{"id":"https://openalex.org/W4205185612","doi":"https://doi.org/10.1109/taslp.2021.3138681","title":"Optimizing Tandem Speaker Verification and Anti-Spoofing Systems","display_name":"Optimizing Tandem Speaker Verification and Anti-Spoofing Systems","publication_year":2021,"publication_date":"2021-12-28","ids":{"openalex":"https://openalex.org/W4205185612","doi":"https://doi.org/10.1109/taslp.2021.3138681"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3138681","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3138681","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09664367.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09664367.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048689678","display_name":"Anssi Kanervisto","orcid":"https://orcid.org/0000-0002-7479-4574"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"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/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI","JP"],"is_corresponding":true,"raw_author_name":"Anssi Kanervisto","raw_affiliation_strings":["School of Computing, University of Eastern Finland, 163043 Joensuu, It-Suomi, Finland, 80101 (e-mail: anssk@uef.fi)","National University of Singapore. J. Yamagishi is with National Institute of Informatics, Tokyo, Japan","with School of Comput-ing, University of Eastern Finland, Joensuu, Finland. V"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, 163043 Joensuu, It-Suomi, Finland, 80101 (e-mail: anssk@uef.fi)","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]},{"raw_affiliation_string":"National University of Singapore. J. Yamagishi is with National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"with School of Comput-ing, University of Eastern Finland, Joensuu, Finland. V","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"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/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI","JP"],"is_corresponding":false,"raw_author_name":"Ville Hautamaki","raw_affiliation_strings":["School of Computing, University of Eastern Finland, 163043 Joensuu, It-Suomi, Finland, (e-mail: villeh@uef.fi)","with School of Comput-ing, University of Eastern Finland, Joensuu, Finland. V","National University of Singapore. J. Yamagishi is with National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, 163043 Joensuu, It-Suomi, Finland, (e-mail: villeh@uef.fi)","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]},{"raw_affiliation_string":"with School of Comput-ing, University of Eastern Finland, Joensuu, Finland. V","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]},{"raw_affiliation_string":"National University of Singapore. J. Yamagishi is with National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"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/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI","JP"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["School of Computing, University of Eastern Finland, 163043 Joensuu, It-Suomi, Finland, (e-mail: tkinnu@uef.fi)","National University of Singapore. J. Yamagishi is with National Institute of Informatics, Tokyo, Japan","with School of Comput-ing, University of Eastern Finland, Joensuu, Finland. V"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, 163043 Joensuu, It-Suomi, Finland, (e-mail: tkinnu@uef.fi)","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]},{"raw_affiliation_string":"National University of Singapore. J. Yamagishi is with National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"with School of Comput-ing, University of Eastern Finland, Joensuu, Finland. V","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"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/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"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/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, 13513 Chiyoda-ku Tokyo, Japan, 101-8430 (e-mail: jyamagis@nii.ac.jp)","with School of Comput-ing, University of Eastern Finland, Joensuu, Finland. V","National University of Singapore. J. Yamagishi is with National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, 13513 Chiyoda-ku Tokyo, Japan, 101-8430 (e-mail: jyamagis@nii.ac.jp)","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"with School of Comput-ing, University of Eastern Finland, Joensuu, Finland. V","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]},{"raw_affiliation_string":"National University of Singapore. J. Yamagishi is with National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048689678"],"corresponding_institution_ids":["https://openalex.org/I175532246","https://openalex.org/I184597095","https://openalex.org/I4210107997"],"apc_list":null,"apc_paid":null,"fwci":1.2599,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84219381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"477","last_page":"488"},"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":0.9954000115394592,"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":0.9915000200271606,"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/spoofing-attack","display_name":"Spoofing