{"id":"https://openalex.org/W2039241583","doi":"https://doi.org/10.1109/tasl.2012.2213247","title":"Personalized Spectral and Prosody Conversion Using Frame-Based Codeword Distribution and Adaptive CRF","display_name":"Personalized Spectral and Prosody Conversion Using Frame-Based Codeword Distribution and Adaptive CRF","publication_year":2012,"publication_date":"2012-08-15","ids":{"openalex":"https://openalex.org/W2039241583","doi":"https://doi.org/10.1109/tasl.2012.2213247","mag":"2039241583"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2213247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2213247","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112612990","display_name":"Yi\u2010Chin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Chin Huang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011691071","display_name":"Yu-Ting Chao","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ting Chao","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7497,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95850895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"21","issue":"1","first_page":"51","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9828000068664551,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7494050860404968},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6879889369010925},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6125210523605347},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6101665496826172},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5566231608390808},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49057358503341675},{"id":"https://openalex.org/keywords/code-word","display_name":"Code word","score":0.470132440328598},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.4548916518688202},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4363557994365692},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.42807719111442566},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4279625713825226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41877514123916626},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37807488441467285},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20093977451324463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16045835614204407},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.1184844970703125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494050860404968},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6879889369010925},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6125210523605347},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6101665496826172},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5566231608390808},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49057358503341675},{"id":"https://openalex.org/C153207627","wikidata":"https://www.wikidata.org/wiki/Q863873","display_name":"Code word","level":3,"score":0.470132440328598},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.4548916518688202},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4363557994365692},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.42807719111442566},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4279625713825226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41877514123916626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37807488441467285},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20093977451324463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16045835614204407},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.1184844970703125},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2012.2213247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2213247","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W18774747","https://openalex.org/W37701520","https://openalex.org/W98894605","https://openalex.org/W130954704","https://openalex.org/W1518567289","https://openalex.org/W1543281296","https://openalex.org/W1926768285","https://openalex.org/W2009259304","https://openalex.org/W2015060114","https://openalex.org/W2049633694","https://openalex.org/W2051434435","https://openalex.org/W2060491759","https://openalex.org/W2100441082","https://openalex.org/W2102066412","https://openalex.org/W2106132814","https://openalex.org/W2108601574","https://openalex.org/W2110332474","https://openalex.org/W2111550316","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2139525902","https://openalex.org/W2147880316","https://openalex.org/W2149062204","https://openalex.org/W2151262064","https://openalex.org/W2153914468","https://openalex.org/W2156142001","https://openalex.org/W2156690084","https://openalex.org/W2157412983","https://openalex.org/W2159150199","https://openalex.org/W2161135987","https://openalex.org/W2162295204","https://openalex.org/W2254292464","https://openalex.org/W2365209858","https://openalex.org/W2400063444","https://openalex.org/W4376534080","https://openalex.org/W6600762380","https://openalex.org/W6674890362","https://openalex.org/W6676110152","https://openalex.org/W6682082992","https://openalex.org/W6683730234","https://openalex.org/W6691808304","https://openalex.org/W7025091378"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3203313352","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W1965141925","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W2587342322"],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3,17,33,43,147],"voice":[4,30,56,97,188],"conversion-based":[5],"approach":[6],"to":[7,143,162,173,213],"personalized":[8,164],"text-to-speech":[9],"(TTS)":[10],"synthesis.":[11],"The":[12,181],"conversion":[13,57,65,70,189],"functions,":[14],"trained":[15],"using":[16,75,155],"small":[18],"parallel":[19,49,115],"corpus":[20,50,116],"with":[21,60],"source":[22,86,101],"and":[23,87,102,168,195,205],"target":[24,34,89,103],"speech":[25,203],"data,":[26],"can":[27,92,129,200],"impose":[28],"the":[29,48,63,80,85,88,96,100,108,114,134,144,175,178,186,202,209,216,220,224],"characteristics":[31],"of":[32,45,84,99,113,177,208,223],"speaker":[35,206],"on":[36,192],"an":[37,122,156],"existing":[38],"synthesizer.":[39],"Frame":[40],"alignment":[41,74,128,194],"between":[42,79],"pair":[44],"sentences":[46],"in":[47,121],"is":[51],"generally":[52],"used":[53],"for":[54],"training":[55],"functions.":[58],"However,":[59],"incorrect":[61],"alignment,":[62],"resultant":[64],"functions":[66],"may":[67],"generate":[68,163],"unacceptable":[69],"results.":[71],"Traditional":[72],"frame":[73,127],"minimal":[76],"spectral":[77,145],"distance":[78,139],"frame-based":[81],"feature":[82,111],"vectors":[83,112],"phone":[90],"sequences":[91],"be":[93,130],"imprecise":[94],"because":[95],"properties":[98],"phones":[104],"inherently":[105],"differ.":[106],"In":[107,141],"proposed":[109,179,187,225],"method,":[110,190],"are":[117],"transformed":[118],"into":[119,138],"codewords":[120],"eigenspace.":[123],"A":[124],"more":[125],"precise":[126],"obtained":[131],"by":[132],"integrating":[133],"codeword":[135],"occurrence":[136],"distributions":[137],"estimation.":[140],"addition":[142],"property,":[146],"prosodic":[148,165,196],"word/phrase":[149],"boundary":[150,198],"prediction":[151],"model":[152],"was":[153],"constructed":[154],"adaptive":[157],"conditional":[158],"random":[159],"field":[160],"(CRF)":[161],"information.":[166],"Objective":[167],"subjective":[169],"tests":[170],"were":[171],"conducted":[172],"evaluate":[174],"performance":[176,222],"approach.":[180],"experimental":[182],"results":[183,218],"showed":[184],"that":[185],"based":[191],"distribution-based":[193],"word":[197],"detection,":[199],"improve":[201],"quality":[204],"similarity":[207],"converted":[210],"speech.":[211],"Compared":[212],"other":[214],"methods,":[215],"evaluation":[217],"verified":[219],"improved":[221],"method.":[226]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}