{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:21Z","timestamp":1740169341365,"version":"3.37.3"},"reference-count":44,"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-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002241","name":"JST","doi-asserted-by":"publisher","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3270699","type":"journal-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T18:48:36Z","timestamp":1682534916000},"page":"44590-44599","source":"Crossref","is-referenced-by-count":2,"title":["Non-Parallel Whisper-to-Normal Speaking Style Conversion Using Auxiliary Classifier Variational Autoencoder"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3990-3740","authenticated-orcid":false,"given":"Shogo","family":"Seki","sequence":"first","affiliation":[{"name":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3102-0162","authenticated-orcid":false,"given":"Hirokazu","family":"Kameoka","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuhiro","family":"Kaneko","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kou","family":"Tanaka","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref35","first-page":"223","article-title":"The CMU Arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc ISCA Speech Synth Workshop (SSW)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2280"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref10","first-page":"1","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WNYIPW.2019.8923082"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref38","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","author":"kingma","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036784"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413959"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref26","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2307"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706604"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047262"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049336"},{"key":"ref9","first-page":"1","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref40","first-page":"1","article-title":"Adam: A method for stochastic gradient optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10109017.pdf?arnumber=10109017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:28:12Z","timestamp":1686594492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10109017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3270699","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}