{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:40:36Z","timestamp":1753602036389,"version":"3.37.3"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB0204403,20I7YFB1401202,2018YFB1003500"],"award-info":[{"award-number":["2018YFB0204403,20I7YFB1401202,2018YFB1003500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687948","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"930-937","source":"Crossref","is-referenced-by-count":9,"title":["Cyclegean: Cycle Generative Enhanced Adversarial Network for Voice Conversion"],"prefix":"10.1109","author":[{"given":"Xulong","family":"Zhang","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward","family":"Xiao","sequence":"additional","affiliation":[{"name":"Aquinas International Academy,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref36","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume":"37","author":"ganin","year":"2015","journal-title":"Thirty-second International Conference on Machine Learning (ICML)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.04.003"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947513"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855141"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-271"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2010.5656960"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659658"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1198"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1504"},{"key":"ref19","first-page":"1","article-title":"Phonetic posteriorgrams for many-to-one voice conversion without parallel data training","author":"sun","year":"2016","journal-title":"2016 IEEE International Conference on Multimedia and Expo (ICME)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref27","article-title":"A new multi-speaker formant synthesizer that applies voice conversion techniques","author":"guti\u00e9rrez-arriola","year":"0","journal-title":"Seventh European Conference on Speech Communication and Technology"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955289"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1798"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1542"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","article-title":"Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory","volume":"15","author":"tomoki","year":"2007","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref20","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682589"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1785"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref26","first-page":"3364","article-title":"Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks","author":"hsu","year":"0","journal-title":"18th Annual Conference of the International Speech Communication Association (Interspeech)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036784"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687948.pdf?arnumber=9687948","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:49Z","timestamp":1652733709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687948\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687948","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}