{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T22:45:32Z","timestamp":1784069132227,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2010,7,1]],"date-time":"2010-07-01T00:00:00Z","timestamp":1277942400000},"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":[[2010,7]]},"DOI":"10.1109\/tasl.2010.2041688","type":"journal-article","created":{"date-parts":[[2010,6,23]],"date-time":"2010-06-23T15:05:22Z","timestamp":1277305522000},"page":"932-943","source":"Crossref","is-referenced-by-count":20,"title":["Supervisory Data Alignment for Text-Independent Voice Conversion"],"prefix":"10.1109","volume":"18","author":[{"given":"Jianhua","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jani","family":"Nurminen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilei","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2008.4697232"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2007.05.028"},{"key":"ref32","first-page":"1445","article-title":"voice conversion based on topological feature maps and time-variant filtering","author":"ansgar","year":"0","journal-title":"Proc ICSLP'96"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1993.713902"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"367","DOI":"10.21437\/Eurospeech.1993-105","article-title":"speaker normalization and adaptation based on feature-map projection","author":"knohl","year":"1993","journal-title":"Proc Eurospeech'93 3rd Eur Conf Speech Commun Technol"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2005.04.006"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.56"},{"key":"ref35","volume":"16","author":"bengio","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71701-0_33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(94)00051-B"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1996.548907"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318521"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659962"},{"key":"ref13","article-title":"voice conversion for unknown speakers","author":"ye","year":"0","journal-title":"Proc ICSLP'04"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00015-1"},{"key":"ref15","article-title":"Text-independent cross-language voice conversion","author":"sndermann","year":"2006","journal-title":"Proc ICSLP"},{"key":"ref16","article-title":"text-independent voice conversion based on state mapped codebook","author":"zhang","year":"2008","journal-title":"Proc ICASSP'08"},{"key":"ref17","author":"ladefoged","year":"1971","journal-title":"Preliminaries to Linguistic Phonetics"},{"key":"ref18","author":"labov","year":"2001","journal-title":"Principles of Linguistic Change Vol II Social Factors"},{"key":"ref19","first-page":"40","article-title":"Recherche sur la structure des voyelles orales","volume":"20","author":"essner","year":"1947","journal-title":"Archives Nerlandaises de Phontique Exprimentale"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/1427581"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-383","article-title":"voice conversion by codebook mapping of line spectral frequencies and excitation spectrum","author":"arslan","year":"1997","journal-title":"Proc EUROSPEECH'97"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-97610-0","volume":"30","author":"kohonen","year":"1995","journal-title":"Self-Organizing Maps"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1177004611"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(92)90012-V"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266370"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(94)00058-I"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2307\/522229"},{"key":"ref22","article-title":"robust and efficient quantization of speech lsf parameters using structured vector quantizers","author":"laroia","year":"1991","journal-title":"Proc ICASSP'91"},{"key":"ref21","year":"0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479789"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479789"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/89.221363"},{"key":"ref26","article-title":"manifold learning using euclidean k-nearest neighbor graphs","author":"costa","year":"2004","journal-title":"Proc ICASSP"},{"key":"ref25","volume":"202","author":"lee","year":"2000","journal-title":"Introduction to Topological Manifolds"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/5485195\/05485203.pdf?arnumber=5485203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T05:42:45Z","timestamp":1740202965000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5485203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,7]]},"references-count":41,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2010.2041688","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,7]]}}}