{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T02:58:42Z","timestamp":1770433122021,"version":"3.49.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2010,8,1]],"date-time":"2010-08-01T00:00:00Z","timestamp":1280620800000},"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":[[2010,8]]},"DOI":"10.1109\/tasl.2009.2034771","type":"journal-article","created":{"date-parts":[[2009,10,22]],"date-time":"2009-10-22T19:24:11Z","timestamp":1256239451000},"page":"1394-1405","source":"Crossref","is-referenced-by-count":32,"title":["Hierarchical Prosody Conversion Using Regression-Based Clustering for Emotional Speech Synthesis"],"prefix":"10.1109","volume":"18","author":[{"family":"Chung-Hsien Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Chi-Chun Hsia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Chung-Han Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Mai-Chun Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","author":"mei","year":"1983","journal-title":"Cilin-thesaurus of Chinese words"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415185"},{"key":"ref32","first-page":"2625","article-title":"pitch accent versus lexical stress: quantifying acoustic measures related to the voice source","author":"shue","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref31","year":"0","journal-title":"The Stanford Parser A Statistical Parser"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.21437\/Interspeech.2008-421","article-title":"Maximum a posteriori adaptation for many-to-one eigenvoice conversion","author":"tani","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref37","year":"0","journal-title":"TsingHuaCorpus of Speech Synthesis TH-CoSS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861811"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"427","DOI":"10.21437\/SpeechProsody.2004-97","article-title":"Automatic analysis and synthesis of Fujisaki's intonation model for TTS","author":"agero","year":"2004","journal-title":"Proc Speech Prosody"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1121\/1.1923349","article-title":"loudness predicts prominence: fundamental frequency lends little","volume":"118","author":"kochanski","year":"2005","journal-title":"JASA"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415037"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"2845","DOI":"10.21437\/Eurospeech.2003-36","article-title":"voice conversion methods for vocal tract and pitch contour modification","author":"turk","year":"2003","journal-title":"Proc Eurospeech'03"},{"key":"ref12","first-page":"949","article-title":"stochastic modeling of spectral adjustment for high quality pitch modification","volume":"2","author":"kain","year":"2000","journal-title":"Proc ICASSP'00"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.21437\/Eurospeech.2003-31","article-title":"a new method for pitch prediction from spectral envelop and its application in voice conversion","author":"en-najjary","year":"2003","journal-title":"Proc Eurospeech'03"},{"key":"ref14","first-page":"199","article-title":"voice conversion based on joint pitch and spectral transformation with component group-gmm","author":"ma","year":"2005","journal-title":"Proc NLP-KE 2005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1250\/ast.5.233"},{"key":"ref16","first-page":"239","article-title":"stem-ml: language independent prosody description","author":"kochanski","year":"2000","journal-title":"Proc ICSLP'00"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00063-7"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/TASL.2006.876113","article-title":"Prosody conversion from neutral speech to emotional speech","volume":"14","author":"tao","year":"2006","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.015"},{"key":"ref28","first-page":"177","article-title":"a superposed prosodic model for chinese tts synthesis","author":"peng","year":"2004","journal-title":"Proc ISCSLP '04"},{"key":"ref4","first-page":"5","article-title":"including dynamic and phonetic information in voice conversion systems","author":"duxans","year":"2004","journal-title":"Proc ICSLP 2004"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2781","DOI":"10.21437\/Eurospeech.1999-696","article-title":"fixed point analysis of frequency to instantaneous frequency mapping for acurrate estimation of f0 and periodicity","author":"kawahara","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"2401","DOI":"10.21437\/Eurospeech.2003-661","article-title":"gmm-based voice conversion applied to emotional speech synthesis","author":"kawanami","year":"2003","journal-title":"Proc Eurospeech'03"},{"key":"ref6","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00081-X"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"561","DOI":"10.21437\/Eurospeech.2001-150","article-title":"Emotional speech synthesis—a review","volume":"1","author":"schrder","year":"2001","journal-title":"Proc Eurospeech'01"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref20","author":"sun","year":"2002","journal-title":"The determination analysis and synthesis of fundamental frequency"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596185"},{"key":"ref24","author":"kay","year":"1993","journal-title":"Fundamentals of Statistical Signal Processing Estimation Theory"},{"key":"ref23","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":"ref26","first-page":"901","article-title":"segmental tonal modeling for phone set design in mandarin lvcsr","volume":"1","author":"huang","year":"2004","journal-title":"Proc ICASSP'04"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/26.61370"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/5508665\/05289985.pdf?arnumber=5289985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T22:03:13Z","timestamp":1739397793000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5289985\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,8]]},"references-count":38,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2009.2034771","relation":{},"ISSN":["1558-7916"],"issn-type":[{"value":"1558-7916","type":"print"}],"subject":[],"published":{"date-parts":[[2010,8]]}}}