{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T02:17:41Z","timestamp":1768616261268,"version":"3.49.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2012,8,1]],"date-time":"2012-08-01T00:00:00Z","timestamp":1343779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2012,8]]},"DOI":"10.1109\/tasl.2012.2188628","type":"journal-article","created":{"date-parts":[[2012,2,22]],"date-time":"2012-02-22T22:14:13Z","timestamp":1329948853000},"page":"1784-1794","source":"Crossref","is-referenced-by-count":17,"title":["Statistical Voice Conversion Based on Noisy Channel Model"],"prefix":"10.1109","volume":"20","author":[{"given":"Daisuke","family":"Saito","sequence":"first","affiliation":[]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]},{"given":"Atsushi","family":"Nakamura","sequence":"additional","affiliation":[]},{"given":"Nobuaki","family":"Minematsu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947373"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828640"},{"key":"ref31","first-page":"191","article-title":"An introduction of trajectory model into HMM-based speech synthesis","author":"zen","year":"2004","journal-title":"Proc 5th ISCA Speech Synth Workshop"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040791"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876112"},{"key":"ref35","first-page":"1193","article-title":"Including dynamic and phonetic information in voice conversion systems","author":"duxans","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(94)00058-I"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857790"},{"key":"ref14","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":"ref15","first-page":"2446","article-title":"Eigenvoice conversion based on Gaussian mixture model","author":"toda","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/78.80902"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/89.876308"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"2413","DOI":"10.21437\/Eurospeech.2003-664","article-title":"Voice conversion with smoothed GMM and MAP adaptation","author":"chen","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940827"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref6","first-page":"1847","article-title":"Narrowband to wideband conversion of speech using GMM based transformation","author":"park","year":"2000","journal-title":"Proc ICASSP"},{"key":"ref29","author":"kominek","year":"2003","journal-title":"CMU ARCTIC Databases for Speech Synthesis"},{"key":"ref5","first-page":"57","article-title":"Uncertainty decoding with SPLICE for noise robust speech recognition","author":"droppo","year":"2002","journal-title":"Proc ICASSP"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"308","DOI":"10.21437\/Interspeech.2009-102","article-title":"Speech generation from hand gestures based on space mapping","author":"kunikoshi","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref7","first-page":"1395","article-title":"Speaking aid system for total laryngectomees using voice conversion of body transmitted artificial speech","author":"nakamura","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"57","DOI":"10.2478\/v10187-010-0008-5","article-title":"Voice conversion using pitch shifting algorithm by time stretching with PSOLA and re-sampling","volume":"61","author":"mousa","year":"2010","journal-title":"J Elect Eng"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1109\/TSA.2005.860839","article-title":"Quality-enhanced voice morphing using maximum likelihood transformations","volume":"14","author":"ye","year":"2006","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/112405.112427"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"1728","DOI":"10.21437\/Interspeech.2010-496","article-title":"Probabilistic integration of joint density model and speaker model for voice conversion","author":"saito","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.925147"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164788"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/6176018\/06156420.pdf?arnumber=6156420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T07:00:41Z","timestamp":1713596441000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6156420\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,8]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2012.2188628","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,8]]}}}