{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:43:25Z","timestamp":1760132605547,"version":"3.37.3"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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"]}]},{"name":"JST CREST","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.3036784","type":"journal-article","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T21:38:07Z","timestamp":1605130687000},"page":"2982-2995","source":"Crossref","is-referenced-by-count":20,"title":["Nonparallel Voice Conversion With Augmented Classifier Star Generative Adversarial Networks"],"prefix":"10.1109","volume":"28","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":"ref73","first-page":"14 910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639636"},{"article-title":"Neural source-filter-based waveform model for statistical parametric speech synthesis","year":"2018","author":"wang","key":"ref71"},{"article-title":"FloWaveNet: A generative flow for raw audio","year":"2018","author":"kim","key":"ref70"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref77","first-page":"223","article-title":"The CMU Arctic speech databases","author":"kominek","year":"0","journal-title":"Proc ISCA Speech Synth Workshop"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref75","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953090"},{"article-title":"The voice conversion challenge 2018: Promoting development of parallel and nonparallel methods","year":"2018","author":"trueba","key":"ref78"},{"year":"0","key":"ref79"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2910637"},{"key":"ref32","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1587\/transfun.E96.A.1946"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref37","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","author":"kingma","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"article-title":"Auto-encoding variational Bayes","year":"2013","author":"kingma","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"article-title":"Blow: A single-scale hyperconditioned flow for non-parallel raw-audio voice conversion","year":"2019","author":"serr\u00e0","key":"ref62"},{"year":"0","key":"ref61"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-961"},{"article-title":"Efficient neural audio synthesis","year":"2018","author":"kalchbrenner","key":"ref64"},{"key":"ref27","first-page":"6309","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","year":"2016","author":"mehri","key":"ref65"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","year":"2017","author":"van den oord","key":"ref67"},{"article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","year":"2019","author":"ping","key":"ref68"},{"article-title":"WaveGlow: A flow-based generative network for speech synthesis","year":"2018","author":"prenger","key":"ref69"},{"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","first-page":"1","article-title":"Parallel-data-free, many-to-many voice conversion using an adaptive restricted Boltzmann machine","author":"nakashika","year":"0","journal-title":"Proc Int Workshop Mach Learn Signal Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1183"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-116"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","year":"2019","author":"kaneko","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953215"},{"article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","year":"2017","author":"van den oord","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref90","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","first-page":"5769","article-title":"Improved training of Wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"journal-title":"Optimal Transport Old and New","year":"2008","author":"villani","key":"ref58"},{"key":"ref57","first-page":"1","article-title":"Towards principled methods for training generative adversarial networks","author":"arjovsky","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2307"},{"article-title":"Non-parallel sequence-to-sequence voice conversion with disentangled linguistic and speaker representations","year":"2019","author":"zhang","key":"ref55"},{"article-title":"Many-to-many voice transformer network","year":"2020","author":"kameoka","key":"ref54"},{"article-title":"Voice transformer network: Sequence-to-sequence voice conversion using transformer with text-to-speech pretraining","year":"2019","author":"huang","key":"ref53"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"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","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078543"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDL8034"},{"year":"0","key":"ref82"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.29007\/s4t1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"year":"0","key":"ref84"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1403"},{"year":"0","key":"ref83"},{"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":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.347"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"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":"ref85","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2522655"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198872"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref49"},{"year":"0","key":"ref87"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"article-title":"Autoencoding beyond pixels using a learned similarity metric","year":"2015","author":"larsen","key":"ref48"},{"article-title":"StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation","year":"2017","author":"choi","key":"ref47"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553396"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-962"},{"key":"ref44","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":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09256995.pdf?arnumber=9256995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:20Z","timestamp":1651080680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9256995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3036784","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2020]]}}}