{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T15:24:36Z","timestamp":1783178676724,"version":"3.54.6"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JST Moonshot R&D","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]},{"DOI":"10.13039\/501100003850","name":"Inner Mongolia University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003850","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2022.3190715","type":"journal-article","created":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T19:41:25Z","timestamp":1657827685000},"page":"11-24","source":"Crossref","is-referenced-by-count":19,"title":["Decoupling Speaker-Independent Emotions for Voice Conversion via Source-Filter Networks"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4173-6319","authenticated-orcid":false,"given":"Zhaojie","family":"Luo","sequence":"first","affiliation":[{"name":"Institute of Scientific and Industrial Research, Osaka University, Toyonaka, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9508-0706","authenticated-orcid":false,"given":"Shoufeng","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Bentley, WA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4524-7413","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Inner Mongolia University, Hohhot, Inner Mongolia, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0680-5021","authenticated-orcid":false,"given":"Jun","family":"Baba","sequence":"additional","affiliation":[{"name":"CyberAgent, Inc., Shibuya-ku, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3484-0361","authenticated-orcid":false,"given":"Yuichiro","family":"Yoshikawa","sequence":"additional","affiliation":[{"name":"Graduate School of Engineer Science, Osaka University, Toyonaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"Graduate School of Engineer Science, Osaka University, Toyonaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1515087112"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2017.03.014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2590"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1037\/\/0022-3514.76.5.805"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/1534582302001001003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1037\/a0035669"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.05.016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90055-E"},{"key":"ref35","first-page":"220","article-title":"Vocal communication of emotion","volume":"2","author":"johnstone","year":"2000","journal-title":"Handbook of Emotions"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2898818"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1515\/REVNEURO.2004.15.4.241"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.5051323"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-012-0314-x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262725"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2014-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2007.1079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-017-0116-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2016.7550889"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1053"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2923951"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-7998.2009.00661.x"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref51","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref55","first-page":"3","article-title":"Group normalization","author":"wu","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref54","article-title":"JSUT corpus: Free large-scale japanese speech corpus for end-to-end speech synthesis","author":"sonobe","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-019-01701-x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref40","author":"stevens","year":"1998","journal-title":"Acoustic Phonetics (Current Studies in Linguistics)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2644258"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref15","first-page":"139","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-116"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-661"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1515\/lp-2013-0003"},{"key":"ref6","article-title":"Voice conversion using sequence-to-sequence learning of context posterior probabilities and evaluation of dual learning","author":"miyoshi","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-102"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053726"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-558704-4.50011-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref46","article-title":"Emotion and personality","author":"arnold","year":"1960"},{"key":"ref45","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","author":"qian","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/TASL.2006.876113","article-title":"Prosody conversion from neutral speech to emotional speech","volume":"14","author":"tao","year":"2006","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(83)90074-9"},{"key":"ref44","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-447"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/09829916.pdf?arnumber=9829916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:27:29Z","timestamp":1672082849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9829916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3190715","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}