{"id":"https://openalex.org/W2106865280","doi":"https://doi.org/10.1109/icassp.2006.1659969","title":"Secondary Classification for GMM Based Speaker Recognition","display_name":"Secondary Classification for GMM Based Speaker Recognition","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2106865280","doi":"https://doi.org/10.1109/icassp.2006.1659969","mag":"2106865280"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1659969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1659969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5029030495","display_name":"Jason Pelecanos","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Pelecanos","raw_affiliation_strings":["Conversational Biometrics Group, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","Conversational Biometrics Group, IBM T.J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598. jwpeleca@us.ibm.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Conversational Biometrics Group, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"Conversational Biometrics Group, IBM T.J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, NY 10598. jwpeleca@us.ibm.com","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Povey","raw_affiliation_strings":["Conversational Biometrics Group, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","Conversational Biometrics Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Conversational Biometrics Group, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"Conversational Biometrics Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111944718","display_name":"Ganesh N. Ramaswamy","orcid":"https://orcid.org/0009-0002-8015-0844"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Ramaswamy","raw_affiliation_strings":["Conversational Biometrics Group, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","Conversational Biometrics Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Conversational Biometrics Group, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"Conversational Biometrics Group, IBM Thomas J. Watson Res. Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8651,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87657215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.72802734375},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7001435160636902},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6703716516494751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.629571795463562},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6215965151786804},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5649211406707764},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.545886754989624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5266199707984924},{"id":"https://openalex.org/keywords/handset","display_name":"Handset","score":0.5109164118766785},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44831612706184387},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43285125494003296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72802734375},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7001435160636902},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6703716516494751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.629571795463562},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6215965151786804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5649211406707764},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.545886754989624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5266199707984924},{"id":"https://openalex.org/C2779971919","wikidata":"https://www.wikidata.org/wiki/Q1378949","display_name":"Handset","level":2,"score":0.5109164118766785},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44831612706184387},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43285125494003296},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2006.1659969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1659969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.124.2291","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.124.2291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dpovey.googlepages.com/icassp06_spkrid.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1532958172","https://openalex.org/W1752971345","https://openalex.org/W1838773786","https://openalex.org/W2041823554","https://openalex.org/W2078953162","https://openalex.org/W2105393821","https://openalex.org/W2139037446","https://openalex.org/W2402182541","https://openalex.org/W6713344487"],"related_works":["https://openalex.org/W2106922437","https://openalex.org/W2807901368","https://openalex.org/W2158491338","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2118039276"],"abstract_inverted_index":{"This":[0,46],"paper":[1],"discusses":[2],"the":[3,11,42,49,53,122],"use":[4],"of":[5,14,41,55,61],"a":[6,15,36,83,92],"secondary":[7],"classifier":[8],"to":[9,20,34,51,69,90,114],"reweight":[10],"frame-based":[12],"scores":[13],"speaker":[16],"recognition":[17],"system":[18],"according":[19],"which":[21],"region":[22],"in":[23,109],"feature":[24,62],"space":[25,63],"they":[26],"belong.":[27],"The":[28,103],"score":[29],"mapping":[30,94],"function":[31,95],"is":[32,112],"constructed":[33],"perform":[35],"likelihood":[37],"ratio":[38],"(LR)":[39],"correction":[40],"original":[43],"LR":[44],"scores.":[45],"approach":[47,108],"has":[48],"ability":[50],"limit":[52],"effect":[54],"rogue":[56],"model":[57],"components":[58],"and":[59],"regions":[60],"that":[64,96],"may":[65],"not":[66],"be":[67,88],"robust":[68],"different":[70],"audio":[71],"environments,":[72],"handset":[73],"types":[74],"or":[75],"speakers.":[76],"Prior":[77],"information":[78],"available":[79],"from":[80],"tests":[81],"on":[82],"development":[84],"data":[85,128],"set":[86],"can":[87],"used":[89],"determine":[91],"log-likelihood-ratio":[93],"more":[97],"appropriately":[98],"weights":[99],"each":[100],"speech":[101],"frame.":[102],"computational":[104],"overhead":[105],"for":[106,116,121],"this":[107],"online":[110],"mode":[111],"close":[113],"negligible":[115],"significant":[117],"performance":[118],"gains":[119],"shown":[120],"NIST":[123],"2004":[124],"Speaker":[125],"Recognition":[126],"Evaluation":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}