{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:18:46Z","timestamp":1740169126406,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009023","name":"Precursory Research for Embryonic Science and Technology","doi-asserted-by":"publisher","award":["JPMJPR1657"],"award-info":[{"award-number":["JPMJPR1657"]}],"id":[{"id":"10.13039\/501100009023","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP17H06101"],"award-info":[{"award-number":["JP17H06101"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JST CREST [https:\/\/www.jst.go.jp\/kisoken\/crest\/en\/about\/]","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2955978","type":"journal-article","created":{"date-parts":[[2019,11,26]],"date-time":"2019-11-26T21:37:49Z","timestamp":1574804269000},"page":"171114-171125","source":"Crossref","is-referenced-by-count":3,"title":["Voice Conversion With CycleRNN-Based Spectral Mapping and Finely Tuned WaveNet Vocoder"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2792-8418","authenticated-orcid":false,"given":"Patrick","family":"Lumban Tobing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Chiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDL8015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682156"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1080"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639608"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"journal-title":"PyWorldVocoder—A Python Wrapper for World Vocoder","year":"0","author":"hsu","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.006"},{"journal-title":"WaveNet-Vocoder Implementation With PyTorch","year":"0","author":"hayashi","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.004"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2753583"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045239"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283471"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-35"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-31"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2162","DOI":"10.21437\/Interspeech.2010-596","article-title":"Applying voice conversion to concatenative singing-voice synthesis","author":"villavicencio","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"3067","DOI":"10.21437\/Interspeech.2013-669","article-title":"A hybrid approach to electrolaryngeal speech enhancement based on spectral subtraction and statistical voice conversion","author":"tanaka","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2286917"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168479"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-29"},{"key":"ref20","volume":"2","author":"fant","year":"1970","journal-title":"Acoustic theory of speech production with calculations based on X-ray studies of Russian articulations"},{"journal-title":"dtw-c","year":"0","author":"tobing","key":"ref45"},{"key":"ref22","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2016","journal-title":"arXiv 1612 07837"},{"key":"ref47","first-page":"3976","article-title":"Bias and statistical significance in evaluating speech synthesis with mean opinion scores","author":"rosenberg","year":"2018","journal-title":"Proc INTERSPEECH"},{"key":"ref21","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref42","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref41","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref23","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"arXiv 1802 08435"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08913551.pdf?arnumber=8913551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T19:37:17Z","timestamp":1722109037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8913551\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2955978","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}