{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:19:22Z","timestamp":1740169162170,"version":"3.37.3"},"reference-count":71,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency (JST), Precursory Research for Embryonic Science and Technology (PRESTO) [https:\/\/www.jst.go.jp\/kisoken\/presto\/en\/about\/index.html]","doi-asserted-by":"publisher","award":["JPMJPR1657"],"award-info":[{"award-number":["JPMJPR1657"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"JST, CREST [https:\/\/www.jst.go.jp\/kisoken\/crest\/en\/about\/]","doi-asserted-by":"publisher","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research (KAKENHI) [https:\/\/www.jsps.go.jp\/english\/e-grants\/]","doi-asserted-by":"publisher","award":["17H06101"],"award-info":[{"award-number":["17H06101"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2984007","type":"journal-article","created":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T03:20:22Z","timestamp":1585624822000},"page":"62094-62106","source":"Crossref","is-referenced-by-count":2,"title":["Non-Parallel Voice Conversion System With WaveNet Vocoder and Collapsed Speech Suppression"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4390-1354","authenticated-orcid":false,"given":"Yi-Chiao","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2792-8418","authenticated-orcid":false,"given":"Patrick Lumban","family":"Tobing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"The WaveNet With the Collapsed Speech Suppression Demo","year":"2019","key":"ref71"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-1072","article-title":"A cyclical post-filtering approach to mismatch refinement of neural vocoder for text-to-speech systems","author":"wu","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683746"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947509"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.21437\/Interspeech.2009-488","article-title":"Cross-language voice conversion based on eigenvoices","author":"charlier","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref36","first-page":"1","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2017","journal-title":"Proc ICLR"},{"key":"ref35","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"Proc of SSW6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-31"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902651"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639608"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318521"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1131"},{"key":"ref27","first-page":"2177","article-title":"Cross-language voice conversion evaluation using bilingual databases","volume":"43","author":"mashimo","year":"2002","journal-title":"IPSJ J"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref29","first-page":"1969","article-title":"Frame alignment method for cross-lingual voice conversion","author":"erro","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref67","article-title":"A heuristic approach to obtain signal envelope with a simple software implementation","author":"jarne","year":"2017","journal-title":"arXiv 1703 06812"},{"article-title":"The CMU ARCTIC speech databases for speech synthesis research","year":"2003","author":"kominek","key":"ref68"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref69","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref20","first-page":"2254","article-title":"Map-based adaptation for speech conversion using adaptation data selection and non-parallel training","author":"lee","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2522643"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639000"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367007"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.21437\/Interspeech.2009-485","article-title":"Many-to-many eigenvoice conversion with reference voice","author":"ohtani","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115676"},{"key":"ref25","first-page":"1","article-title":"Singing voice conversion method based on many-to-many eigenvoice conversion and training data generation using a singing-to-singing synthesis system","author":"doi","year":"2012","journal-title":"Proc APSIPA"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1757"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1635"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-986"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref56","first-page":"1","article-title":"FloWaveNet: A generative flow for raw audio","author":"kim","year":"2019","journal-title":"Proc ICML"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref54","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2017","journal-title":"arXiv 1711 10433"},{"key":"ref53","first-page":"1","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-116"},{"key":"ref40","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume":"1","author":"bengio","year":"2015","journal-title":"Proc NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593263"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-349"},{"key":"ref16","article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","author":"kaneko","year":"2017","journal-title":"arXiv 1711 11293"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682156"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857790"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"369","DOI":"10.21437\/Interspeech.2013-102","article-title":"Voice conversion in high-order Eigen space using deep belief nets","author":"nakashika","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-567"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1109\/TASLP.2014.2333242","article-title":"Exemplar-based sparse representation with residual compensation for voice conversion","volume":"22","author":"wu","year":"2014","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1232"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038669"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref48","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"arXiv 1802 08435"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1210"},{"key":"ref41","first-page":"1","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"Proc ICLR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-30"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09050502.pdf?arnumber=9050502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T03:24:44Z","timestamp":1722655484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9050502\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2984007","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}