{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:28:06Z","timestamp":1780392486176,"version":"3.54.1"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682897","type":"proceedings-article","created":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T20:07:22Z","timestamp":1555445242000},"page":"6820-6824","source":"Crossref","is-referenced-by-count":214,"title":["Cyclegan-VC2: Improved Cyclegan-based Non-parallel Voice Conversion"],"prefix":"10.1109","author":[{"given":"Takuhiro","family":"Kaneko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kou","family":"Tanaka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nobukatsu","family":"Hojo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953090"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","first-page":"1857","article-title":"Learning to discover cross-domain relations with generative adversarial networks","author":"kim","year":"2017","journal-title":"Proc ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.20"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref35","article-title":"Unsupervised cross-domain image generation","author":"taigman","year":"2017","journal-title":"Proc ICLR"},{"key":"ref34","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"ref27","article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","author":"kaneko","year":"2017"},{"key":"ref29","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proceedings of NPIS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857790"},{"key":"ref22","first-page":"2446","article-title":"Eigenvoice conversion based on Gaussian mixture model","author":"toda","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref21","first-page":"2254","article-title":"MAP-based adaptation for speech conversion using adaptation data selection and non-parallel training","author":"lee","year":"2006","journal-title":"Proc ICSLP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593263"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"653","DOI":"10.21437\/Interspeech.2011-268","article-title":"One-to-many voice conversion based on tensor representation of speaker space","author":"saito","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref26","article-title":"ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder","author":"kameoka","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref52","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1403"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-962"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078543"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282025"},{"key":"ref14","first-page":"2278","article-title":"High-order sequence modeling using speaker-dependent recurrent temporal restricted Boltzmann machines for voice conversion","author":"nakashika","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1587\/transfun.E96.A.1946"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1109\/TASLP.2014.2333242","article-title":"Exemplar-based sparse representation with residual compensation for voice conversion","volume":"22","author":"wu","year":"2014","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-116"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref46","first-page":"693","article-title":"F0 transformation techniques for statistical voice conversion with direct waveform modification with spectral differential","author":"kobayashi","year":"2016","journal-title":"Proc SLT"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.347"},{"key":"ref48","first-page":"2016","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"0"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639636"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref43","first-page":"702","article-title":"Precomputed real-time texture synthesis with Markovian generative adversarial networks","author":"li","year":"2016","journal-title":"Proc ECCV"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682897.pdf?arnumber=8682897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T02:54:04Z","timestamp":1663296844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682897\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682897","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}