{"id":"https://openalex.org/W2078749372","doi":"https://doi.org/10.1109/icassp.2013.6639191","title":"Personalized natural speech synthesis based on retrieval of pitch patterns using hierarchical Fujisaki model","display_name":"Personalized natural speech synthesis based on retrieval of pitch patterns using hierarchical Fujisaki model","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2078749372","doi":"https://doi.org/10.1109/icassp.2013.6639191","mag":"2078749372"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-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":true,"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"],"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"],"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/A5089534712","display_name":"Shih-Lun Lin","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":"Shih-Lun Lin","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"],"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":["https://openalex.org/A5112612990"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":null,"apc_paid":null,"fwci":1.9237,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88431329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"21","issue":null,"first_page":"7844","last_page":"7848"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9979000091552734,"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/T12031","display_name":"Speech and dialogue systems","score":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.8114127516746521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7033248543739319},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6895343065261841},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6817963123321533},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6634570956230164},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6418048143386841},{"id":"https://openalex.org/keywords/pitch-contour","display_name":"Pitch contour","score":0.5775237083435059},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.507614254951477},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49554693698883057},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.4805600941181183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4730469584465027},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.47250592708587646},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42895835638046265},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4039362668991089}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114127516746521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7033248543739319},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6895343065261841},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6817963123321533},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6634570956230164},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6418048143386841},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.5775237083435059},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.507614254951477},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49554693698883057},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.4805600941181183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4730469584465027},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.47250592708587646},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42895835638046265},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4039362668991089},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W344150399","https://openalex.org/W1599512239","https://openalex.org/W1908832847","https://openalex.org/W1935622938","https://openalex.org/W2009259304","https://openalex.org/W2039241583","https://openalex.org/W2066186361","https://openalex.org/W2100441082","https://openalex.org/W2108601574","https://openalex.org/W2119174565","https://openalex.org/W2119219448","https://openalex.org/W2123808477","https://openalex.org/W2136603502","https://openalex.org/W2139525902","https://openalex.org/W2161135987","https://openalex.org/W2162295204","https://openalex.org/W2365209858","https://openalex.org/W3142087749","https://openalex.org/W6611766843","https://openalex.org/W6639675702","https://openalex.org/W6674890362","https://openalex.org/W6677611487","https://openalex.org/W6677898495","https://openalex.org/W6678313624","https://openalex.org/W7025091378"],"related_works":["https://openalex.org/W119415662","https://openalex.org/W4391272374","https://openalex.org/W2476379844","https://openalex.org/W4390912566","https://openalex.org/W2743005163","https://openalex.org/W2535215250","https://openalex.org/W2024201202","https://openalex.org/W2370805772","https://openalex.org/W2095212625","https://openalex.org/W3168158558"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"speech":[3,20,80,92],"synthesis":[4,195],"based":[5],"on":[6],"Hidden":[7],"Markov":[8],"Model":[9],"(HMM)":[10],"has":[11],"been":[12],"developed,":[13],"which":[14],"can":[15,189],"synthesize":[16],"stable":[17],"and":[18,23,36,120,136,142,154,182,201],"intelligible":[19],"with":[21,89],"flexibility":[22],"small":[24],"footprint.":[25],"However,":[26],"synthesized":[27,138,155],"prosodic":[28,47,54],"features":[29],"are":[30,49,64,140],"still":[31],"incapable":[32],"to":[33,51,71,94,107,114,144,166],"convey":[34],"personalization":[35],"natural":[37,98],"property.":[38],"Previous":[39],"prosody":[40],"models,":[41],"mainly":[42],"constructed":[43,141,165],"from":[44,77],"the":[45,57,61,78,83,90,109,126,134,137,146,152,174,186,192],"clustered":[46],"features,":[48],"unable":[50],"characterize":[52],"personalized":[53,74,97],"information":[55],"as":[56],"linguistic":[58],"cues":[59],"of":[60,73,82,123,131,148,161,173,199],"input":[62,175],"sentence":[63],"indistinguishable":[65],"for":[66],"all":[67],"speakers.":[68],"An":[69],"approach":[70,188],"retrieval":[72],"pitch":[75,99,111,117,149,162,170],"patterns":[76,150],"real":[79,153],"corpus":[81],"target":[84],"speaker,":[85],"is":[86,105,164],"proposed,":[87],"incorporating":[88],"HMM-based":[91],"synthesizer,":[93],"generate":[95],"a":[96,158],"contour.":[100],"The":[101,128,177],"modified":[102],"Fujisaki":[103],"model":[104,115,160],"adopted":[106],"depict":[108],"hierarchical":[110],"patterns,":[112],"aiming":[113],"local":[116],"contour":[118],"variation":[119],"global":[121],"intonation":[122],"utterances":[124,132],"in":[125,133,197],"corpus.":[127],"codeword":[129],"sequences":[130],"training":[135],"corpora":[139],"used":[143],"obtain":[145,167],"relationship":[147],"between":[151],"speech.":[156],"Finally,":[157],"language":[159],"pattern":[163,171],"an":[168],"optimal":[169],"sequence":[172],"sentence.":[176],"experimental":[178],"results":[179],"using":[180],"subjective":[181],"objective":[183],"evaluations":[184],"demonstrated":[185],"proposed":[187],"substantially":[190],"outperform":[191],"conventional":[193],"statistical":[194],"methods,":[196],"terms":[198],"naturalness":[200],"speaker":[202],"similarity.":[203]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}