{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T18:51:03Z","timestamp":1774551063725,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2017,5,1]],"date-time":"2017-05-01T00:00:00Z","timestamp":1493596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100007225","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["MOST105-2218-E-006-028"],"award-info":[{"award-number":["MOST105-2218-E-006-028"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Headquarters of University Advancement at the National Cheng Kung University"},{"name":"Ministry of Education, Taiwan"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/taslp.2017.2679603","type":"journal-article","created":{"date-parts":[[2017,3,8]],"date-time":"2017-03-08T19:31:00Z","timestamp":1489001460000},"page":"1048-1060","source":"Crossref","is-referenced-by-count":1,"title":["Personalized Spontaneous Speech Synthesis Using a Small-Sized Unsegmented Semispontaneous Speech"],"prefix":"10.1109","volume":"25","author":[{"given":"Yi-Chin","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Hsien","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan-You","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Ge","family":"Shie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jhing-Fa","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2350","article-title":"A study on detection based automatic speech recognition","author":"ma","year":"2006","journal-title":"Proc Interspeech 2006"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198737"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2004.05.008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372916"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1973.9030"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960451"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00020-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0148"},{"key":"ref35","first-page":"79","article-title":"Moving beyond the ‘beads-on-a-string’ model of speech","author":"ostendorf","year":"1999","journal-title":"Proc IEEE ASRU Workshop"},{"key":"ref34","first-page":"1613","article-title":"Distinctive features for use in an automatic speech recognition system","author":"eide","year":"2001","journal-title":"Interspeech 2001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288926"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.09.014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960554"},{"key":"ref2","first-page":"251","article-title":"Speech rate and prosody units: Evidence of interaction from mandarin Chinese","author":"tseng","year":"2004","journal-title":"Proc International Conf on Speech Prosody"},{"key":"ref1","article-title":"Annotation of Mandarin conversational dialogue corpus","author":"tseng","year":"2002"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1109\/TASL.2009.2034771","article-title":"Hierarchical prosody conversion using regression-based clustering for emotional speech synthesis","volume":"18","author":"wu","year":"2010","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2213247"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495140"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828635"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1109\/TASLP.2013.2297018","article-title":"Synthesis of spontaneous speech with syllable contraction using state-based context-dependent voice transformation","volume":"22","author":"wu","year":"2014","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006578"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415109"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref51","first-page":"610","article-title":"Mel-generalized log spectral approximation filter","volume":"j68 a","author":"kobayashi","year":"1985","journal-title":"IEICE Trans Fund"},{"key":"ref56","first-page":"294","article-title":"Fluent personalized speech synthesis with prosodic word-level spontaneous speech generation","author":"huang","year":"2016","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1002\/scj.20354"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660155"},{"key":"ref11","first-page":"173","article-title":"Utilising spontaneous conversational speech in HMM-based speech synthesis","author":"andersson","year":"2010","journal-title":"Proc 7th ISCA Speech Synthesis Workshop"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518596"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2657","DOI":"10.21437\/Interspeech.2011-679","article-title":"On the use of extended context for HMM-based spontaneous conversational speech synthesis","author":"koriyama","year":"2011","journal-title":"Proc Interspeech 2011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/627189"},{"key":"ref14","first-page":"1137","article-title":"Practical implementations of speaker-adaptive training","author":"matsoukas","year":"1997","journal-title":"Proc DARPA Speech Recognit Workshop"},{"key":"ref15","first-page":"1956","article-title":"A training method of average voice model for HMM-based speech synthesis","volume":"e86 a","author":"yamagishi","year":"2003","journal-title":"IEICE Trans Fund"},{"key":"ref16","article-title":"Average-voice-based speech synthesis","author":"yamagishi","year":"2006","journal-title":"Tokyo Institute of Technology"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"853","DOI":"10.21437\/Interspeech.2010-190","article-title":"Conversational spontaneous speech synthesis using average voice model","author":"koriyama","year":"2010","journal-title":"Proc INTERSPEECH 2010"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2037400"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"2943","DOI":"10.21437\/Interspeech.2009-745","article-title":"Mandarin spontaneous narrative planning-prosodic evidence from national Taiwan university lecture corpus","author":"tseng","year":"2009","journal-title":"Proc Interspeech 2009"},{"key":"ref6","first-page":"581","article-title":"Optimising selection of units from speech databases for concatenative synthesis","volume":"1","author":"black","year":"1995","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495140"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941031"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref49","article-title":"A tutorial introduction to the minimum description length principle","author":"gr\u00fcnwald","year":"2004","journal-title":"Advances in Minimum Description Length Theory and Applications"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00075-3"},{"key":"ref46","first-page":"1043","article-title":"Mel-generalized cepstral analysis - a unified approach to speech spectral estimation","author":"tokuda","year":"1994","journal-title":"Proc ICSLP ’94"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.852988"},{"key":"ref48","article-title":"The NICO artificial neural network toolkit","author":"strom","year":"1997"},{"key":"ref47","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178764"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"2390","DOI":"10.21437\/Interspeech.2008-126","article-title":"A penalized logistic regression approach to detection based phone classification","author":"siniscalchi","year":"2008","journal-title":"Proc Interspeech 2008"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2522655"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2461448"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7895265\/07874173.pdf?arnumber=7874173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T17:50:47Z","timestamp":1658771447000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7874173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":56,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2679603","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5]]}}}