{"id":"https://openalex.org/W1640528046","doi":"https://doi.org/10.1109/icassp.2003.1198826","title":"A Mandarin intonation prediction model that can output real pitch patterns","display_name":"A Mandarin intonation prediction model that can output real pitch patterns","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W1640528046","doi":"https://doi.org/10.1109/icassp.2003.1198826","mag":"1640528046"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198826","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5026474711","display_name":"Neng\u2010Huang Pan","orcid":"https://orcid.org/0000-0002-4057-7993"},"institutions":[{"id":"https://openalex.org/I162838928","display_name":"National Chung Hsing University","ror":"https://ror.org/05vn3ca78","country_code":"TW","type":"education","lineage":["https://openalex.org/I162838928"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Neng-Huang Pan","raw_affiliation_strings":["Department of Applied Mathematics, National Chung Hsing University, Taichung, Taiwan","[Dept. of Appl. Math., Nat. Chung-Hsing Univ., Taichung, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, National Chung Hsing University, Taichung, Taiwan","institution_ids":["https://openalex.org/I162838928"]},{"raw_affiliation_string":"[Dept. of Appl. Math., Nat. Chung-Hsing Univ., Taichung, Taiwan]","institution_ids":["https://openalex.org/I162838928"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100968486","display_name":"Ming\u2010Shing Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I162838928","display_name":"National Chung Hsing University","ror":"https://ror.org/05vn3ca78","country_code":"TW","type":"education","lineage":["https://openalex.org/I162838928"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Shing Yu","raw_affiliation_strings":["Department of Applied Mathematics, National Chung Hsing University, Taichung, Taiwan","[Dept. of Appl. Math., Nat. Chung-Hsing Univ., Taichung, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, National Chung Hsing University, Taichung, Taiwan","institution_ids":["https://openalex.org/I162838928"]},{"raw_affiliation_string":"[Dept. of Appl. Math., Nat. Chung-Hsing Univ., Taichung, Taiwan]","institution_ids":["https://openalex.org/I162838928"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113834336","display_name":"Ming-Jer Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I162838928","display_name":"National Chung Hsing University","ror":"https://ror.org/05vn3ca78","country_code":"TW","type":"education","lineage":["https://openalex.org/I162838928"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Jer Wu","raw_affiliation_strings":["Department of Applied Mathematics, National Chung Hsing University, Taichung, Taiwan","[Dept. of Appl. Math., Nat. Chung-Hsing Univ., Taichung, Taiwan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, National Chung Hsing University, Taichung, Taiwan","institution_ids":["https://openalex.org/I162838928"]},{"raw_affiliation_string":"[Dept. of Appl. Math., Nat. Chung-Hsing Univ., Taichung, Taiwan]","institution_ids":["https://openalex.org/I162838928"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162838928"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.06858919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9975000023841858,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8163740634918213},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.7970293760299683},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.76981520652771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7152581214904785},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6904229521751404},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5032307505607605},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.48825764656066895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4289492666721344}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8163740634918213},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.7970293760299683},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.76981520652771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152581214904785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6904229521751404},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5032307505607605},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.48825764656066895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4289492666721344},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198826","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W62144051","https://openalex.org/W128984794","https://openalex.org/W1551113872","https://openalex.org/W1594031697","https://openalex.org/W2060491759","https://openalex.org/W2066186361","https://openalex.org/W2066452495","https://openalex.org/W2093085637","https://openalex.org/W2101011209","https://openalex.org/W2102066412","https://openalex.org/W2106564373","https://openalex.org/W2123449470","https://openalex.org/W2146921187","https://openalex.org/W2157768221","https://openalex.org/W2330820318","https://openalex.org/W3085162807","https://openalex.org/W6602579319","https://openalex.org/W6675046034","https://openalex.org/W6675230906"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2535215250","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2024201202","https://openalex.org/W2049083033","https://openalex.org/W290673751"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"proposed":[4],"an":[5],"intonation":[6],"prediction":[7],"model":[8,14,41],"for":[9,79,96],"Mandarin":[10],"TTS":[11],"systems.":[12],"Our":[13],"can":[15,47,125],"output":[16],"real":[17,24],"pitch":[18,25],"patterns":[19],"by":[20],"finding":[21],"a":[22,34],"suitable":[23],"pattern":[26,107],"from":[27],"the":[28,49,52,60,80,97,106,127],"training":[29,117],"corpus.":[30],"This":[31],"method":[32,110],"is":[33],"new":[35],"experiment.":[36],"The":[37,116],"advantages":[38],"of":[39,51,71,88],"our":[40],"are":[42],"as":[43],"follows.":[44],"(1)":[45],"It":[46,55,65,124],"improve":[48],"naturalness":[50],"synthesized":[53],"speech.":[54],"gets":[56],"higher":[57],"scores":[58],"in":[59],"subjective":[61],"listening":[62],"tests.":[63],"(2)":[64],"has":[66],"high":[67],"accuracies.":[68],"Average":[69],"errors":[70,87],"0.425":[72],"ms":[73,76,90,93],"and":[74,82,91,99],"0.457":[75],"were":[77,94],"obtained":[78,95],"inside":[81,98],"outside":[83,100],"tests,":[84,101],"respectively.":[85,102],"Pattern":[86],"0.128":[89],"0.129":[92],"We":[103],"found":[104],"that":[105],"error":[108],"measurement":[109],"complies":[111],"with":[112],"human":[113],"hearing.":[114],"(3)":[115],"corpus":[118],"need":[119],"not":[120],"be":[121],"very":[122],"large.":[123],"relieve":[126],"data":[128],"sparsity":[129],"problem.":[130]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
