{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T18:51:05Z","timestamp":1774551065782,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054534","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7769-7773","source":"Crossref","is-referenced-by-count":11,"title":["Multi-Speaker and Multi-Domain Emotional Voice Conversion Using Factorized Hierarchical Variational Autoencoder"],"prefix":"10.1109","author":[{"given":"Mohamed","family":"Elgaar","sequence":"first","affiliation":[{"name":"KAIST"}]},{"given":"Jungbae","family":"Park","sequence":"additional","affiliation":[{"name":"KAIST"}]},{"given":"Sang Wan","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST"}]}],"member":"263","reference":[{"key":"ref10","first-page":"6306","article-title":"Neural discrete representation learning","author":"den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref12","first-page":"2172","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"6","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume":"2","author":"higgins","year":"2017","journal-title":"ICLRE"},{"key":"ref14","year":"0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2525"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683514"},{"key":"ref17","first-page":"1837","article-title":"Max-margin deep generative models","author":"li","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref4","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"Proc 2nd Int Conf on Learning Representations ICLR 2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929050"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref5","article-title":"Gmm-based voice conversion applied to emotional speech synthesis","author":"kawanami","year":"2003","journal-title":"Eighth European Conference on Speech Communication and Technology"},{"key":"ref8","article-title":"Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks","author":"hsu","year":"2017","journal-title":"CoRR"},{"key":"ref7","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2018","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674422"},{"key":"ref9","article-title":"Generative adversarial networks for unpaired voice transformation on impaired speech","author":"chen","year":"2018"},{"key":"ref1","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Nonparallel emotional speech conversion","author":"gao","year":"2018","journal-title":"CoRR"},{"key":"ref22","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/TASL.2006.876113","article-title":"Prosody conversion from neutral speech to emotional speech","volume":"14","author":"tao","year":"2006","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054534.pdf?arnumber=9054534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:57:30Z","timestamp":1659484650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054534\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054534","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}