{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T19:22:17Z","timestamp":1759778537010,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2010,11,1]],"date-time":"2010-11-01T00:00:00Z","timestamp":1288569600000},"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":[[2010,11]]},"DOI":"10.1109\/tasl.2010.2040791","type":"journal-article","created":{"date-parts":[[2010,4,7]],"date-time":"2010-04-07T18:44:46Z","timestamp":1270665886000},"page":"1994-2003","source":"Crossref","is-referenced-by-count":23,"title":["Exploiting Prosody Hierarchy and Dynamic Features for Pitch Modeling and Generation in HMM-Based Speech Synthesis"],"prefix":"10.1109","volume":"18","author":[{"family":"Chi-Chun Hsia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Chung-Hsien Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Jung-Yun Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1097\/00006534-199102000-00029"},{"key":"ref38","first-page":"103","author":"lin","year":"1992","journal-title":"Phonetic Tutorials"},{"key":"ref33","first-page":"3","author":"klein","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596185"},{"key":"ref37","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":"ref36","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":"ref35","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1250\/ast.21.79"},{"key":"ref10","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":"ref40","first-page":"89","article-title":"minimum generation error training for hmm-based speech synthesis","author":"wu","year":"2006","journal-title":"Proc ICASSP'06"},{"key":"ref11","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 Expo"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/89.668817"},{"key":"ref13","first-page":"243","article-title":"efficient model of establishing words tone dictionary for korean tts system","author":"kim","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref14","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'02"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00075-3"},{"journal-title":"Lecture Nodes of Artificial Intelligence","year":"2004","author":"tao","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.015"},{"journal-title":"The determination analysis and synthesis of fundamental frequency","year":"2002","author":"sun","key":"ref18"},{"key":"ref19","first-page":"251","article-title":"speech rate and prosody units: evidence of interaction from mandarin chinese","author":"tseng","year":"2004","journal-title":"Proc 3rd Int Conf Speech Prosody"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.21437\/Interspeech.2008-558","article-title":"multilevel parametric-based f0 model for speech synthesis","author":"latorre","year":"2008","journal-title":"Proc Interspeech'08"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"581","DOI":"10.21437\/Eurospeech.1995-148","article-title":"optimizing selection of units from speech database for concatenative synthesis","author":"black","year":"1995","journal-title":"Proc EuroSpeech'95"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518524"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/26.61370"},{"key":"ref5","article-title":"the hmm-based speech synthesis system version 2.0","author":"zen","year":"2007","journal-title":"Proc ISCA SSW6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/29.31286"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2016394"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889752"},{"key":"ref9","first-page":"1771","article-title":"a corpus-based mandarin text-to-speech synthesizer","author":"benijamin","year":"1994","journal-title":"Proc ICSLP'94"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.03.005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1121\/1.1841572"},{"key":"ref22","first-page":"169","article-title":"a mandarin tts system with an integrated prosodic model","author":"pin","year":"2004","journal-title":"Proc ISCSLP '04"},{"key":"ref21","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":"ref24","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.21437\/Eurospeech.1999-513","article-title":"simultaneous modeling of spectrum, pitch and duration in hmm-based speech synthesis","author":"yoshimura","year":"1999","journal-title":"Proc Eurospeech'99"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1250\/ast.5.233"},{"key":"ref26","first-page":"1383","article-title":"the tile intonation model","author":"taylor","year":"1998","journal-title":"Proc ICSLP'98"},{"key":"ref25","first-page":"867","article-title":"tobi: a standard for labeling english prosody","author":"silverman","year":"1992","journal-title":"Proc ICSLP'92"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/5559658\/05443736.pdf?arnumber=5443736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T22:00:01Z","timestamp":1740002401000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5443736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,11]]},"references-count":40,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2010.2040791","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"type":"print","value":"1558-7916"},{"type":"electronic","value":"1558-7924"}],"subject":[],"published":{"date-parts":[[2010,11]]}}}