{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:37:49Z","timestamp":1776883069037,"version":"3.51.2"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["17H01763"],"award-info":[{"award-number":["17H01763"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1109\/taslp.2019.2917232","type":"journal-article","created":{"date-parts":[[2019,5,25]],"date-time":"2019-05-25T04:19:52Z","timestamp":1558757992000},"page":"1432-1443","source":"Crossref","is-referenced-by-count":90,"title":["ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational Autoencoder"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3102-0162","authenticated-orcid":false,"given":"Hirokazu","family":"Kameoka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuhiro","family":"Kaneko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kou","family":"Tanaka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobukatsu","family":"Hojo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"201","article-title":"Information maximization in noisy channels: A variational approach","author":"barber","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"2172","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","first-page":"1857","article-title":"Learning to discover cross-domain relations with generative adversarial networks","author":"kim","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref30","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref37","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","article-title":"StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation","author":"choi","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.29007\/s4t1"},{"key":"ref62","year":"2017"},{"key":"ref61","year":"2017"},{"key":"ref63","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2522655"},{"key":"ref27","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","author":"kingma","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","year":"2016"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref29","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref1","article-title":"ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder","author":"kameoka","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref22","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1587\/transfun.E96.A.1946"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953215"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-116"},{"key":"ref26","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639636"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.347"},{"key":"ref57","year":"2015"},{"key":"ref56","year":"2016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324328"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref40","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier GANs","volume":"70","author":"odena","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1403"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078543"},{"key":"ref16","first-page":"2278","article-title":"High-order sequence modeling using speaker-dependent recurrent temporal restricted Boltzmann machines for voice conversion","author":"nakashika","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1183"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref49","article-title":"FloWaveNet: A generative flow for raw audio","author":"kim","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref46","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref47","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref41","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref44","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref43","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8736368\/08718381.pdf?arnumber=8718381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:13:25Z","timestamp":1657746805000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8718381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":66,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2917232","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9]]}}}