attack","score":0.8590147495269775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8501890897750854},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.8020889759063721},{"id":"https://openalex.org/keywords/tandem","display_name":"Tandem","score":0.60898357629776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5401285290718079},{"id":"https://openalex.org/keywords/countermeasure","display_name":"Countermeasure","score":0.4507737159729004},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4270373284816742},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3640151023864746},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.15387094020843506}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.8590147495269775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8501890897750854},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8020889759063721},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.60898357629776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5401285290718079},{"id":"https://openalex.org/C21593369","wikidata":"https://www.wikidata.org/wiki/Q1032176","display_name":"Countermeasure","level":2,"score":0.4507737159729004},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4270373284816742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3640151023864746},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.15387094020843506},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3138681","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3138681","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09664367.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2201.09709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.09709","pdf_url":"https://arxiv.org/pdf/2201.09709","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/taslp.2021.3138681","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3138681","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09664367.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G598299161","display_name":null,"funder_award_id":"309629","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4205185612.pdf","grobid_xml":"https://content.openalex.org/works/W4205185612.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W577640895","https://openalex.org/W1486911581","https://openalex.org/W1506806321","https://openalex.org/W2013477326","https://openalex.org/W2023238506","https://openalex.org/W2069883713","https://openalex.org/W2119717200","https://openalex.org/W2121812409","https://openalex.org/W2136682440","https://openalex.org/W2137310491","https://openalex.org/W2165880886","https://openalex.org/W2219249508","https://openalex.org/W2257979135","https://openalex.org/W2571059041","https://openalex.org/W2586846985","https://openalex.org/W2736601468","https://openalex.org/W2745896134","https://openalex.org/W2754517384","https://openalex.org/W2799053639","https://openalex.org/W2808631503","https://openalex.org/W2936802426","https://openalex.org/W2963508548","https://openalex.org/W2964268978","https://openalex.org/W2967606780","https://openalex.org/W2972606715","https://openalex.org/W2972811785","https://openalex.org/W2982474723","https://openalex.org/W3004720752","https://openalex.org/W3024198351","https://openalex.org/W3024541814","https://openalex.org/W3026777299","https://openalex.org/W3041816239","https://openalex.org/W3100448777","https://openalex.org/W3104056985","https://openalex.org/W3126634788","https://openalex.org/W3177149368","https://openalex.org/W3197358873","https://openalex.org/W3198329097","https://openalex.org/W3200527256","https://openalex.org/W6627932998","https://openalex.org/W6680117457","https://openalex.org/W6683204974","https://openalex.org/W6688816777","https://openalex.org/W6729448088","https://openalex.org/W6741002519","https://openalex.org/W6766978945","https://openalex.org/W6769178842"],"related_works":["https://openalex.org/W4294437891","https://openalex.org/W4226389478","https://openalex.org/W3016138785","https://openalex.org/W4297792928","https://openalex.org/W4221161333","https://openalex.org/W3113108043","https://openalex.org/W2061278248","https://openalex.org/W2168254078","https://openalex.org/W4298202768","https://openalex.org/W1914348842"],"abstract_inverted_index":{"As":[0],"automatic":[1],"speaker":[2],"verification":[3],"(ASV)":[4],"systems":[5,21,71],"are":[6,12,72],"vulnerable":[7],"to":[8,22,93],"spoofing":[9,18],"attacks,":[10],"they":[11],"typically":[13],"used":[14],"in":[15,131,134,138],"conjunction":[16],"with":[17,60,123],"countermeasure":[19],"(CM)":[20],"improve":[23],"security.":[24],"For":[25],"example,":[26],"the":[27,33,39,47,95,132,135],"CM":[28,70],"can":[29,41,57],"first":[30],"determine":[31,42],"whether":[32,43],"input":[34],"is":[35],"human":[36],"speech,":[37],"then":[38],"ASV":[40,68],"this":[44,89],"speech":[45],"matches":[46],"speakers":[48],"identity.":[49],"The":[50,112],"performance":[51],"of":[52,104],"such":[53],"a":[54,61,101,127,139],"tandem":[55,62,96],"system":[56,97],"be":[58],"measured":[59],"detection":[63],"cost":[64],"function":[65],"(t-DCF).":[66],"However,":[67],"and":[69,79,106],"usually":[73],"trained":[74],"separately,":[75],"using":[76],"different":[77],"metrics":[78],"data,":[80],"which":[81],"does":[82],"not":[83],"optimize":[84,94],"their":[85],"combined":[86],"performance.":[87],"In":[88],"work,":[90],"we":[91],"propose":[92],"directly":[98],"by":[99],"creating":[100],"differentiable":[102],"version":[103],"t-DCF":[105,133],"employing":[107],"techniques":[108],"from":[109],"reinforcement":[110],"learning.":[111],"results":[113],"indicate":[114],"that":[115],"these":[116],"approaches":[117],"offer":[118],"better":[119],"outcomes":[120],"than":[121],"finetuning,":[122],"our":[124],"method":[125],"providing":[126],"20\\%":[128],"relative":[129],"improvement":[130],"ASVSpoof19":[136],"dataset":[137],"constrained":[140],"setting.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}