{"id":"https://openalex.org/W3216312964","doi":"https://doi.org/10.1109/taslp.2021.3129360","title":"Coupling a Generative Model With a Discriminative Learning Framework for Speaker Verification","display_name":"Coupling a Generative Model With a Discriminative Learning Framework for Speaker Verification","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3216312964","doi":"https://doi.org/10.1109/taslp.2021.3129360","mag":"3216312964"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3129360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3129360","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486855","display_name":"Peng Shen","orcid":"https://orcid.org/0000-0002-0137-2629"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Peng Shen","raw_affiliation_strings":["Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academic Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academic Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034792613"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.5598,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7421156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"3631","last_page":"3641"},"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":0.9970999956130981,"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/discriminative-model","display_name":"Discriminative model","score":0.8833955526351929},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6985241174697876},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6948482990264893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6441415548324585},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6224485635757446},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.588670015335083},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4549736976623535},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45469892024993896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45078104734420776},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4503379166126251},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.44423699378967285},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39688557386398315},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2264009416103363},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.15608301758766174}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8833955526351929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6985241174697876},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6948482990264893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6441415548324585},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6224485635757446},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.588670015335083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4549736976623535},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45469892024993896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45078104734420776},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4503379166126251},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.44423699378967285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39688557386398315},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2264009416103363},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.15608301758766174},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3129360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3129360","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W102958777","https://openalex.org/W170472577","https://openalex.org/W577640895","https://openalex.org/W1522301498","https://openalex.org/W1618905105","https://openalex.org/W1677182931","https://openalex.org/W1894664571","https://openalex.org/W1936725236","https://openalex.org/W1990942610","https://openalex.org/W2046056978","https://openalex.org/W2056983531","https://openalex.org/W2062104878","https://openalex.org/W2064039105","https://openalex.org/W2064364374","https://openalex.org/W2114217318","https://openalex.org/W2114925438","https://openalex.org/W2117154949","https://openalex.org/W2121812409","https://openalex.org/W2123768812","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2153939756","https://openalex.org/W2170088868","https://openalex.org/W2344769595","https://openalex.org/W2395750323","https://openalex.org/W2406312423","https://openalex.org/W2406982333","https://openalex.org/W2516764878","https://openalex.org/W2560919222","https://openalex.org/W2588127192","https://openalex.org/W2748466034","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2955210370","https://openalex.org/W2962788625","https://openalex.org/W2969985801","https://openalex.org/W2972403660","https://openalex.org/W2981087920","https://openalex.org/W3008391559","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3015368919","https://openalex.org/W3024097277","https://openalex.org/W3024098654","https://openalex.org/W3024869864","https://openalex.org/W3097605294","https://openalex.org/W3111481301","https://openalex.org/W3182396116","https://openalex.org/W6631190155","https://openalex.org/W6636501900","https://openalex.org/W6677328822","https://openalex.org/W6684952529","https://openalex.org/W6713727690","https://openalex.org/W6787439801","https://openalex.org/W6798941905"],"related_works":["https://openalex.org/W3040691452","https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W1493875009","https://openalex.org/W3042518613","https://openalex.org/W3015304056","https://openalex.org/W4388844349"],"abstract_inverted_index":{"The":[0,78,199],"task":[1,91],"of":[2,24,113,231,307],"speaker":[3,40],"verification":[4],"(SV)":[5],"is":[6,12,31,70,126,181,207,265],"to":[7,72,122,128,130,210],"decide":[8],"whether":[9],"an":[10,18,270],"utterance":[11],"spoken":[13],"by":[14,75],"a":[15,26,35,45,49,81,88,131,141,149,155,165,176,246,251,301],"target":[16],"or":[17],"imposter":[19],"speaker.":[20],"In":[21,101,144,172],"most":[22],"studies":[23],"SV,":[25,79],"log-likelihood":[27],"ratio":[28],"(LLR)":[29],"score":[30,201],"estimated":[32],"based":[33,95,258],"on":[34,39,57,140,259,282],"generative":[36,53,159],"probability":[37],"model":[38,54,160,206,229,239,296],"features,":[41],"and":[42,69,125,162,267,288],"compared":[43,304],"with":[44,110,164,183,189,225,241,300,305],"threshold":[46],"for":[47,170,311],"making":[48],"decision.":[50],"However,":[51,116],"the":[52,64,104,111,173,196,204,211,215,221,226,232,238,242,274,285,298,308],"usually":[55],"focuses":[56],"individual":[58],"feature":[59,66],"distributions,":[60],"does":[61],"not":[62],"have":[63],"discriminative":[65,96,102,117,167,216,275],"selection":[67],"ability,":[68],"easy":[71],"be":[73,85,99,108],"distracted":[74],"nuisance":[76,105],"features.":[77],"as":[80,87,193,245,269],"hypothesis":[82],"test,":[83],"could":[84,98,107],"formulated":[86,208],"binary":[89,247],"discrimination":[90,248],"where":[92],"neural":[93,166,179,223],"network":[94,180,224],"learning":[97,118,151,168,217],"applied.":[100],"learning,":[103],"features":[106],"removed":[109],"help":[112],"label":[114],"supervision.":[115],"pays":[119],"more":[120],"attention":[121],"classification":[123],"boundaries,":[124],"prone":[127],"overfitting":[129],"training":[132],"set":[133],"which":[134],"may":[135],"result":[136],"in":[137,195,203,214,256,273,284],"bad":[138],"generalization":[139],"test":[142],"set.":[143],"this":[145],"paper,":[146],"we":[147,235],"propose":[148],"hybrid":[150,174],"framework,":[152,175],"i.e.,":[153],"coupling":[154],"joint":[156],"Bayesian":[157],"(JB)":[158],"structure":[161],"parameters":[163,230,240],"framework":[169],"SV.":[171,312],"two-branch":[177,222],"Siamese":[178],"built":[182],"dense":[184],"layers":[185],"that":[186,293],"are":[187],"coupled":[188],"factorized":[190],"affine":[191],"transforms":[192],"used":[194],"JB":[197,205,233],"model.":[198],"LLR":[200],"estimation":[202],"according":[209],"distance":[212],"metric":[213,254],"framework.":[218],"By":[219],"initializing":[220],"generatively":[227],"learned":[228],"model,":[234],"further":[236],"train":[237],"pairwise":[243],"samples":[244],"task.":[249],"Moreover,":[250],"direct":[252],"evaluation":[253],"(DEM)":[255],"SV":[257,280],"minimum":[260],"empirical":[261],"Bayes":[262],"risk":[263],"(EBR)":[264],"designed":[266],"integrated":[268],"objective":[271],"function":[272],"learning.":[276],"We":[277],"carried":[278],"out":[279],"experiments":[281],"Speakers":[283],"wild":[286],"(SITW)":[287],"Voxceleb.":[289],"Experimental":[290],"results":[291],"showed":[292],"our":[294],"proposed":[295],"improved":[297],"performance":[299],"large":[302],"margin":[303],"state":[306],"art":[309],"models":[310]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}