{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:13Z","timestamp":1740172453406,"version":"3.37.3"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2016,11,1]],"date-time":"2016-11-01T00:00:00Z","timestamp":1477958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"MOST of Taiwan","award":["MOST 103-2221-E-009-077-MY3","NSC-102-2221-E-305-005-MY3"],"award-info":[{"award-number":["MOST 103-2221-E-009-077-MY3","NSC-102-2221-E-305-005-MY3"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1109\/taslp.2016.2598307","type":"journal-article","created":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T18:11:15Z","timestamp":1470334275000},"page":"2046-2058","source":"Crossref","is-referenced-by-count":6,"title":["Speaker Adaptation of SR-HPM for Speaking Rate-Controlled Mandarin TTS"],"prefix":"10.1109","volume":"24","author":[{"given":"I-Bin","family":"Liao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4997-8774","authenticated-orcid":false,"given":"Chen-Yu","family":"Chiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yih-Ru","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sin-Horng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1117769.1117775"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/89.906001"},{"key":"ref33","first-page":"655","article-title":"A new approach of speaking rate modeling for Mandarin speech prosody","author":"hsieh","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2321482"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638999"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2213247"},{"key":"ref37","first-page":"1","article-title":"Maximum a posteriori linear regression with elliptically symmetric matrix variate priors","volume":"1","author":"chou","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref36","first-page":"105","article-title":"A CART-based hierarchical stochastic model for prosodic phrasing in Chinese","author":"shen","year":"0","journal-title":"Proc 2nd Int Symp Chin Lang Process"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/26.61370"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/scj.10332"},{"key":"ref2","first-page":"1703","article-title":"The IBM trainable speech synthesis system","volume":"5","author":"donovan","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref20","first-page":"1105","article-title":"Towards automatic extraction of prosodic patterns for speech synthesis","author":"dominguez","year":"0","journal-title":"Proceedings of 7th Speech Prosody"},{"key":"ref22","first-page":"367","article-title":"Corpus-based unit selection TTS for Hungarian","author":"f\u00e9k","year":"0","journal-title":"Proc Text Speech Dialogue"},{"key":"ref21","first-page":"1057","article-title":"Tone modeling using stress information for HMM-based Thai speech synthesis","author":"moungsri","year":"0","journal-title":"Proceedings of 7th Speech Prosody"},{"key":"ref24","first-page":"273","article-title":"Speaker adaptation for HMM-based speech synthesis system using MLLR","author":"tamura","year":"0","journal-title":"Proc 3rd ESCA\/COCOSDA Workshop Speech Synthesis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2016394"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"ref25","first-page":"867","article-title":"ToBI: A standard for labeling English prosody","volume":"2","author":"silverman","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.02.005"},{"article-title":"Language model adaptation through shared linear transformations","year":"2014","author":"ma","key":"ref51"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2097248"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"year":"2014","key":"ref40","article-title":"HTS-2.2 source code and demonstrations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178817"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/89.668817"},{"key":"ref14","first-page":"23","article-title":"Higher level organization and discourse prosody","author":"tseng","year":"0","journal-title":"Proc TAL"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1017\/S095267570000066X","article-title":"International structure in Japanese and English","volume":"3","author":"beckman","year":"1986","journal-title":"Phonology"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684835"},{"key":"ref17","first-page":"2149","article-title":"A grammar based approach to style specific phrase prediction","author":"parlikar","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref18","first-page":"558","article-title":"Pause insertion prediction using evaluation model of perceptual pause insertion naturalness","author":"muto","year":"0","journal-title":"Proceedings of 7th Speech Prosody"},{"key":"ref19","first-page":"1032","article-title":"Hierarchical stress generation with Fujisaki model in expressive speech synthesis","author":"li","year":"0","journal-title":"Proceedings of 7th Speech Prosody"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(02)00031-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.2.533"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2089679"},{"key":"ref8","first-page":"455","article-title":"Multi-space probability distribution HMM","volume":"e85 d","author":"tokuda","year":"2002","journal-title":"IEICE Trans Inf Syst"},{"journal-title":"From Text to Speech The MITalk System","year":"1987","author":"allen","key":"ref7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/EUROCON.2013.6625192"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.1092"},{"key":"ref46","first-page":"219","article-title":"Speech-rate-variable HMM-based Japanese TTS system","author":"iwano","year":"0","journal-title":"Proc IEEE Workshop Speech Synthesis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1121\/1.3056559"},{"key":"ref48","first-page":"2847","article-title":"Text-to-speech voice adaptation from sparse training data","volume":"7","author":"kain","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref47","first-page":"530","article-title":"Augmentation of adaptation data","author":"vipperla","year":"0","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref42","first-page":"2625","article-title":"Structure maximum a posteriori speaker adaptation of speaking rate-dependent hierarchical prosody model for Mandarin TTS","author":"liao","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936616"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2006.260473"},{"key":"ref43","first-page":"1873","article-title":"Estimating speaking rate by means of rhythmicity parameters","author":"heinrich","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7542618\/07533472.pdf?arnumber=7533472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:03:09Z","timestamp":1642003389000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7533472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11]]},"references-count":51,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2598307","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2016,11]]}}}