{"id":"https://openalex.org/W2009049512","doi":"https://doi.org/10.1016/s0167-6393(00)00089-3","title":"Speaker clustering for speech recognition using vocal tract parameters","display_name":"Speaker clustering for speech recognition using vocal tract parameters","publication_year":2002,"publication_date":"2002-03-01","ids":{"openalex":"https://openalex.org/W2009049512","doi":"https://doi.org/10.1016/s0167-6393(00)00089-3","mag":"2009049512"},"language":"en","primary_location":{"id":"doi:10.1016/s0167-6393(00)00089-3","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0167-6393(00)00089-3","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","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/A5013227099","display_name":"Masaki Naito","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masaki Naito","raw_affiliation_strings":["ATR Interpreting Telecommunications Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan","ATR Interpreting Telecommunications Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Interpreting Telecommunications Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"ATR Interpreting Telecommunications Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan#TAB#","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Ont., Canada N2L 3G1","[Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ONT, Canada]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Ont., Canada N2L 3G1","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"[Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ONT, Canada]","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045034259","display_name":"Yoshinori Sagisaka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshinori Sagisaka","raw_affiliation_strings":["ATR Interpreting Telecommunications Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan","ATR Interpreting Telecommunications Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Interpreting Telecommunications Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"ATR Interpreting Telecommunications Research Laboratory, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan#TAB#","institution_ids":["https://openalex.org/I4210104143"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013227099"],"corresponding_institution_ids":["https://openalex.org/I4210104143"],"apc_list":{"value":2610,"currency":"USD","value_usd":2610},"apc_paid":null,"fwci":2.2106,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89472583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"36","issue":"3-4","first_page":"305","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9961000084877014,"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/vocal-tract","display_name":"Vocal tract","score":0.8561693429946899},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8385624289512634},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7683519721031189},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7097045183181763},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7065067291259766},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6976447105407715},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6855663657188416},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5765720009803772},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4831904470920563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3704564571380615},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.12347599864006042}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8561693429946899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8385624289512634},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7683519721031189},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7097045183181763},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7065067291259766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6976447105407715},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6855663657188416},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5765720009803772},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4831904470920563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3704564571380615},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.12347599864006042}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/s0167-6393(00)00089-3","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0167-6393(00)00089-3","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W37344644","https://openalex.org/W357399442","https://openalex.org/W1511242468","https://openalex.org/W1585177184","https://openalex.org/W2068970468","https://openalex.org/W2116708935","https://openalex.org/W2141934504"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2894697037","https://openalex.org/W2045900265","https://openalex.org/W2131046383"],"abstract_inverted_index":null,"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}