{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:44:11Z","timestamp":1778053451676,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639535","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T18:36:34Z","timestamp":1550169394000},"page":"266-273","source":"Crossref","is-referenced-by-count":258,"title":["StarGAN-VC: non-parallel many-to-many Voice Conversion Using Star Generative Adversarial Networks"],"prefix":"10.1109","author":[{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553396"},{"key":"ref33","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Adv NIPS"},{"key":"ref32","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","author":"kingma","year":"2014","journal-title":"Adv NIPS"},{"key":"ref31","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.21437\/Interspeech.2017-962","article-title":"Generative adversarial network-based postfilter for STFT spectrograms","author":"kaneko","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref36","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"arXiv 1703 09452 [cs LG]"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953090"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-961","article-title":"Parallel-data-free many-to-many voice conversion based on dnn integrated with eigenspace using a non-parallel speech corpus","author":"hashimoto","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref27","first-page":"6309","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Adv NIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref20","article-title":"Parallel-data-free, many-to-many voice conversion using an adaptive restricted Boltzmann machine","author":"nakashika","year":"2015","journal-title":"Proc MLSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref21","first-page":"1770","article-title":"Modeling and transforming speech using variational autoencoders","author":"blaauw","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-116"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"3364","DOI":"10.21437\/Interspeech.2017-63","article-title":"Voice conversion from unaligned corpora using variational autoencoding Wasserstein generative adversarial networks","author":"hsu","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref26","article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","author":"kaneko","year":"2017","journal-title":"arXiv 1711 11293 [stat ML]"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953215"},{"key":"ref50","article-title":"The voice conversion challenge 2018: Promoting development of parallel and nonparallel methods","author":"lorenzo-trueba","year":"2018","journal-title":"arXiv 1804 04262 [eess AS]"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.347"},{"key":"ref52","article-title":"StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks","author":"kameoka","year":"2018","journal-title":"arXiv 1806 02169 [cs SD]"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref40","first-page":"1857","article-title":"Learning to discover cross-domain relations with generative adversarial networks","author":"kim","year":"2017","journal-title":"Proc ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078543"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDL8034"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1587\/transfun.E96.A.1946"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1403"},{"key":"ref19","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041113"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref45","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2017","journal-title":"arXiv 1711 10433 [cs LG]"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461746"},{"key":"ref47","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc ICML"},{"key":"ref42","article-title":"StarGAN: Unified generative adversarial networks for multidomain image-to-image translation","author":"choi","year":"2017","journal-title":"arXiv 1711 09020 [cs CV]"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref44","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499 [cs SD]"},{"key":"ref43","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"2015","journal-title":"arXiv 1512 09300 [cs LG]"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","location":"Athens, Greece","start":{"date-parts":[[2018,12,18]]},"end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639535.pdf?arnumber=8639535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T02:43:44Z","timestamp":1643251424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639535","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}