{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:11:46Z","timestamp":1783523506598,"version":"3.55.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2009,8,1]],"date-time":"2009-08-01T00:00:00Z","timestamp":1249084800000},"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":[[2009,8]]},"DOI":"10.1109\/tasl.2009.2016394","type":"journal-article","created":{"date-parts":[[2009,7,1]],"date-time":"2009-07-01T14:53:03Z","timestamp":1246459983000},"page":"1208-1230","source":"Crossref","is-referenced-by-count":108,"title":["Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis"],"prefix":"10.1109","volume":"17","author":[{"given":"Junichi","family":"Yamagishi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takashi","family":"Nose","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heiga","family":"Zen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keiichi","family":"Tokuda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steve","family":"Renals","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","first-page":"89","article-title":"minimum generation error training for hmm-based speech synthesis","author":"wu","year":"2006","journal-title":"Proc ICASSP-06"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.01.014"},{"key":"ref71","first-page":"1245","article-title":"hmm-based hierarchical unit selection combining kullbackleibler divergence with likelihood criterion","author":"ling","year":"2007","journal-title":"Proc ICASSP-07"},{"key":"ref70","first-page":"2034","article-title":"hmm-based unit selection using frame sized speech segments","author":"ling","year":"2006","journal-title":"Proc Interspeech 2006"},{"key":"ref76","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2008-7","article-title":"the hts-2008 system: yet another evaluation of the speaker-adaptive hmm-based speech synthesis system in the 2008 blizzard challenge","author":"yamagishi","year":"2008","journal-title":"Proc Blizzard Challenge 2008"},{"key":"ref77","article-title":"combining statistical parametric speech synthesis and unit-selection for automatic voice cloning","author":"aylett","year":"2008","journal-title":"Proc LangTech 2008"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(96)00026-X"},{"key":"ref39","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 Fundamentals"},{"key":"ref75","first-page":"823","article-title":"synthesis of regional english using a keyword lexicon","volume":"2","author":"fitt","year":"1999","journal-title":"Proc Eurospeech 1999"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1093\/ietisy\/e90-d.2.533","article-title":"average-voice-based speech synthesis using hsmm-based speaker adaptation and adaptive training","volume":"e90 d","author":"yamagishi","year":"2007","journal-title":"IEICE Trans Inf Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675351"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/89.759034"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/scj.10332"},{"key":"ref36","first-page":"805","article-title":"adaptation of pitch and spectrum for hmm-based speech synthesis using mllr","author":"tamura","year":"2001","journal-title":"Proc ICASSP-01"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref34","first-page":"273","article-title":"speaker adaptation for hmm-based speech synthesis system using mllr","author":"tamura","year":"1998","journal-title":"Proc 3rd ESCA\/COCOSDA Workshop Speech Synth"},{"key":"ref60","article-title":"atrecssatr english speech corpus for speech synthesis","author":"ni","year":"2007","journal-title":"Proc BLZ3-2007 (in Proc SSW6)"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2002.806705"},{"key":"ref61","author":"black","year":"1999","journal-title":"The Festival Speech Synthesis System"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/89.388149"},{"key":"ref28","article-title":"the blizzard challenge 2007","author":"fraser","year":"2007","journal-title":"Proc BLZ3-2007 (in Proc SSW6)"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.3.692"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2006-14","article-title":"the blizzard challenge 2006","author":"bennett","year":"2006","journal-title":"Proc Blizzard Challenge 2006"},{"key":"ref65","author":"zen","year":"2007","journal-title":"Implementing an HSMM-based speech synthesis system using an efficient forward-backward algorithm"},{"key":"ref66","article-title":"statistical analysis of the blizzard challenge 2007 listening test results","author":"clark","year":"2007","journal-title":"Proc BLZ3-2007 (in Proc SSW6)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref67","article-title":"the ustc and iflytek speech synthesis systems for blizzard challenge 2007","author":"ling","year":"2007","journal-title":"Proc BLZ3-2007 (in Proc SSW6)"},{"key":"ref68","article-title":"festival multisyn voices for the 2007 blizzard challenge","author":"richmond","year":"2007","journal-title":"Proc BLZ3-2007 (in Proc SSW6)"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref2","first-page":"2099","article-title":"simultaneous modeling of spectrum, pitch and duration in hmm-based speech synthesis","volume":"j83 d ii","author":"yoshimura","year":"2000","journal-title":"IEICE Trans"},{"key":"ref1","first-page":"2374","article-title":"simultaneous modeling of spectrum, pitch and duration in hmm-based speech synthesis","author":"yoshimura","year":"1999","journal-title":"Proc