{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T05:40:21Z","timestamp":1688967621561},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2014,3,1]],"date-time":"2014-03-01T00:00:00Z","timestamp":1393632000000},"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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1109\/taslp.2013.2297018","type":"journal-article","created":{"date-parts":[[2014,1,31]],"date-time":"2014-01-31T17:49:08Z","timestamp":1391190548000},"page":"585-595","source":"Crossref","is-referenced-by-count":1,"title":["Synthesis of Spontaneous Speech With Syllable Contraction Using State-Based Context-Dependent Voice Transformation"],"prefix":"10.1109","volume":"22","author":[{"family":"Chung-Hsien Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Yi-Chin Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Chung-Han Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Jun-Cheng Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"139","article-title":"Noise robustness in HMM-TTS speaker adaptation","author":"yanagisawa","year":"2013","journal-title":"Proc 5th ISCA Speech Synthesis Workshop"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"528","DOI":"10.21437\/Interspeech.2009-192","article-title":"State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis","author":"wu","year":"2009","journal-title":"Proc Interspeech '09"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1109\/TSA.2005.860839","article-title":"Quality-enhanced voice morphing using maximum likelihood transformations","volume":"14","author":"ye","year":"2006","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"key":"ref31","article-title":"Pitch contour model for chinese text-to-speech using cart and statistical model","author":"dong","year":"2002","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref30","year":"1999","journal-title":"Handbook of the Int Phonetic Association A Guide to the Use of the International Phonetic Alphabet"},{"key":"ref37","first-page":"4633","article-title":"Speaker and style adaptation using average voice model for style control in hmm-based speech synthesis","author":"tachibana","year":"2008","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP '08)"},{"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","first-page":"1","article-title":"Maximum likelihood from incomplete data via the em algorithm","author":"dempster","year":"1977","journal-title":"J R Statist Soc B (Methodological)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2014796"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.408547"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1075\/ijcl.10.1.04tse"},{"key":"ref13","author":"tseng","year":"2002","journal-title":"?Annotation manual of Mandarin conversational dialogue corpus ?"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415109"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828635"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660155"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TASL.2006.876112","article-title":"Voice conversion using duration-embedded bi-HMMs for expressive speech synthesis","volume":"14","author":"wu","year":"2006","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref28","first-page":"i","article-title":"Segmental tonal modeling for phone set design in mandarin lvcsr","volume":"1","author":"huang","year":"2004","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP?04)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889752"},{"key":"ref27","first-page":"1315","article-title":"Speech parameter generation algorithms for hmm-based speech synthesis","volume":"3","author":"tokuda","year":"2000","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP?00)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00075-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.386780"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2016394"},{"key":"ref7","first-page":"1229","article-title":"Statistical parametric speech synthesis","author":"zen","year":"2007","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"581","DOI":"10.21437\/Eurospeech.1995-148","article-title":"Optimising selection of units from speech databases for concatenative synthesis","author":"black","year":"1995","journal-title":"Proc EUROSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288797"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00035-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2007.1079"},{"key":"ref21","first-page":"153","article-title":"Contracted syllables in mandarin: Evidence from spontaneous conversations","volume":"6","author":"tseng","year":"2005","journal-title":"Lang Linguist -Taipei"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034771"},{"key":"ref23","article-title":"Non-uniform unit selection and the similarity metric within bt?s laureate tts system","author":"breen","year":"1998","journal-title":"Proc 3rd ESCA\/COCOSDA Workshop Speech Synthesis"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref25","first-page":"294","article-title":"The hmm-based speech synthesis system (hts) version 2.0","author":"zen","year":"2007","journal-title":"Proc 6th ISCA Workshop Speech Synth"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/6722963\/06698295.pdf?arnumber=6698295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T05:00:46Z","timestamp":1688965246000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6698295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3]]},"references-count":39,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2013.2297018","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,3]]}}}