{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:04:00Z","timestamp":1779383040490,"version":"3.53.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"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":["2017YFB1002202"],"award-info":[{"award-number":["2017YFB1002202"]}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61871358"],"award-info":[{"award-number":["61871358"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"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":[[2019,3]]},"DOI":"10.1109\/taslp.2019.2892235","type":"journal-article","created":{"date-parts":[[2019,1,10]],"date-time":"2019-01-10T20:04:12Z","timestamp":1547150652000},"page":"631-644","source":"Crossref","is-referenced-by-count":100,"title":["Sequence-to-Sequence Acoustic Modeling for Voice Conversion"],"prefix":"10.1109","volume":"27","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-Juan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Jiang","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.2018.8461452"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref33","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":"ref32","first-page":"1283","article-title":"Sequence-to-sequence voice conversion with similarity metric learned using generative adversarial networks","author":"kaneko","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref31","article-title":"Voice conversion with deep learning","author":"ramos","year":"2016"},{"key":"ref30","article-title":"VoiceLoop: Voice fitting and synthesis via a phonological loop","author":"taigman","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461948"},{"key":"ref35","first-page":"1138","article-title":"Statistical voice conversion with WaveNet-based waveform generation","author":"kobayashi","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref34","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"den oord","year":"0","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref28","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref29","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"},{"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","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref24","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":"ref23","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":"ref26","article-title":"Deep Voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref50","article-title":"CMU ARCTIC databases for speech synthesis","author":"kominek","year":"2003"},{"key":"ref51","article-title":"Zoneout: Regularizing RNNs by randomly preserving hidden activations","author":"krueger","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2269291"},{"key":"ref55","article-title":"Merlin: An open source neural network speech synthesis system","author":"wu","year":"0","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref54","first-page":"2266","article-title":"Maximum likelihood voice conversion based on GMM with STRAIGHT mixed excitation","author":"ohtani","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675407"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2012.05.027"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461878"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2379589"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP.2016.7877819"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref17","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref19","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"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":"10.1109\/TASL.2007.907344"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref49","article-title":"Empirical evaluation of recitified acitvations in convolutional network","author":"xu","year":"0","journal-title":"Proc ICML Deep Learn Workshop"},{"key":"ref9","author":"titterington","year":"1985","journal-title":"Statistical Analysis of Finite Mixture Distributions"},{"key":"ref46","article-title":"Mixture density networks","author":"bishop","year":"1994"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref48","author":"christopher","year":"2016","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref44","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8579631\/08607053.pdf?arnumber=8607053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:43:51Z","timestamp":1657745031000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8607053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":56,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2892235","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3]]}}}