{"id":"https://openalex.org/W2166577872","doi":"https://doi.org/10.1109/icassp.2002.5743677","title":"Speaker identification using online, frame dependent, and diffusive variance adaptation","display_name":"Speaker identification using online, frame dependent, and diffusive variance adaptation","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2166577872","doi":"https://doi.org/10.1109/icassp.2002.5743677","mag":"2166577872"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743677","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5082098338","display_name":"Scott Axelrod","orcid":null},"institutions":[{"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":true,"raw_author_name":"Scott Axelrod","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5082098338"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26960154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9825000166893005,"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/variance","display_name":"Variance (accounting)","score":0.691145658493042},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6765441298484802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6656330227851868},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6050543189048767},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5820595622062683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5533574819564819},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.48770079016685486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3799459934234619},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.19242507219314575},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12176504731178284},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11792242527008057}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.691145658493042},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6765441298484802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6656330227851868},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6050543189048767},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5820595622062683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5533574819564819},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.48770079016685486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3799459934234619},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.19242507219314575},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12176504731178284},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11792242527008057},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743677","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":11,"referenced_works":["https://openalex.org/W133895826","https://openalex.org/W1578604476","https://openalex.org/W1806101177","https://openalex.org/W1846690939","https://openalex.org/W2041823554","https://openalex.org/W2049633694","https://openalex.org/W2146871184","https://openalex.org/W2162125266","https://openalex.org/W2326565381","https://openalex.org/W3129711340","https://openalex.org/W6634752090"],"related_works":["https://openalex.org/W2517638034","https://openalex.org/W4366725928","https://openalex.org/W4247725880","https://openalex.org/W2249138175","https://openalex.org/W2120097768","https://openalex.org/W2154141294","https://openalex.org/W2978471304","https://openalex.org/W2100854157","https://openalex.org/W2380891674","https://openalex.org/W2075208738"],"abstract_inverted_index":{"In":[0],"this":[1,86],"paper":[2],"we":[3,121],"perform":[4,58],"maximum":[5],"likelihood":[6],"adaptation":[7,40],"of":[8,11,30,36,47,50,88,95,101,113,125],"the":[9,28,37,39,48,51,70,74,89,98,111,118,137],"variances":[10],"a":[12,19,43,64],"Gaussian":[13],"mixture":[14],"model":[15,71],"(GMM)":[16],"based":[17],"on":[18,117],"single":[20],"acoustic":[21],"data":[22],"frame.":[23],"We":[24,53],"show":[25],"that,":[26],"in":[27,62,130],"case":[29],"prototype":[31,77],"(and":[32],"frame)":[33],"dependent":[34],"scaling":[35],"variances,":[38],"amounts":[41],"to":[42,57,69,93,106,110,127,136],"simple":[44],"non-linear":[45],"warping":[46],"exponent":[49],"Gaussian.":[52],"also":[54],"introduce":[55],"algorithms":[56],"\u201cdiffusive\u201d":[59],"variance":[60],"adaptation,":[61],"which":[63,103],"positive":[65],"constant":[66,75],"is":[67,76,91,104],"added":[68],"variance.":[72],"When":[73],"independent":[78],"(but":[79],"possibly":[80],"frame":[81],"and":[82],"coordinate":[83],"dimension":[84],"dependent),":[85],"modification":[87],"GMM":[90],"equivalent":[92],"evolution":[94],"it":[96],"by":[97],"diffusion":[99],"equation":[100],"physics,":[102],"guaranteed":[105],"increase":[107],"entropy.":[108],"Applied":[109],"task":[112],"text-independent":[114],"speaker":[115,131],"identification":[116,132],"LLHDB":[119],"database,":[120],"report":[122],"relative":[123],"improvements":[124],"up":[126],"28%":[128],"reduction":[129],"error":[133],"rate":[134],"compared":[135],"unadapted":[138],"model.":[139]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}