{"id":"https://openalex.org/W2156580233","doi":"https://doi.org/10.1109/icassp.2009.4960638","title":"Perturbation and pitch normalization as enhancements to speaker recognition","display_name":"Perturbation and pitch normalization as enhancements to speaker recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2156580233","doi":"https://doi.org/10.1109/icassp.2009.4960638","mag":"2156580233"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/A5110121997","display_name":"A. Lawson","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"A. Lawson","raw_affiliation_strings":["RADC, Inc., USA"],"affiliations":[{"raw_affiliation_string":"RADC, Inc., USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111913739","display_name":"Mark Linderman","orcid":null},"institutions":[{"id":"https://openalex.org/I1280414376","display_name":"United States Air Force Research Laboratory","ror":"https://ror.org/02e2egq70","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280414376","https://openalex.org/I1330347796","https://openalex.org/I4210102105","https://openalex.org/I4389425425"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Linderman","raw_affiliation_strings":["Air Force Research Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Air Force Research Laboratory, USA","institution_ids":["https://openalex.org/I1280414376"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076289339","display_name":"Matthew R. Leonard","orcid":null},"institutions":[{"id":"https://openalex.org/I182980787","display_name":"University of Dallas","ror":"https://ror.org/00v3ak792","country_code":"US","type":"education","lineage":["https://openalex.org/I182980787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Leonard","raw_affiliation_strings":["University of Texas, Dallas, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas, Dallas, USA","institution_ids":["https://openalex.org/I182980787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043103292","display_name":"Allen Stauffer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Stauffer","raw_affiliation_strings":["RADC, Inc., USA"],"affiliations":[{"raw_affiliation_string":"RADC, Inc., USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002078949","display_name":"B. B. Pokines","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092106","display_name":"Ocean Acoustical Services and Instrumentation Systems (United States)","ror":"https://ror.org/00cnb1p42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092106"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"B. Pokines","raw_affiliation_strings":["Oasis Systems, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Oasis Systems, Inc., USA","institution_ids":["https://openalex.org/I4210092106"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020355345","display_name":"Michael A. Carlin","orcid":null},"institutions":[{"id":"https://openalex.org/I1280414376","display_name":"United States Air Force Research Laboratory","ror":"https://ror.org/02e2egq70","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280414376","https://openalex.org/I1330347796","https://openalex.org/I4210102105","https://openalex.org/I4389425425"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Carlin","raw_affiliation_strings":["Air Force Research Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Air Force Research Laboratory, USA","institution_ids":["https://openalex.org/I1280414376"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5110121997"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8724,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81402841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4533","last_page":"4536"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9983000159263611,"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":0.996999979019165,"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/normalization","display_name":"Normalization (sociology)","score":0.755772590637207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7024967670440674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6940003633499146},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6742159724235535},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6700750589370728},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.531184196472168},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5041381120681763},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4773730933666229},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45936837792396545},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.434996098279953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4083574116230011},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.084759920835495}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.755772590637207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7024967670440674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940003633499146},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6742159724235535},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6700750589370728},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.531184196472168},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5041381120681763},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4773730933666229},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45936837792396545},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.434996098279953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4083574116230011},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.084759920835495},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W97107628","https://openalex.org/W1964704927","https://openalex.org/W2047131713","https://openalex.org/W2051840726","https://openalex.org/W2054115175","https://openalex.org/W2075142587","https://openalex.org/W2129343891","https://openalex.org/W2170939707","https://openalex.org/W2340721751","https://openalex.org/W4285719527","https://openalex.org/W6604007911","https://openalex.org/W6703643038"],"related_works":["https://openalex.org/W1911592522","https://openalex.org/W2087669554","https://openalex.org/W3044757496","https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321"],"abstract_inverted_index":{"This":[0,71],"study":[1],"proposes":[2],"an":[3,128],"approach":[4],"to":[5,102,122,132],"improving":[6,39],"speaker":[7,94,125],"recognition":[8,95,126],"through":[9],"the":[10,40,51,97,106],"process":[11],"of":[12,18,33,42,53,84,130],"minute":[13],"vocal":[14,85],"tract":[15,86],"length":[16,87,111],"perturbation":[17,34,121],"training":[19,43,107],"files,":[20],"coupled":[21],"with":[22,120],"pitch":[23,110],"normalization":[24,112],"for":[25,38,45,88],"both":[26],"train":[27],"and":[28,82],"test":[29],"data.":[30,108],"The":[31],"notion":[32],"as":[35],"a":[36,61,89],"method":[37],"robustness":[41],"data":[44],"supervised":[46],"classification":[47],"is":[48,114,118],"taken":[49],"from":[50,127],"field":[52],"optical":[54],"character":[55],"recognition,":[56],"where":[57],"distorting":[58],"characters":[59],"within":[60],"certain":[62],"range":[63],"has":[64],"shown":[65],"strong":[66],"improvements":[67],"across":[68],"disparate":[69],"conditions.":[70],"paper":[72],"demonstrates":[73],"that":[74],"acoustic":[75],"perturbation,":[76],"in":[77],"this":[78],"case":[79],"analysis,":[80],"distortion,":[81],"resynthesis":[83],"given":[90],"speaker,":[91],"significantly":[92],"improves":[93],"when":[96],"resulting":[98],"files":[99],"are":[100],"used":[101],"augment":[103],"or":[104],"replace":[105],"A":[109],"technique":[113],"also":[115],"discussed,":[116],"which":[117],"combined":[119],"improve":[123],"open-set":[124],"EER":[129],"20%":[131],"6.7%.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
