{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T23:54:18Z","timestamp":1778716458250,"version":"3.51.4"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/apsipa.2016.7820901","type":"proceedings-article","created":{"date-parts":[[2017,1,20]],"date-time":"2017-01-20T02:38:58Z","timestamp":1484879938000},"page":"1-6","source":"Crossref","is-referenced-by-count":16,"title":["On the use of I-vectors and average voice model for voice conversion without parallel data"],"prefix":"10.1109","author":[{"given":"Jie","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2551865"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472664"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref12","first-page":"369","article-title":"Voice conversion in high-order eigen space using deep belief nets","author":"nakashika","year":"2013","journal-title":"INTER-SPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref15","first-page":"2413","article-title":"Voice conversion with smoothed gmm and map adaptation","author":"chen","year":"2003","journal-title":"Eurospeech-2003"},{"key":"ref16","article-title":"Map-based adaptation for speech conversion using adaptation data selection and non-parallel training","author":"lee","year":"2006","journal-title":"INTER-SPEECH"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-613","article-title":"Eigenvoice conversion based on gaussian mixture model","author":"toda","year":"2006","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/89.876308"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E93.D.1589"},{"key":"ref28","article-title":"Msr identity toolbox vI. 0: A matlab toolbox for speaker-recognition research","volume":"1","author":"sadjadi","year":"2013","journal-title":"Speech and Language Processing Technical Committee Newsletter"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"2765","DOI":"10.21437\/Interspeech.2011-692","article-title":"Intonation conversion from neutral to expressive speech","author":"veaux","year":"2011","journal-title":"InterSpeech"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479278"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref29","first-page":"547","article-title":"Introducing currennt-the munich open-source cuda recurrent neural network toolkit","volume":"16","author":"weninger","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","first-page":"2472","article-title":"Esophageal speech enhancement based on statistical voice conversion with gaussian mixture models","volume":"93","author":"hironori","year":"2010","journal-title":"IEICE Transactions on Information and Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2165944"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1331"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596185"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"ref23","article-title":"A study of speaker adaptation for dnn-based speech synthesis","author":"wu","year":"2015","journal-title":"InterSpeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref25","article-title":"Discriminant nap for svm speaker recognition","author":"vogt","year":"2008","journal-title":"Odyssey"}],"event":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","location":"Jeju, South Korea","start":{"date-parts":[[2016,12,13]]},"end":{"date-parts":[[2016,12,16]]}},"container-title":["2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7803478\/7820670\/07820901.pdf?arnumber=7820901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T06:45:39Z","timestamp":1658472339000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7820901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/apsipa.2016.7820901","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}