{"id":"https://openalex.org/W186911294","doi":"https://doi.org/10.21437/interspeech.2005-642","title":"Class-dependent score combination for speaker recognition","display_name":"Class-dependent score combination for speaker recognition","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W186911294","doi":"https://doi.org/10.21437/interspeech.2005-642","mag":"186911294"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-642","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023103090","display_name":"Kemal S\u00f6nmez","orcid":"https://orcid.org/0000-0002-2816-6438"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kemal S\u00f6nmez","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065814281","display_name":"Sachin Kajarekar","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Kajarekar","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056267912"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.7402,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90427526,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2173","last_page":"2176"},"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":0.9973000288009644,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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/nist","display_name":"NIST","score":0.8203705549240112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7674567699432373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7590539455413818},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6946523189544678},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.645674467086792},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6178171038627625},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5970357656478882},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5581061244010925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5194529891014099},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44741290807724},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4449130892753601},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42537420988082886},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4128812849521637}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8203705549240112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674567699432373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7590539455413818},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6946523189544678},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.645674467086792},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6178171038627625},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5970357656478882},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5581061244010925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194529891014099},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44741290807724},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4449130892753601},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42537420988082886},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4128812849521637},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2005-642","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W7296353","https://openalex.org/W88602082","https://openalex.org/W1535817944","https://openalex.org/W1553271421","https://openalex.org/W2108445219","https://openalex.org/W2114851258","https://openalex.org/W2129125243","https://openalex.org/W2144158639","https://openalex.org/W2165358012","https://openalex.org/W3145606929"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Many":[0],"recent":[1],"performance":[2,131],"improvements":[3],"in":[4,12,59,73,103],"speaker":[5,149],"recognition":[6,125],"using":[7,136],"higher-level":[8],"features,":[9],"as":[10],"demonstrated":[11],"the":[13,35,47,96,100,119,137,148,173],"NIST":[14,174],"Speaker":[15],"Recognition":[16],"Evaluation":[17],"(SRE)":[18],"task,":[19],"rely":[20],"on":[21,92,172],"combinations":[22],"of":[23,30,34,38,57,62,69,94,111,118,142],"multiple":[24],"systems":[25],"modeling":[26],"a":[27,54,60,74,85,104,109,143,163],"large":[28,36,55],"variety":[29],"features.":[31],"The":[32],"diversity":[33],"set":[37,56,110],"features":[39,45],"starting":[40],"from":[41,53],"short-term":[42],"acoustic":[43],"spectrum":[44],"all":[46],"way":[48],"to":[49],"habitual":[50],"word":[51],"usage":[52],"speakers":[58],"multitude":[61],"settings":[63],"(acoustic":[64],"environment,":[65],"speaking":[66],"style,":[67],"quantities":[68],"enrollment/test":[70],"data)":[71],"results":[72,171],"challenging":[75],"model":[76,144],"combination":[77,88],"task.":[78],"In":[79],"this":[80],"work,":[81],"we":[82],"are":[83,133],"presenting":[84],"class-based":[86],"score":[87],"technique":[89],"that":[90,129],"relies":[91],"clustering":[93,147],"both":[95],"target":[97],"models":[98],"and":[99,160,177],"test":[101,157],"utterances":[102],"vector":[105],"space":[106],"defined":[107],"by":[108,122,135],"speaker-specific":[112],"transformation":[113],"parameters":[114],"estimated":[115],"during":[116],"transcription":[117],"talker\u2019s":[120],"speech":[121,124],"automatic":[123],"(ASR).":[126],"We":[127,169],"show":[128],"significant":[130],"gains":[132],"obtained":[134],"first":[138],"few":[139],"principal":[140],"components":[141],"transform":[145],"for":[146,154,166],"verification":[150],"trials":[151],"into":[152],"classes":[153],"(target":[155],"speaker,":[156],"utterance)":[158],"pairs,":[159],"then":[161],"training":[162],"separate":[164],"combiner":[165],"each":[167],"class.":[168],"report":[170],"SRE":[175],"2004":[176],"FISHER":[178],"datasets.":[179]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}