{"id":"https://openalex.org/W3152426975","doi":"https://doi.org/10.1109/icassp43922.2022.9746688","title":"Attention Back-End for Automatic Speaker Verification with Multiple Enrollment Utterances","display_name":"Attention Back-End for Automatic Speaker Verification with Multiple Enrollment Utterances","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3152426975","doi":"https://doi.org/10.1109/icassp43922.2022.9746688","mag":"3152426975"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746688","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.01541","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100654128","display_name":"Chang Zeng","orcid":"https://orcid.org/0000-0002-4882-1823"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I4210110163","display_name":"Nippon Soken (Japan)","ror":"https://ror.org/01yk36x23","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110163"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chang Zeng","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan","SOKENDAI, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"SOKENDAI, Japan","institution_ids":["https://openalex.org/I4210110163","https://openalex.org/I200475212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018159","display_name":"Xiaoxiao Miao","orcid":"https://orcid.org/0000-0002-6645-6524"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaoxiao Miao","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I4210110163","display_name":"Nippon Soken (Japan)","ror":"https://ror.org/01yk36x23","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110163"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan","SOKENDAI, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"SOKENDAI, Japan","institution_ids":["https://openalex.org/I4210110163","https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6717","last_page":"6721"},"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":0.9991000294685364,"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":0.9879000186920166,"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/speaker-verification","display_name":"Speaker verification","score":0.8141250610351562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7849903702735901},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.601323127746582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.586576521396637},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43151214718818665},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4112307131290436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36939573287963867}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8141250610351562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7849903702735901},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.601323127746582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.586576521396637},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43151214718818665},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4112307131290436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36939573287963867}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746688","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.01541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01541","pdf_url":"https://arxiv.org/pdf/2104.01541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.01541","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.01541","pdf_url":"https://arxiv.org/pdf/2104.01541","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1589137271","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2134706965","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2201092681","https://openalex.org/W2219249508","https://openalex.org/W2395750323","https://openalex.org/W2397336997","https://openalex.org/W2597655663","https://openalex.org/W2612434969","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2888867175","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2955488837","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2963386218","https://openalex.org/W2963403868","https://openalex.org/W2963466847","https://openalex.org/W2964054038","https://openalex.org/W2972403660","https://openalex.org/W2972961496","https://openalex.org/W2981461916","https://openalex.org/W3008391559","https://openalex.org/W3013020904","https://openalex.org/W3015598461","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3103152812","https://openalex.org/W3115097893","https://openalex.org/W4385245566","https://openalex.org/W6635152626","https://openalex.org/W6735377749","https://openalex.org/W6736780073","https://openalex.org/W6737575990","https://openalex.org/W6739901393","https://openalex.org/W6748257384","https://openalex.org/W6787743207"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2611678594","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Probabilistic":[0],"linear":[1],"discriminant":[2],"analysis":[3],"(PLDA)":[4],"or":[5],"cosine":[6,126],"similarity":[7,127],"have":[8],"been":[9],"widely":[10],"used":[11,42,144],"in":[12],"traditional":[13],"speaker":[14,50,93,131],"verification":[15],"systems":[16],"as":[17,61],"back-end":[18,37,113],"techniques":[19],"to":[20,116],"measure":[21],"pairwise":[22],"similarities.":[23],"To":[24,70],"make":[25],"better":[26],"use":[27,54],"of":[28,67,79],"multiple":[29,103],"enrollment":[30,68,104,149],"utterances,":[31],"we":[32,53,75],"propose":[33],"a":[34,77,147],"novel":[35],"attention":[36,112],"model":[38,114,141],"that":[39,63,109,139],"can":[40,142],"be":[41,143],"for":[43,129,146],"both":[44],"textindependent":[45],"(TI)":[46],"and":[47,52,57,84,97,119,125,133],"text-dependent":[48],"(TD)":[49],"verification,":[51],"scaled-dot":[55],"self-attention":[56,59],"feed-forward":[58],"networks":[60],"architectures":[62],"learn":[64],"the":[65,72,82,110],"intra-relationships":[66],"utterances.":[69],"verify":[71],"proposed":[73,111],"model,":[74],"conduct":[76],"series":[78],"experiments":[80],"on":[81,106,136],"CNCeleb":[83,107],"VoxCeleb":[85,137],"datasets":[86],"by":[87],"combining":[88],"it":[89],"with":[90],"several":[91],"state-of-the-art":[92],"encoders":[94],"including":[95],"TDNN":[96],"ResNet.":[98],"Experimental":[99],"results":[100],"obtained":[101],"using":[102],"utterances":[105],"show":[108],"leads":[115],"lower":[117],"EER":[118],"minDCF":[120],"scores":[121],"than":[122],"its":[123],"PLDA":[124],"counterparts":[128],"each":[130],"encoder,":[132],"an":[134],"experiment":[135],"demonstrates":[138],"our":[140],"even":[145],"single":[148],"case.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-04-13T00:00:00"}