice cloning toolkit (version 0. 92)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747236"},{"key":"ref30","author":"Loshchilov","year":"2018","journal-title":"Fixing weight decay regularization in adam"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022498.pdf?arnumber=10022498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:33:32Z","timestamp":1707813212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022498\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022498","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}