{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:19:50Z","timestamp":1777486790166,"version":"3.51.4"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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":[[2024]]},"DOI":"10.1109\/taslp.2024.3379901","type":"journal-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T18:30:46Z","timestamp":1710959446000},"page":"2213-2226","source":"Crossref","is-referenced-by-count":9,"title":["VoiceGrad: Non-Parallel Any-to-Many Voice Conversion With Annealed Langevin Dynamics"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3102-0162","authenticated-orcid":false,"given":"Hirokazu","family":"Kameoka","sequence":"first","affiliation":[{"name":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8016-5144","authenticated-orcid":false,"given":"Takuhiro","family":"Kaneko","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7107-607X","authenticated-orcid":false,"given":"Kou","family":"Tanaka","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobukatsu","family":"Hojo","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3990-3740","authenticated-orcid":false,"given":"Shogo","family":"Seki","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3379901"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198872"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref10","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref11","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref13","first-page":"1","article-title":"NICE: Non-linear independent components estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh","year":"2015"},{"key":"ref14","first-page":"1","article-title":"Density estimation using real NVP","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh","year":"2017"},{"key":"ref15","first-page":"10215","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. Adv. Neural Inf. Process Syst.","volume":"31","author":"Kingma","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref18","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706604"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref22","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/3305381"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2307"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036784"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref34","first-page":"6793","article-title":"Blow: A single-scale hyperconditioned flow for non-parallel raw-audio voice conversion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Serr","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1066"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047262"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900072"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-247"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1504"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-36"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/vcc_bc.2020-14"},{"key":"ref48","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song","year":"2019"},{"key":"ref49","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Song","year":"2020"},{"key":"ref50","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref51","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Nichol","year":"2021"},{"key":"ref52","first-page":"695","article-title":"Estimation of non-normalized statistical models using score matching","volume":"6","author":"Hyvrinen","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref54","first-page":"1","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"},{"key":"ref56","first-page":"1","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Popov","year":"2022"},{"key":"ref57","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref60","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin","year":"2017"},{"key":"ref61","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot","year":"2010"},{"key":"ref62","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Salimans","year":"2016"},{"key":"ref63","first-page":"223","article-title":"The CMU arctic speech databases","volume-title":"Proc. ISCA Speech Synth. Workshop","author":"Kominek","year":"2004"},{"key":"ref64","first-page":"1","article-title":"Towards principled methods for training generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Arjovsky","year":"2017"},{"key":"ref65","first-page":"5769","article-title":"Improved training of wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gulrajani","year":"2017"},{"key":"ref66","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref67","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10476715.pdf?arnumber=10476715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T18:48:12Z","timestamp":1712688492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10476715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3379901","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}