{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:04:05Z","timestamp":1781366645377,"version":"3.54.1"},"reference-count":60,"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":"National Key R&D Program of China","award":["2019YFF0303001"],"award-info":[{"award-number":["2019YFF0303001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871358"],"award-info":[{"award-number":["61871358"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Science and Technology Project of Anhui Province","award":["18030901016"],"award-info":[{"award-number":["18030901016"]}]}],"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.2019.2960721","type":"journal-article","created":{"date-parts":[[2019,12,19]],"date-time":"2019-12-19T20:59:16Z","timestamp":1576789156000},"page":"540-552","source":"Crossref","is-referenced-by-count":74,"title":["Non-Parallel Sequence-to-Sequence Voice Conversion With Disentangled Linguistic and Speaker Representations"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4341-3174","authenticated-orcid":false,"given":"Jing-Xuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-Rong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682589"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1504"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref30","first-page":"1268","article-title":"Voice conversion using sequence-to-sequence learning of context posterior probabilities","author":"miyoshi","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref37","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"0","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref35","first-page":"3364","article-title":"Voice conversion from unaligned corpora using variational autoencoding Wasserstein generative adversarial networks","author":"hsu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref60","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593263"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(89)90041-1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168479"},{"key":"ref20","first-page":"6785","article-title":"Improving sequence-to-sequence acoustic modeling by adding text-supervision","author":"zhang","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659962"},{"key":"ref21","first-page":"238","article-title":"Voice conversion of non-aligned data using unit selection","author":"duxans","year":"0","journal-title":"Proc TC-STAR Workshop Speech to Speech Translation"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038669"},{"key":"ref23","first-page":"1969","article-title":"Frame alignment method for cross-lingual voice conversion","author":"erro","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref50","article-title":"CMU ARCTIC databases for speech synthesis","author":"kominek","year":"2003"},{"key":"ref51","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2017"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675407"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref56","first-page":"1","article-title":"Merlin: An open source neural network speech synthesis system","author":"wu","year":"0","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref55","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref53","first-page":"1","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref52","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683204"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2379589"},{"key":"ref14","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref16","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00015-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TASL.2006.876112","article-title":"Voice conversion using duration-embedded bi-HMMs for expressive speech synthesis","volume":"14","author":"wu","year":"2006","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref45","first-page":"4006","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref48","first-page":"251","article-title":"Out of time: Automated lip sync in the wild","author":"chung","year":"0","journal-title":"Proc Asian Conf Comput Vision"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref42","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"10\ufffd040","article-title":"Neural voice cloning with a few samples","author":"arik","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref43","first-page":"3683","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08936924.pdf?arnumber=8936924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:43Z","timestamp":1651080703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8936924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2960721","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}