{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:14Z","timestamp":1775229974277,"version":"3.50.1"},"reference-count":30,"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\/icassp43922.2022.9746430","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6552-6556","source":"Crossref","is-referenced-by-count":28,"title":["S3PRL-VC: Open-Source Voice Conversion Framework with Self-Supervised Speech Representations"],"prefix":"10.1109","author":[{"given":"Wen-Chin","family":"Huang","sequence":"first","affiliation":[{"name":"Nagoya University,Japan"}]},{"given":"Shu-Wen","family":"Yang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Japan"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-19"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref13","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc NeruIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-17"},{"key":"ref18","first-page":"4480","article-title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","author":"jia","year":"2018","journal-title":"Proc NIPS"},{"key":"ref19","first-page":"5998","article-title":"Attention is All you Need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref28","first-page":"99","article-title":"Predictions of Subjective Ratings and Spoofing Assessments of Voice Conversion Challenge 2020 Submissions","author":"kumar das","year":"2020","journal-title":"Proc Joint Workshop for the BC and VCC 2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-24"},{"key":"ref27","article-title":"Subjective evaluation of speech quality with a crowdsourcing approach","year":"2018"},{"key":"ref3","first-page":"80","article-title":"Voice Conversion Challenge 2020 - Intra-lingual semi-parallel and cross-lingual voice conversion -","author":"zhao","year":"2020","journal-title":"Proc Joint Workshop for the BC and VCC 2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-16"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953087"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828650"},{"key":"ref24","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit","author":"veaux","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2665"},{"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":"Proc NeurIPS"}],"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\/09746430.pdf?arnumber=9746430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:11:53Z","timestamp":1661184713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746430","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}