{"id":"https://openalex.org/W66706303","doi":"https://doi.org/10.21437/interspeech.2006-180","title":"Speaker identification under noisy environments by using harmonic structure extraction and reliable frame weighting","display_name":"Speaker identification under noisy environments by using harmonic structure extraction and reliable frame weighting","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W66706303","doi":"https://doi.org/10.21437/interspeech.2006-180","mag":"66706303"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-180","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5110207817","display_name":"Hiromasa Fujihara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiromasa Fujihara","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108346747","display_name":"Tetsuro Kitahara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuro Kitahara","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Techno"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Techno","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"institutions":[{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5110207817"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"],"apc_list":null,"apc_paid":null,"fwci":0.6361,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.63761297,"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":"paper 1525","last_page":"Wed1A1O.2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":0.9993000030517578,"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":0.9991000294685364,"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/robustness","display_name":"Robustness (evolution)","score":0.8116123080253601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7688311338424683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6693339943885803},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.651336669921875},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6340765357017517},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.5088543891906738},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.506766140460968},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.502791166305542},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.467529296875},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4621696174144745},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4180895984172821},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4066162109375},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3462064266204834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3424534201622009},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2357473075389862},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06780433654785156}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8116123080253601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7688311338424683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6693339943885803},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.651336669921875},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6340765357017517},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.5088543891906738},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.506766140460968},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.502791166305542},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.467529296875},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4621696174144745},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4180895984172821},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4066162109375},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3462064266204834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3424534201622009},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2357473075389862},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06780433654785156},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-180","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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":8,"referenced_works":["https://openalex.org/W178884067","https://openalex.org/W2005522781","https://openalex.org/W2023800933","https://openalex.org/W2045036776","https://openalex.org/W2050693797","https://openalex.org/W2118938505","https://openalex.org/W2128653836","https://openalex.org/W2138084857"],"related_works":["https://openalex.org/W2128073728","https://openalex.org/W4234190324","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W4396668120","https://openalex.org/W2126085626","https://openalex.org/W2129048388","https://openalex.org/W2129090883","https://openalex.org/W2972577568"],"abstract_inverted_index":{"We":[0],"present":[1],"methods":[2],"for":[3,109,155],"automatic":[4],"speaker":[5,15,38,115,163],"identification":[6],"in":[7],"noisy":[8],"environments.":[9],"To":[10],"improve":[11],"noise":[12,48,143,165],"robustness":[13],"of":[14,39,58,91,141,149],"identification,":[16,164],"we":[17],"developed":[18],"two":[19,105],"methods,":[20],"theharmonic":[21],"structure":[22,33],"extraction":[23,34],"method":[24,35,53,85,134,158],"and":[25,65,112,144],"the":[26,37,59,62,92,110,139,152],"reliable":[27,82,96,124],"frame":[28,83,90],"weighting":[29,84],"method.":[30],"The":[31,81,114],"harmonic":[32,56,79],"enables":[36],"input":[40],"speech":[41,60,70,94,111],"signals":[42],"to":[43,123,137],"be":[44,117],"identified":[45,119],"after":[46],"environmental":[47,101,142],"has":[49],"been":[50],"reduced.":[51],"This":[52],"first":[54],"extracts":[55],"components":[57],"from":[61],"sound":[63],"mixtures":[64],"then":[66,86],"resynthesizes":[67],"a":[68,74,156],"clean":[69],"signal":[71],"by":[72,78,100,103,120],"using":[73,104],"sinusoidal":[75],"model":[76],"driven":[77],"components.":[80],"determines":[87],"how":[88],"each":[89],"resynthesized":[93],"is":[95],"(i.e.":[97],"little":[98],"influenced":[99],"noises)":[102],"Gaussian":[106,171],"mixture":[107,172],"models":[108],"noise.":[113],"can":[116],"robustly":[118],"attaching":[121],"importance":[122],"frames.":[125],"Experimental":[126],"results":[127],"with":[128],"thirty":[129],"speakers":[130],"showed":[131],"that":[132],"our":[133],"was":[135,159],"able":[136],"reduce":[138],"influences":[140],"achieved":[145],"an":[146],"error":[147,153],"rate":[148,154],"10.7%,":[150],"while":[151],"conventional":[157],"18.9%.":[160],"Index":[161],"Terms:":[162],"robustness,":[166],"voice":[167,169],"extraction,":[168],"reliability,":[170],"model.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}