{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,30]],"date-time":"2025-11-30T08:49:28Z","timestamp":1764492568171,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute (ETRI) funded by the Korean Government","doi-asserted-by":"publisher","award":["20ZS1100"],"award-info":[{"award-number":["20ZS1100"]}],"id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3058382","type":"journal-article","created":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T07:46:35Z","timestamp":1613720795000},"page":"27278-27286","source":"Crossref","is-referenced-by-count":4,"title":["Many-to-Many Unsupervised Speech Conversion From Nonparallel Corpora"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1050-2667","authenticated-orcid":false,"given":"Yun Kyung","family":"Lee","sequence":"first","affiliation":[{"name":"Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun Woo","family":"Kim","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeon Gue","family":"Park","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1331"},{"key":"ref32","first-page":"1","article-title":"Wasserstein auto-encoders","author":"tolstikhin","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref31","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref37","article-title":"DARPA TIMIT acoustic phonetic continuous speech corpus CDROM","volume":"93","author":"garofolo","year":"1993"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.05.017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref11","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2307"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref16","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref19","first-page":"1","article-title":"Nonparallel emotional speech conversion","volume":"abs 1811 1174","author":"gao","year":"2018","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-32"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(89)90041-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2048"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref6","first-page":"2","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume":"3","author":"lee","year":"2013","journal-title":"Proc Workshop Challenges Represent Learn (ICML)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639000"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1183"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref9","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"2162","DOI":"10.21437\/Interspeech.2010-596","article-title":"Applying voice conversion to concatenative singing-voice synthesis","author":"villavicencio","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01243"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref25","first-page":"1","article-title":"Audio albert: A lite bert for self-supervised learning of audio representation","volume":"abs 2005 8575","author":"chi","year":"2020","journal-title":"CoRR"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09351918.pdf?arnumber=9351918","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,18]],"date-time":"2022-12-18T04:56:34Z","timestamp":1671339394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9351918\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3058382","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}