{"id":"https://openalex.org/W2761478804","doi":"https://doi.org/10.1109/taslp.2017.2762432","title":"Cross-Dialect Adaptation Framework for Constructing Prosodic Models for Chinese Dialect Text-to-Speech Systems","display_name":"Cross-Dialect Adaptation Framework for Constructing Prosodic Models for Chinese Dialect Text-to-Speech Systems","publication_year":2017,"publication_date":"2017-10-12","ids":{"openalex":"https://openalex.org/W2761478804","doi":"https://doi.org/10.1109/taslp.2017.2762432","mag":"2761478804"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2762432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2762432","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM 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/A5101446417","display_name":"Chen-Yu Chiang","orcid":"https://orcid.org/0000-0003-4997-8774"},"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":true,"raw_author_name":"Chen-Yu Chiang","raw_affiliation_strings":["Department of Communication Engineering, National Taipei University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communication Engineering, National Taipei University, Taipei, Taiwan","institution_ids":["https://openalex.org/I99613584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101446417"],"corresponding_institution_ids":["https://openalex.org/I99613584"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.6844,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.7986121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"1","first_page":"108","last_page":"121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9959999918937683,"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/T11309","display_name":"Music and Audio Processing","score":0.9908999800682068,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8912073373794556},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7088133096694946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6818982362747192},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48829174041748047},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4690794348716736},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.43938884139060974},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.43242523074150085},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4140566289424896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4125105142593384},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1720971167087555},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09862524271011353}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8912073373794556},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7088133096694946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818982362747192},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48829174041748047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4690794348716736},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.43938884139060974},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43242523074150085},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4140566289424896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4125105142593384},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1720971167087555},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09862524271011353},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2762432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2762432","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G5052406846","display_name":"Prosody Modeling for English and Its Applications","funder_award_id":"NSC102-2221-E305-005-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"},{"id":"https://openalex.org/G6358536910","display_name":"Development of Customer-Configurable Text-To-Speech, Voice Conversion, and Speech to Text Systems","funder_award_id":"MOST105-2622-E305-003-CC3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W39033210","https://openalex.org/W857326229","https://openalex.org/W1481373816","https://openalex.org/W1557790732","https://openalex.org/W1652788343","https://openalex.org/W1965555277","https://openalex.org/W1983715885","https://openalex.org/W1997732994","https://openalex.org/W2001383325","https://openalex.org/W2035480460","https://openalex.org/W2076151915","https://openalex.org/W2102355353","https://openalex.org/W2134230850","https://openalex.org/W2134541711","https://openalex.org/W2146921187","https://openalex.org/W2148367456","https://openalex.org/W2149175990","https://openalex.org/W2152910988","https://openalex.org/W2160232583","https://openalex.org/W2163775454","https://openalex.org/W2400778424","https://openalex.org/W2504361220","https://openalex.org/W2537756377","https://openalex.org/W2596871810","https://openalex.org/W3085162807","https://openalex.org/W4301074325","https://openalex.org/W6601583134","https://openalex.org/W6623558092","https://openalex.org/W6633198447","https://openalex.org/W6679989464","https://openalex.org/W6680151211","https://openalex.org/W6682164309","https://openalex.org/W6682605591","https://openalex.org/W6683353402"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"This":[0,119],"paper":[1],"presents":[2],"an":[3,26,101],"efficient":[4],"cross-dialect":[5,205],"adaptation":[6,79,102,206],"framework":[7,38,207],"for":[8,12],"constructing":[9],"prosodic":[10,21,32,56,86,109,139,173,182],"models":[11,22,183],"Chinese":[13,49,161],"dialect":[14,20,82,135,178],"text-to-speech":[15],"systems.":[16],"In":[17],"this":[18,64],"framework,":[19],"are":[23,61],"adapted":[24],"from":[25,192],"existing":[27],"Mandarin":[28,46],"speaking":[29,83,116,136,179,189],"rate-dependent":[30,84,137,180],"hierarchical":[31,85,138,181],"model.":[33,87],"The":[34,88,149],"rationale":[35],"of":[36,53,72,80,100,151],"the":[37,42,70,76,81,93,98,125,134,152,172,177,203],"is":[39,121,208],"based":[40],"on":[41,159],"cross-dialectal":[43,73],"similarities":[44,74],"between":[45],"and":[47,55,78,108,164,167,210],"other":[48,89],"dialects":[50],"in":[51,63,75,187],"terms":[52],"syntactic":[54],"structures.":[57],"Two":[58],"main":[59],"problems":[60],"addressed":[62],"study:":[65],"One":[66],"problem":[67,90,120],"pertains":[68,91],"to":[69,92,145,194],"use":[71],"design":[77],"data":[94],"sparseness":[95],"caused":[96],"by":[97,123,157,176],"insufficiency":[99],"corpus":[103],"covering":[104],"essential":[105],"linguistic":[106],"contexts":[107],"events":[110],"as":[111,113],"well":[112],"a":[114,128],"wide":[115],"rate":[117],"range.":[118],"solved":[122],"employing":[124],"structural":[126],"maximum":[127],"posteriori":[129],"method":[130],"that":[131,171,202],"hierarchically":[132],"organizes":[133],"model":[140],"parameters":[141],"into":[142],"decision":[143],"trees":[144],"facilitate":[146],"parameter":[147],"estimations.":[148],"effectiveness":[150],"proposed":[153,204],"approach":[154],"was":[155],"evaluated":[156],"experiments":[158],"two":[160],"dialects:":[162],"Min":[163],"Hakka.":[165],"Objective":[166],"subjective":[168],"evaluations":[169],"demonstrated":[170],"features":[174],"generated":[175],"were":[184],"quite":[185],"natural":[186],"various":[188],"rates":[190],"ranging":[191],"3.3":[193],"6.7":[195],"syllables":[196],"per":[197],"second.":[198],"These":[199],"results":[200],"confirm":[201],"effective":[209],"promising.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}