{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:03:49Z","timestamp":1761897829824,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095393","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["DVQVC: An Unsupervised Zero-Shot Voice Conversion Framework"],"prefix":"10.1109","author":[{"given":"Dayong","family":"Li","sequence":"first","affiliation":[{"name":"Westlake University & Westlake,Institute for Advanced Study,Hangzhou,China"}]},{"given":"Xian","family":"Li","sequence":"additional","affiliation":[{"name":"Westlake University & Westlake,Institute for Advanced Study,Hangzhou,China"}]},{"given":"Xiaofei","family":"Li","sequence":"additional","affiliation":[{"name":"Westlake University & Westlake,Institute for Advanced Study,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10019"},{"article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","year":"2019","author":"baevski","key":"ref12"},{"key":"ref15","first-page":"6142","article-title":"Self-supervised speaker recognition with lossgated learning","author":"tao","year":"2022","journal-title":"ICASSP 2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC52510.2021.9621202"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-285"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1333"},{"article-title":"Towards end-to-end unsupervised speech recognition","year":"2022","author":"liu","key":"ref17"},{"key":"ref16","first-page":"12449","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"article-title":"Vector quantized image modeling with improved vqgan","year":"2021","author":"yu","key":"ref18"},{"article-title":"Voice conversion challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion","year":"2020","author":"zhao","key":"ref24"},{"key":"ref23","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"veaux","year":"2017","journal-title":"Centre for Speech Technology Research University of Edinburgh"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5334\/jors.187"},{"key":"ref25","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":"ref20","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746369"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2412"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747239"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414788"},{"key":"ref5","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095393.pdf?arnumber=10095393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:02:57Z","timestamp":1699884177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095393\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095393","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}