{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T23:57:36Z","timestamp":1774742256885,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"MIC\/SCOPE","award":["182103104"],"award-info":[{"award-number":["182103104"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3205755","type":"journal-article","created":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T19:43:15Z","timestamp":1663098195000},"page":"2981-2992","source":"Crossref","is-referenced-by-count":5,"title":["Voice Conversion Based on Deep Neural Networks for Time-Variant Linear Transformations"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3152-0239","authenticated-orcid":false,"given":"Gaku","family":"Kotani","sequence":"first","affiliation":[{"name":"University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Saito","sequence":"additional","affiliation":[{"name":"University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8778-9555","authenticated-orcid":false,"given":"Nobuaki","family":"Minematsu","sequence":"additional","affiliation":[{"name":"University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940827"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.759801"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-419"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref8","first-page":"201","article-title":"Exemplar-based voice conversion using non-negative spectrogram deconvolution","volume-title":"Proc. ISCA Workshop Speech Synth.","author":"Wu","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-666"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177437"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038669"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1232"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/VCCBC.2020-16"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-613"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-268"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/vcc_bc.2020-14"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1840"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2162"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1239"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDL8034"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.848881"},{"issue":"5","key":"ref31","first-page":"367","article-title":"Rotational properties of vocal tract length difference in cepstral space","volume":"15","author":"Saito","year":"2011","journal-title":"J. ResearchInstitute Signal Process."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282216"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164788"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-539"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/89.650310"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-14"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-448"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-1035"},{"key":"ref46","article-title":"On the convergence of Adam and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddi","year":"2018"},{"key":"ref47","first-page":"223","article-title":"The CMU ARCTIC speech databases","volume-title":"Proc. 5th ISCA Speech Synth. Workshop","author":"Kominek","year":"2004"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.21437\/Eurospeech.2001-396","volume-title":"Proc. EUROSPEECH","author":"Lee","year":"2001"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP.2016.7877819"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1331"},{"key":"ref51","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref52","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","volume-title":"Proc. Int. Conf. Representations","author":"Mehri","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1965"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09889291.pdf?arnumber=9889291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:13:29Z","timestamp":1705958009000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9889291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3205755","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}