{"id":"https://openalex.org/W2537421476","doi":"https://doi.org/10.1109/icsda.2014.7051427","title":"Hierarchical prosody modeling of English speech and its application to TTS","display_name":"Hierarchical prosody modeling of English speech and its application to TTS","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2537421476","doi":"https://doi.org/10.1109/icsda.2014.7051427","mag":"2537421476"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2014.7051427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2014.7051427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (COCOSDA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5112224227","display_name":"Chung-Yao Tsai","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Yao Tsai","raw_affiliation_strings":["National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071305336","display_name":"Chin-Kuan Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chin-Kuan Kuo","raw_affiliation_strings":["National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071941088","display_name":"Yih\u2010Ru Wang","orcid":"https://orcid.org/0000-0002-4483-1418"},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yih-Ru Wang","raw_affiliation_strings":["Chunghwa Telecom Laboratories, Yangmei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chunghwa Telecom Laboratories, Yangmei, Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015529786","display_name":"Sin\u2010Horng Chen","orcid":"https://orcid.org/0000-0002-9820-2318"},"institutions":[{"id":"https://openalex.org/I99613584","display_name":"National Taipei University","ror":"https://ror.org/03e29r284","country_code":"TW","type":"education","lineage":["https://openalex.org/I99613584"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sin-Horng Chen","raw_affiliation_strings":["National Taipei University, New Taipei City, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taipei University, New Taipei City, Taiwan","institution_ids":["https://openalex.org/I99613584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081460934","display_name":"I-Bin Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Bin Liao","raw_affiliation_strings":["National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101446417","display_name":"Chen-Yu Chiang","orcid":"https://orcid.org/0000-0003-4997-8774"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen-Yu Chiang","raw_affiliation_strings":["National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4135,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63091483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"20","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9794999957084656,"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":0.9746000170707703,"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":0.859822690486908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7422521114349365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6015012264251709},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5112240314483643},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5025312900543213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3827667236328125}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.859822690486908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422521114349365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6015012264251709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5112240314483643},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5025312900543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3827667236328125}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2014.7051427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2014.7051427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W857326229","https://openalex.org/W1599910466","https://openalex.org/W1983715885","https://openalex.org/W1985192489","https://openalex.org/W2004590799","https://openalex.org/W2093414802","https://openalex.org/W2110332474","https://openalex.org/W2146921187","https://openalex.org/W3146055280","https://openalex.org/W4301074325","https://openalex.org/W6636073158"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925","https://openalex.org/W2587342322"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,30,66,88,95,102,129],"hierarchical":[4],"prosody":[5,58,67],"modeling":[6,70],"approach":[7,21],"for":[8,24,128],"English":[9],"speech":[10,44,90,140],"is":[11,14],"proposed.":[12],"It":[13,27,63],"an":[15],"extended":[16],"version":[17],"of":[18,39,42,48,60,82,101,112],"the":[19,43,49,56,61,74,79,109,113,121,138],"HPM":[20],"proposed":[22],"previously":[23],"Mandarin":[25],"speech.":[26,62],"first":[28],"designs":[29],"syllable-based,":[31],"statistical":[32],"prosodic":[33,53,80,126],"model":[34,75,114,123],"to":[35,72,124],"describe":[36],"various":[37],"relationships":[38],"prosodic-acoustic":[40],"features":[41,47],"signal,":[45],"linguistic":[46],"associated":[50],"text,":[51],"and":[52,69,77],"tags":[54,81],"representing":[55],"underlining":[57],"structure":[59],"then":[64,119],"employs":[65],"labeling":[68],"algorithm":[71],"estimate":[73],"parameters":[76,111],"label":[78],"all":[83,116],"training":[84],"utterances":[85,100],"simultaneously":[86],"from":[87],"prosody-unlabeled":[89],"corpus.":[91],"Experimental":[92],"results":[93],"on":[94],"corpus":[96],"containing":[97],"many":[98],"paragraphic":[99],"female":[103],"English-majored":[104],"Chinese":[105],"speaker":[106],"show":[107],"that":[108,137],"inferred":[110],"are":[115],"meaningful.":[117],"We":[118],"use":[120],"trained":[122],"generate":[125],"information":[127],"TTS":[130],"system.":[131],"An":[132],"informal":[133],"listening":[134],"test":[135],"shows":[136],"synthetic":[139],"sounds":[141],"quite":[142],"natural.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
