{"id":"https://openalex.org/W1553372752","doi":"https://doi.org/10.1109/icassp.2003.1198887","title":"Speech recognition using voice-characteristic-dependent acoustic models","display_name":"Speech recognition using voice-characteristic-dependent acoustic models","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W1553372752","doi":"https://doi.org/10.1109/icassp.2003.1198887","mag":"1553372752"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198887","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/A5101511707","display_name":"Hiroyuki Suzuki","orcid":"https://orcid.org/0009-0005-6640-2760"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Suzuki","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","Dept. of Computer Science, Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Dept. of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Zen","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","Dept. of Computer Science, Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Dept. of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Nankaku","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","Dept. of Computer Science, Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Dept. of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108524583","display_name":"Chiyomi Miyajima","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"C. Miyajima","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","Dept. of Computer Science, Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Dept. of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Tokuda","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","Dept. of Computer Science, Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Dept. of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059137996","display_name":"Tadashi Kitamura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Kitamura","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","Dept. of Computer Science, Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Dept. of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"740"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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/speech-recognition","display_name":"Speech recognition","score":0.7302106022834778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6890817284584045},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4603758454322815},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41466251015663147},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3766097128391266},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3488067388534546},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05646252632141113}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7302106022834778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6890817284584045},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4603758454322815},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41466251015663147},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3766097128391266},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3488067388534546},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05646252632141113}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198887","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":[{"id":"https://metadata.un.org/sdg/5","score":0.6100000143051147,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1836266387","https://openalex.org/W1963627370","https://openalex.org/W1971081490","https://openalex.org/W2050597349","https://openalex.org/W2093450784","https://openalex.org/W2110765229","https://openalex.org/W2116952749","https://openalex.org/W2122272452","https://openalex.org/W4236088841"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2640905660","https://openalex.org/W2131711534"],"abstract_inverted_index":{"This":[0,31,107],"paper":[1,108],"proposes":[2,109],"a":[3,57,110,131],"speech":[4,28,74,98,114,125,133],"recognition":[5,29,75,102,134,143],"technique":[6,60],"based":[7],"on":[8],"acoustic":[9,16,49,54,71,105],"models":[10],"considering":[11],"voice":[12,37,66,94,120],"characteristic":[13],"variations.":[14],"Context-dependent":[15],"models,":[17,55,78],"which":[18],"are":[19,23,45,99,126],"typically":[20],"triphone":[21,77],"HMM,":[22],"often":[24],"used":[25],"in":[26,48,89,91,101,145],"continuous":[27],"systems.":[30],"work":[32],"hypothesizes":[33],"that":[34,39,137],"the":[35,79,86,93,119,123,138],"speaker":[36,65],"characteristics":[38,67,95,121],"humans":[40],"can":[41],"perceive":[42],"by":[43],"listening":[44],"also":[46,62],"factors":[47],"variation":[50],"for":[51],"construction":[52],"of":[53,96,112,122,130],"and":[56],"tree-based":[58],"clustering":[59],"is":[61,83],"applied":[63],"to":[64,68,147],"construct":[69],"voice-characteristic-dependent":[70,104],"models.":[72,106],"In":[73],"using":[76,103],"neighboring":[80],"phonetic":[81],"context":[82],"given":[84],"from":[85],"linguistic-phonetic":[87],"knowledge":[88],"advance;":[90],"contrast,":[92],"input":[97,124],"unknown":[100],"method":[111,140],"recognizing":[113],"even":[115],"under":[116],"conditions":[117],"where":[118],"unknown.":[127],"The":[128],"result":[129],"gender-dependent":[132],"experiment":[135],"shows":[136],"proposed":[139],"achieves":[141],"higher":[142],"performance":[144],"comparison":[146],"conventional":[148],"methods.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
