{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T21:10:08Z","timestamp":1746306608971,"version":"3.40.4"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2014,10,1]],"date-time":"2014-10-01T00:00:00Z","timestamp":1412121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001868","name":"National Science Council","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001868","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100007750","name":"National Cheng Kung University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007750","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1109\/taslp.2014.2339738","type":"journal-article","created":{"date-parts":[[2014,7,16]],"date-time":"2014-07-16T18:38:36Z","timestamp":1405535916000},"page":"1558-1570","source":"Crossref","is-referenced-by-count":5,"title":["Polyglot Speech Synthesis Based on Cross-Lingual Frame Selection Using Auditory and Articulatory Features"],"prefix":"10.1109","volume":"22","author":[{"given":"Chia-Ping","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Chin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Hsien","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuan-De","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref38","article-title":"Auditory effects for ASR","author":"lyon","year":"1996","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015708"},{"key":"ref32","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"},{"key":"ref31","article-title":"Speaker adaptation and the evaluation of speaker similarity in the EMIME speech-to-speech translation project","author":"wester","year":"2010","journal-title":"Proc 7th ISCA Speech Synth Workshop"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2187195"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115767"},{"key":"ref36","first-page":"901","article-title":"Segmental tonal modeling for phone set design in Mandarin LVCSR","author":"huang","year":"2004","journal-title":"Proc Int Conf Acoust\/ Speech Signal Process"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-39","article-title":"Phonological knowledge guided HMM state mapping for cross-lingual speaker adaptation","author":"liang","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221460"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.05.003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/89.848223"},{"key":"ref2","article-title":"Two types of code-switching in Taiwan","author":"chen","year":"2004","journal-title":"Proc Sociolinguistics Symp 15 (SS15)"},{"key":"ref1","article-title":"Code-switching between English and mandarin Chinese on postings in the college-affiliated bulletin board system in Taiwan: A functional approach","author":"chen","year":"2007","journal-title":"Proc Lancaster Univ Postgraduate Conf Linguist Lang Teaching"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref22","article-title":"The HMM-based speech synthesis system version 2.0","author":"zen","year":"2007","journal-title":"Proc ISCA SSW6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.21437\/Eurospeech.1999-596","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","author":"yoshimura","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref23","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"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2035029"},{"key":"ref25","first-page":"455","article-title":"Multi-space probability distribution HMM","volume":"e85 d","author":"tokuda","year":"2002","journal-title":"IEICE Trans Inf Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857790"},{"key":"ref11","article-title":"Voice conversion of non-aligned data using unit selection","author":"duxans","year":"2006","journal-title":"Proc TC-STAR Workshop Speech to Speech Transl"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.848881"},{"key":"ref12","article-title":"Voice conversion for unknown speakers","author":"ye","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-581","article-title":"Text-independent cross-language voice conversion","author":"s\ufffdndermann","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198737"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00020-6"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-104","article-title":"A study on detection based automatic speech recognition","author":"ma","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref17","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"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171644"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-595","article-title":"Cross-lingual speaker discrimination using natural and synthetic speech","author":"wester","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"835","DOI":"10.21437\/Eurospeech.1999-216","article-title":"From multilingual to polyglot speech synthesis","author":"traber","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034771"},{"key":"ref7","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":"ref49","first-page":"453","author":"ghitza","year":"1991","journal-title":"Advances in Speech and Signal Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038669"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2112646"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2101594"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/S0095-4470(19)30466-8","article-title":"A joint synchrony\/mean-rate model of auditory speech processing","volume":"16","author":"seneff","year":"1988","journal-title":"J Phonetics"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"journal-title":"Simultaneous modeling of phonetic and prosodic parameters and characteristic conversion for HMM-based text-to-speech systems","year":"2002","author":"yoshimura","key":"ref42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495126"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040791"},{"key":"ref43","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"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/6860345\/06857339.pdf?arnumber=6857339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T20:53:42Z","timestamp":1746305622000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6857339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10]]},"references-count":49,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2014.2339738","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2014,10]]}}}