EuroSpeech-99"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-1.1.325"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref21","first-page":"1332","article-title":"improving arabic hmm based speech synthesis quality","author":"ossama","year":"2006","journal-title":"Proc Interspeech 2006"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2006-6","article-title":"ustc system for blizzard challenge 2006 an improved hmm-based speech synthesis method","author":"ling","year":"2006","journal-title":"Proc Blizzard Challenge 2006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e91-d.6.1764"},{"key":"ref26","first-page":"77","article-title":"the blizzard challenge2005: evaluating corpus-based speech synthesis on common datasets","author":"black","year":"2005","journal-title":"Proc Eurospeech 2005"},{"key":"ref25","article-title":"speaker-independent hmm-based speech synthesis systemhts-2007 system for the blizzard challenge 2007","author":"yamagishi","year":"2007","journal-title":"Proc BLZ3-2007 (in Proc SSW6)"},{"key":"ref50","first-page":"31","author":"kubozono","year":"1995","journal-title":"The handbook of Japanese Linguistics"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367299"},{"key":"ref58","article-title":"hmm-based synthesis of child speech","author":"watts","year":"2008","journal-title":"Proc 1st Workshop Child Comput Interaction (ICMI'08 Post-Conf Workshop)"},{"key":"ref57","first-page":"2266","article-title":"maximum likelihood voice conversion based on gmm with straight mixed excitation","author":"ohtani","year":"2006","journal-title":"Proc Interspeech 2006"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90021-Z"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1250\/ast.21.79"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.502"},{"key":"ref53","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 Series B"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/89.466659"},{"key":"ref10","first-page":"455","article-title":"multi-space probability distribution hmm","volume":"e85 d","author":"tokuda","year":"2002","journal-title":"IEICE Trans Inf Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e89-d.3.1092"},{"key":"ref12","first-page":"143","article-title":"variable duration models for speech","author":"ferguson","year":"1980","journal-title":"Proc Symp Applicat Hidden Markov Models to Text and Speech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168477"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(86)80009-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"key":"ref16","first-page":"13","article-title":"aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system straight","author":"kawahara","year":"2001","journal-title":"Proc 2nd MAVEBA"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/29.1651"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.2001-539","article-title":"mixed excitation for hmm-based speech synthesis","author":"yoshimura","year":"2001","journal-title":"Proc Eurospeech'01"},{"key":"ref19","first-page":"1565","article-title":"incorporation of mixed excitation model and postfilter into hmm-based text-to-speech synthesis","volume":"j87 d ii","author":"yoshimura","year":"2004","journal-title":"IEICE Trans"},{"key":"ref4","author":"tokuda","year":"0","journal-title":"The HMM-Based Speech Synthesis System (HTS) Version 2 0 1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"ref6","first-page":"192","article-title":"an algorithm for speech parameter generation from hmm using dynamic features","volume":"53","author":"tokuda","year":"1997","journal-title":"J Acoust Soc Japan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref8","first-page":"2184","article-title":"hmm-based speech synthesis using dynamic features","volume":"j79 d ii","author":"masuko","year":"1996","journal-title":"IEICE Trans"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541114"},{"key":"ref49","first-page":"227","article-title":"an hmm-based speech synthesis system applied to english","author":"tokuda","year":"2002","journal-title":"Proc IEEE Workshop Speech Synth"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref46","first-page":"2781","article-title":"fixed point analysis of frequency to instantaneous frequency mapping for accurate estimation of f0 and periodicity","author":"kawahara","year":"1999","journal-title":"Proc Eurospeech 1999"},{"key":"ref45","first-page":"2812","article-title":"robust f0 estimation of speech signal using harmonicity measure based on instantaneous frequency","volume":"e87 d","author":"arifianto","year":"2004","journal-title":"IEICE Trans Inf Syst"},{"key":"ref48","year":"1993","journal-title":"ESPS Programs Version 5 0"},{"key":"ref47","first-page":"495","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.05.003"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/11939993_27"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/89.906001"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/89.506933"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/5109758\/05153555.pdf?arnumber=5153555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T15:38:59Z","timestamp":1739201939000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5153555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,8]]},"references-count":77,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2009.2016394","relation":{},"ISSN":["1558-7916"],"issn-type":[{"value":"1558-7916","type":"print"}],"subject":[],"published":{"date-parts":[[2009,8]]}}}