{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:04:46Z","timestamp":1781366686705,"version":"3.54.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["21J20920"],"award-info":[{"award-number":["21J20920"]}]},{"name":"JST CREST","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}]},{"DOI":"10.13039\/501100003051","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","award":["JPNP20006"],"award-info":[{"award-number":["JPNP20006"]}],"id":[{"id":"10.13039\/501100003051","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/jstsp.2022.3193761","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T20:08:33Z","timestamp":1658779713000},"page":"1308-1318","source":"Crossref","is-referenced-by-count":20,"title":["A Comparative Study of Self-Supervised Speech Representation Based Voice Conversion"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3172-3335","authenticated-orcid":false,"given":"Wen-Chin","family":"Huang","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5503-9410","authenticated-orcid":false,"given":"Shu-Wen","family":"Yang","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8782-4093","authenticated-orcid":false,"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[{"name":"Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-671"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-363"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2286917"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-669"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168479"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref14","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref17","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"van den Oord","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3232"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref21","first-page":"80","article-title":"Voice conversion challenge 2020 - Intra-lingual semi-parallel and cross-lingual voice conversion","volume-title":"Proc. Joint Workshop Blizzard Challenge Voice Convers. Challenge","author":"Zhao","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-17"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-18"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-19"},{"key":"ref27","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688010"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2412"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref41","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-349"},{"key":"ref48","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref56","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953087"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828650"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref61","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref65","first-page":"27826","article-title":"Unsupervised speech recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2021"},{"key":"ref66","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053176"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-15"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2665"},{"key":"ref71","article-title":"Subjective evaluation of speech quality with a crowdsourcing approach","year":"2018"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1316"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902651"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09839425.pdf?arnumber=9839425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T02:38:55Z","timestamp":1706063935000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9839425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":76,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3193761","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}