{"id":"https://openalex.org/W247152494","doi":"https://doi.org/10.21437/interspeech.2009-391","title":"Text-independent speaker identification using vocal tract length normalization for building universal background model","display_name":"Text-independent speaker identification using vocal tract length normalization for building universal background model","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W247152494","doi":"https://doi.org/10.21437/interspeech.2009-391","mag":"247152494"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-391","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5002627413","display_name":"Achintya Kumar Sarkar","orcid":"https://orcid.org/0000-0002-9870-3980"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"A. K. Sarkar","raw_affiliation_strings":["Indian Institute of Technology Kanpur \u2028"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur \u2028","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["Indian Institute of Technology Kanpur, Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024123814","display_name":"Shakti P. Rath","orcid":null},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. P. Rath","raw_affiliation_strings":["Indian Institute of Technology Kanpur, Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002627413"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":0.901,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79152612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2331","last_page":"2334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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":0.9973000288009644,"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":0.8578941822052002},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8192795515060425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.680860161781311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6530138850212097},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5384559035301208},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.496846467256546},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4671470820903778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39191335439682007},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34917396306991577}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8578941822052002},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8192795515060425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680860161781311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6530138850212097},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5384559035301208},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.496846467256546},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4671470820903778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39191335439682007},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34917396306991577},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-391","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W193437634","https://openalex.org/W257179395","https://openalex.org/W2025013471","https://openalex.org/W2069883713","https://openalex.org/W2105667909","https://openalex.org/W2164931619"],"related_works":["https://openalex.org/W2087669554","https://openalex.org/W3044757496","https://openalex.org/W1911592522","https://openalex.org/W2370679465","https://openalex.org/W1521049138","https://openalex.org/W2154141294","https://openalex.org/W2611875816","https://openalex.org/W2548243992","https://openalex.org/W3035928819","https://openalex.org/W2573756443"],"abstract_inverted_index":{"In":[0],"this":[1,57,117],"paper,":[2],"we":[3,144],"propose":[4],"to":[5,12,86,153],"use":[6,99],"Vocal":[7,26],"Tract":[8,27],"Length":[9,28],"Normalization":[10],"(VTLN)":[11],"build":[13],"the":[14,40,44,61,71,77,83,92,98,106,111,125,154],"Universal":[15],"Background":[16],"Model":[17],"(UBM)":[18],"for":[19],"a":[20,34,67],"closed":[21],"set":[22],"speaker":[23,79,112],"identification":[24],"system.":[25],"(VTL)":[29],"differences":[30],"among":[31],"speakers":[32],"is":[33,47],"major":[35],"source":[36],"of":[37,100],"variability":[38],"in":[39,60,66,70,91,104,124],"speech":[41,62],"signal.":[42],"Since":[43],"UBM":[45,84,107],"model":[46,69,85,108,119],"trained":[48],"using":[49,142],"data":[50],"from":[51,82,116],"many":[52],"speakers,":[53],"it":[54],"statistically":[55],"captures":[56],"inherent":[58],"variation":[59],"signal,":[63],"which":[64],"results":[65],"\u201ccoarse\u201d":[68],"acoustic":[72,93,126],"space.":[73,94,127],"This":[74],"may":[75],"cause":[76],"adapted":[78,113],"models":[80,114],"obtained":[81,115],"have":[87,121],"significantly":[88],"high":[89],"overlap":[90],"We":[95,128],"hypothesize":[96],"that":[97,141],"VTLN":[101,143],"will":[102,120],"help":[103],"compacting":[105],"and":[109,134,139],"thus":[110],"compact":[118],"better":[122],"speaker-separability":[123],"perform":[129],"experiments":[130],"on":[131],"MIT,":[132],"TIMIT":[133],"NIST":[135],"2004":[136],"SRE":[137],"databases":[138],"show":[140],"can":[145],"achieve":[146],"lesser":[147],"Identification":[148],"Error":[149],"Rates":[150],"as":[151],"compared":[152],"conventional":[155],"GMM-UBM":[156],"based":[157],"method.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}