{"id":"https://openalex.org/W2131902459","doi":"https://doi.org/10.1109/icme.2003.1221387","title":"Temporal decomposition: a promising approach to VQ-based speaker identification","display_name":"Temporal decomposition: a promising approach to VQ-based speaker identification","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2131902459","doi":"https://doi.org/10.1109/icme.2003.1221387","mag":"2131902459"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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/A5006647053","display_name":"Phu Chien Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Phu Chien Nguyen","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan","Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Akagi","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan","Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101646487","display_name":"Tu Bao Ho","orcid":"https://orcid.org/0000-0001-5951-643X"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tu Bao Ho","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan","Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006647053"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.9137,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81525853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"III","last_page":"617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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":0.991599977016449,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.76938796043396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7558982372283936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7352681159973145},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6723405122756958},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5700337886810303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5675024390220642},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5373209118843079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49858951568603516},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4926045536994934},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4876004755496979},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4793418347835541},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4504394233226776},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.43473875522613525},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.42910319566726685},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.42271244525909424},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41531264781951904}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.76938796043396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7558982372283936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7352681159973145},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6723405122756958},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5700337886810303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5675024390220642},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5373209118843079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49858951568603516},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4926045536994934},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4876004755496979},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4793418347835541},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4504394233226776},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.43473875522613525},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42910319566726685},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.42271244525909424},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41531264781951904},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2003.1221387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W92500784","https://openalex.org/W1945356021","https://openalex.org/W1980148047","https://openalex.org/W2007266108","https://openalex.org/W2050693797","https://openalex.org/W2052605041","https://openalex.org/W2114548807","https://openalex.org/W2116565421","https://openalex.org/W2122410461","https://openalex.org/W2134383396","https://openalex.org/W2138252835","https://openalex.org/W2148787026","https://openalex.org/W2158358098","https://openalex.org/W2165880886","https://openalex.org/W6603753910"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W1963976507","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W4318225096","https://openalex.org/W106647055"],"abstract_inverted_index":{"In":[0],"this":[1,92],"paper,":[2],"a":[3,127],"new":[4,24,35],"set":[5,25],"of":[6,18,26,55,73,98,126],"features":[7,27,36],"is":[8,28],"proposed":[9],"that":[10,72,114],"has":[11,65],"been":[12,38,66],"found":[13],"to":[14,30,71,104],"improve":[15],"the":[16,47,74,82,115,124],"performance":[17],"automatic":[19],"speaker":[20],"identification":[21,83],"systems.":[22],"The":[23,34,53],"referred":[29],"as":[31],"\"even":[32],"targets\".":[33],"have":[37],"derived":[39],"from":[40],"line":[41],"spectral":[42],"frequency":[43],"(LSF)":[44],"parameters":[45],"using":[46],"so-called":[48],"\"temporal":[49],"decomposition\"":[50],"(TD)":[51],"technique.":[52],"number":[54],"feature":[56],"vectors":[57],"required":[58],"for":[59],"both":[60],"training":[61],"and":[62,109],"testing":[63],"phases":[64],"reduced":[67],"by":[68],"one-fifth":[69],"compared":[70],"traditional":[75],"mel-frequency":[76],"cepstrum":[77],"coefficients":[78],"(MFCC)":[79],"features,":[80],"while":[81],"results":[84],"obtained":[85],"are":[86],"comparable":[87],"or":[88],"even":[89],"better.":[90],"Also,":[91],"work":[93],"introduces":[94],"one":[95],"more":[96],"application":[97],"TD":[99,119],"(speaker":[100],"recognition)":[101],"in":[102,118],"addition":[103],"speech":[105,107,110],"coding,":[106],"segmentation,":[108],"recognition.":[111],"It":[112],"shows":[113],"event":[116],"targets":[117],"can":[120],"convey":[121],"information":[122],"about":[123],"identity":[125],"speaker.":[128]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
