{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:15:26Z","timestamp":1761059726164},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T00:00:00Z","timestamp":1404172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2014,7]]},"DOI":"10.1109\/taslp.2014.2321482","type":"journal-article","created":{"date-parts":[[2014,5,2]],"date-time":"2014-05-02T18:07:19Z","timestamp":1399054039000},"page":"1158-1171","source":"Crossref","is-referenced-by-count":19,"title":["Modeling of Speaking Rate Influences on Mandarin Speech Prosody and Its Application to Speaking Rate-controlled TTS"],"prefix":"10.1109","volume":"22","author":[{"given":"Sin-Horng","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiao-Hua","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen-Yu","family":"Chiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsi-Chun","family":"Hsiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yih-Ru","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Fu","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsiu-Min","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"173","article-title":"Predicting prosodic words from lexical words-A first step towards predicting prosody from text","author":"peng","year":"2004","journal-title":"ISCSLP'04"},{"key":"ref38","first-page":"27","article-title":"A hierarchical stochastic model for automatic prediction of prosodic boundary location","volume":"20","author":"ostendorf","year":"1994","journal-title":"Comput Linguist"},{"key":"ref33","first-page":"294","article-title":"The HMM-based speech synthesis system version 2.0","author":"zen","year":"2007","journal-title":"Proc ISCA SSW6"},{"key":"ref32","author":"yoshimura","year":"2002","journal-title":"Simultaneous modeling of phonetic and prosodic parameters and characteristic conversion for HMM-based text-to-speech systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.814377"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.04.008"},{"key":"ref36","first-page":"117","article-title":"A superposed prosodic model for Chinese text-to-speech synthesis","author":"chen","year":"2004","journal-title":"Proc ISCSLP'04"},{"key":"ref35","first-page":"177","article-title":"Analysis and formulation of prosodic features of speech in standard Chinese based on a model of generating fundamental frequency contours","volume":"50","author":"hirose","year":"1994","journal-title":"J Acoust Soc Jpn"},{"key":"ref34","article-title":"HTS-2.2 source code and demonstrations","year":"0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2009.5278360"},{"key":"ref40","first-page":"61","article-title":"Locating boundaries for prosodic constituents in unrestricted mandarin texts","volume":"6","author":"chu","year":"2001","journal-title":"Computat Linguistics Chinese Language Processing"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1845","DOI":"10.21437\/Interspeech.2011-44","article-title":"Large-scale subjective evaluations of speech rate control methods for HMM-based speech synthesizers","author":"kato","year":"2011","journal-title":"Proc Interspeech'11"},{"key":"ref12","first-page":"141","author":"zu","year":"0","journal-title":"?Speech rate effects on prosodic features ?"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-202","article-title":"A new approach of speaking rate modeling for mandarin speech prosody","author":"hsieh","year":"2012","journal-title":"Proc Interspeech'10"},{"key":"ref14","first-page":"6900","article-title":"A speaking rate-controlled mandarin TTS system","author":"chen","year":"2013","journal-title":"Proc ICASSP'13"},{"key":"ref15","article-title":"Speech-rate variable HMM-based Japanese TTS system","author":"iwano","year":"2002","journal-title":"Proc TTS'02"},{"key":"ref16","first-page":"29","article-title":"Duration modeling for HMM-based speech synthesis","author":"yoshimura","year":"1998","journal-title":"ICSLP'98"},{"key":"ref17","article-title":"Explicit duration modeling in HMM-based speech synthesis using a hybrid hidden Markov model-multilayer perceptron","author":"ogbureke","year":"2012","journal-title":"Workshop on Statistical and Perceptual Audition (SAPA) and Speech Communication with Adaptive Learning (SCALE)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2006.260473"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"2186","DOI":"10.21437\/Interspeech.2010-602","article-title":"Synthesis of fast speech with interpolation of adapted HSMMs and its evaluation by blind and sighted listeners","author":"pucher","year":"2010","journal-title":"Proc Interspeech'10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2097248"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495656"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040791"},{"key":"ref3","first-page":"362","article-title":"A combination of speaker normalization and speech rate normalization for automatic speech recognition","author":"pfau","year":"2000","journal-title":"Proc ICSLP"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2593","DOI":"10.21437\/Interspeech.2011-663","article-title":"About handling boundary uncertainty in a speaking rate dependent modeling approach","author":"jouvet","year":"2011","journal-title":"Proc Interspeech'11"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/89.668817"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2962","DOI":"10.21437\/Interspeech.2010-29","article-title":"A duration modeling technique with incremental speech rate normalization","author":"fujimura","year":"2010","journal-title":"Proc Interspeech'10"},{"key":"ref8","first-page":"145","article-title":"Rate-of-speech modeling for large vocabulary conversational speech recognition","author":"zheng","year":"2002","journal-title":"Proc ASR'00"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318477"},{"key":"ref2","first-page":"483","article-title":"The effect of phrase length and speech rate on prosodic phrasing","author":"jun","year":"2003","journal-title":"Proc ICPhS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828641"},{"key":"ref1","first-page":"449","article-title":"Speaking rate effects on discourse prosody in standard Chinese","author":"li","year":"2008","journal-title":"Proc Speech Prosody"},{"key":"ref20","first-page":"556","article-title":"Duration modeling in voice conversion using artificial neural networks","author":"srikanth","year":"2012","journal-title":"Proc 19th Int Conf Syst Signals Image Process (IWSSIP)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/26.61370"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.3056559"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"995","DOI":"10.21437\/Eurospeech.1997-351","article-title":"Assigning phrase breaks from part-of-speech sequences","author":"black","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref24","author":"breiman","year":"1984","journal-title":"Classification and Regression Tree"},{"key":"ref41","first-page":"14","article-title":"Parsing hierarchical prosodic structure for Mandarin speech synthesis","volume":"1","author":"xu","year":"2006","journal-title":"Proc ICASSP"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.015"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2010-8","article-title":"The NTUT Blizzard Challenge 2010 Entry","author":"liao","year":"2010","journal-title":"The Blizzard Challenge 2010 Workshop"},{"key":"ref26","first-page":"659","article-title":"Corpus phonetic investigations of discourse prosody and I-ligher level information","volume":"9","author":"tseng","year":"2008","journal-title":"Lang Linguist"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.1092"},{"key":"ref25","article-title":"Sinica Treebank 3.0","year":"0"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/6570655\/6817623\/06809996.pdf?arnumber=6809996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,26]],"date-time":"2024-05-26T09:11:30Z","timestamp":1716714690000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/ieeexplore.ieee.org\/document\/6809996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7]]},"references-count":44,"journal-issue":{"issue":"7"},"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/taslp.2014.2321482","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7]]}}}