{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T09:24:16Z","timestamp":1770283456882,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747743","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6557-6561","source":"Crossref","is-referenced-by-count":8,"title":["Training Robust Zero-Shot Voice Conversion Models with Self-Supervised Features"],"prefix":"10.1109","author":[{"given":"Trung","family":"Dang","sequence":"first","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dung","family":"Tran","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Chin","sequence":"additional","affiliation":[{"name":"Boston University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhito","family":"Koishida","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5954","article-title":"Againvc: A one-shot voice conversion using activation guidance and adaptive instance normalization","author":"chen","year":"2021","journal-title":"ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2086"},{"key":"ref13","article-title":"Improving zero-shot voice style transfer via disentangled representation learning","author":"yuan","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2365"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383498"},{"key":"ref19","article-title":"Superseded - cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"veaux","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1710"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref6","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"ICML"},{"key":"ref5","article-title":"Nvc-net: End-to-end adversarial voice conversion","author":"nguyen","year":"2021"},{"key":"ref8","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref1","first-page":"1","article-title":"Voice conversion from non-parallel corpora using variational auto-encoder","author":"hsu","year":"2016","journal-title":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)"},{"key":"ref9","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747743.pdf?arnumber=9747743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:15:06Z","timestamp":1661184906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747743","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}