{"id":"https://openalex.org/W2139525902","doi":"https://doi.org/10.1109/tasl.2010.2040791","title":"Exploiting Prosody Hierarchy and Dynamic Features for Pitch Modeling and Generation in HMM-Based Speech Synthesis","display_name":"Exploiting Prosody Hierarchy and Dynamic Features for Pitch Modeling and Generation in HMM-Based Speech Synthesis","publication_year":2010,"publication_date":"2010-04-07","ids":{"openalex":"https://openalex.org/W2139525902","doi":"https://doi.org/10.1109/tasl.2010.2040791","mag":"2139525902"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2040791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2040791","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/A5112618770","display_name":"Chi-Chun Hsia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Chun Hsia","raw_affiliation_strings":["Industrial Technology and Research Institute, Tainan, Taiwan","ICT-Enabled Healthcare Program, Ind. Technol. Res. Inst.-South, Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Technology and Research Institute, Tainan, Taiwan","institution_ids":["https://openalex.org/I4210148468"]},{"raw_affiliation_string":"ICT-Enabled Healthcare Program, Ind. Technol. Res. Inst.-South, Tainan, Taiwan","institution_ids":[]}]},{"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/A5102155569","display_name":"Jung-Yun Wu","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":"Jung-Yun 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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0599,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96214945,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":"8","first_page":"1994","last_page":"2003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8469913005828857},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7970290780067444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7286200523376465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7052167057991028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5995987057685852},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49288177490234375},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.484106183052063},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4638853669166565},{"id":"https://openalex.org/keywords/pitch-contour","display_name":"Pitch contour","score":0.456596702337265},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43370410799980164},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4274671971797943}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8469913005828857},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7970290780067444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7286200523376465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052167057991028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5995987057685852},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49288177490234375},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.484106183052063},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4638853669166565},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.456596702337265},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43370410799980164},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4274671971797943},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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.2010.2040791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2040791","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":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324663","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W11234093","https://openalex.org/W18774747","https://openalex.org/W113106864","https://openalex.org/W130954704","https://openalex.org/W162654330","https://openalex.org/W1502822555","https://openalex.org/W1572730534","https://openalex.org/W1586553359","https://openalex.org/W1600722501","https://openalex.org/W1926768285","https://openalex.org/W1963627370","https://openalex.org/W1994514815","https://openalex.org/W2009259304","https://openalex.org/W2034277951","https://openalex.org/W2049633694","https://openalex.org/W2049686551","https://openalex.org/W2060491759","https://openalex.org/W2066186361","https://openalex.org/W2093450784","https://openalex.org/W2100441082","https://openalex.org/W2102066412","https://openalex.org/W2106132814","https://openalex.org/W2106421426","https://openalex.org/W2106564373","https://openalex.org/W2110332474","https://openalex.org/W2111194146","https://openalex.org/W2117418893","https://openalex.org/W2126897421","https://openalex.org/W2137718131","https://openalex.org/W2146921187","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2167072947","https://openalex.org/W2254292464","https://openalex.org/W2365209858","https://openalex.org/W2999905431","https://openalex.org/W4205394117","https://openalex.org/W6600452588","https://openalex.org/W6600762380","https://openalex.org/W6606697926","https://openalex.org/W6635290542","https://openalex.org/W6674890362","https://openalex.org/W6676358011","https://openalex.org/W6691808304","https://openalex.org/W7025091378"],"related_works":["https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,30,35,47,80],"method":[4],"for":[5,136,166],"modeling":[6],"and":[7,22,50,89,101,150,159],"generating":[8,137],"pitch":[9,24,77,138,168],"in":[10,69,146],"hidden":[11],"Markov":[12],"model":[13,128],"(HMM)-based":[14],"Mandarin":[15],"speech":[16,81],"synthesis":[17],"by":[18,34,58],"exploiting":[19],"prosody":[20,36,127],"hierarchy":[21],"dynamic":[23],"features.":[25],"The":[26,54,76,170],"prosodic":[27,44,74,93,98,108],"structure":[28],"of":[29,63,72,79,176],"sentence":[31,82],"is":[32,39,56,83,129,144],"represented":[33],"hierarchy,":[37],"which":[38],"constructed":[40,130],"from":[41],"the":[42,60,67,70,73,86,92,106,119,160,173,177],"predicted":[43,107],"breaks":[45],"using":[46,85,131],"supervised":[48],"classification":[49],"regression":[51],"tree":[52],"(S-CART).":[53],"S-CART":[55],"trained":[57],"maximizing":[59],"proportional":[61],"reduction":[62],"entropy":[64],"to":[65,117,163],"minimize":[66],"errors":[68],"prediction":[71],"breaks.":[75],"contour":[78],"estimated":[84,116],"STRAIGHT":[87],"algorithm":[88],"decomposed":[90],"into":[91],"features":[94,111],"(static":[95],"features)":[96],"at":[97,112],"word,":[99],"syllable,":[100],"frame":[102],"layers,":[103],"based":[104],"on":[105],"structure.":[109],"Dynamic":[110],"each":[113],"layer":[114],"are":[115],"preserve":[118],"temporal":[120],"correlation":[121],"between":[122],"adjacent":[123],"units.":[124],"A":[125],"hierarchical":[126],"an":[132],"unsupervised":[133],"CART":[134],"(U-CART)":[135],"contour.":[139],"Minimum":[140],"description":[141],"length":[142],"(MDL)":[143],"adopted":[145],"U-CART":[147],"training.":[148],"Objective":[149],"subjective":[151],"evaluations":[152],"with":[153],"statistical":[154],"hypothesis":[155],"testing":[156],"were":[157],"conducted,":[158],"results":[161,165],"compared":[162],"corresponding":[164],"HMM-based":[167],"modeling.":[169],"comparison":[171],"confirms":[172],"improved":[174],"performance":[175],"proposed":[178],"method.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}