{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T05:16:42Z","timestamp":1719465402115},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"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":[[2013,1]]},"DOI":"10.1109\/tasl.2012.2213247","type":"journal-article","created":{"date-parts":[[2012,8,15]],"date-time":"2012-08-15T18:02:56Z","timestamp":1345053776000},"page":"51-62","source":"Crossref","is-referenced-by-count":15,"title":["Personalized Spectral and Prosody Conversion Using Frame-Based Codeword Distribution and Adaptive CRF"],"prefix":"10.1109","volume":"21","author":[{"family":"Yi-Chin Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Chung-Hsien Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Yu-Ting Chao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"573","DOI":"10.21437\/Interspeech.2008-169","article-title":"Articulatory control of HMM-based parametric speech synthesis driven by phonetic knowledge","author":"ling","year":"2008","journal-title":"Proc Interspeech'08"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J R Statist Soc B"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF01589116"},{"key":"ref30","author":"zhang","year":"2008","journal-title":"Information Retrieval Technology"},{"key":"ref35","author":"zen","year":"2007","journal-title":"The HMM-Based Speech Synthesis System (HTS) Version 2 0 1"},{"key":"ref34","first-page":"94","article-title":"TH-CoSS, a Mandarin speech corpus for TTS","volume":"21","author":"cai","year":"2007","journal-title":"J Chin Inf Process"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TASL.2006.876112","article-title":"Voice conversion using duration-embedded Bi-HMMs for expressive speech synthesis","volume":"14","author":"wu","year":"2006","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.1991.176405"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318521"},{"key":"ref14","first-page":"1571","article-title":"Phonetic Alignment: Speech Synthesis vs. Hybrid HMM\/ANN","volume":"4","author":"malfrere","year":"1998","journal-title":"Proc ICSLP'98"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607292"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034771"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040791"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.015"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"908","DOI":"10.1121\/1.1841572","article-title":"A statistics-based pitch contour model for mandarin speech","volume":"117","author":"chen","year":"2005","journal-title":"J Acoust Soc Amer"},{"key":"ref28","first-page":"2405","article-title":"Pitch Contour Model for Chinese text-to-speech using CART and statistical model","author":"dong","year":"2002","journal-title":"Proc ICSLP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2035029"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1109\/ICME.2000.869636","article-title":"Prosody model in a Mandarin text-to-speech system based on a hierarchical approach","volume":"1","author":"pan","year":"2000","journal-title":"Proc IEEE Int Conf Multimedia and Expo"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref6","first-page":"5","article-title":"Including dynamic and phonetic information in voice conversion systems","author":"duxans","year":"2004","journal-title":"Proc ICSLP'04"},{"key":"ref29","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E93.D.1589"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref9","first-page":"1225","article-title":"Conversion function clustering and selection using linguistic and spectral information for emotional voice conversion","volume":"56","author":"hsia","year":"2007","journal-title":"IEEE Trans Comput"},{"key":"ref1","article-title":"Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV","author":"yamagishi","year":"2007","journal-title":"Proc ISCA SSW6"},{"key":"ref20","first-page":"901","article-title":"Segmental tonal modeling for phone set design in mandarin LVCSR","author":"huang","year":"2004","journal-title":"Proc ICASSP'04"},{"key":"ref22","first-page":"61","article-title":"Locating boundaries for prosodic constituents in unrestricted mandarin texts","volume":"6","author":"chu","year":"2001","journal-title":"Comput Linguist Chinese Lang Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596185"},{"key":"ref24","first-page":"1771","article-title":"A corpus-based Mandarin text-to-speech synthesizer","volume":"s29","author":"benijamin","year":"1994","journal-title":"Proc ICSLP"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/29.31286"},{"key":"ref26","first-page":"1074","article-title":"Synthesis of natural sounding pitch contours in isolated utterances using hidden Markov models","volume":"assp 34","author":"andrej","year":"1986","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"2427","DOI":"10.21437\/Interspeech.2009-306","article-title":"Analysis and recognition of accentual patterns","author":"wagner","year":"2009","journal-title":"Proc Interspeech'09"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/6334458\/06269060.pdf?arnumber=6269060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,28]],"date-time":"2024-04-28T12:42:21Z","timestamp":1714308141000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6269060\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,1]]},"references-count":35,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2012.2213247","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,1]]}}}