{"id":"https://openalex.org/W4414819136","doi":"https://doi.org/10.1109/taslpro.2026.3688932","title":"Joint Optimization of Speaker and Spoof Detectors for Spoofing-Robust Automatic Speaker Verification","display_name":"Joint Optimization of Speaker and Spoof Detectors for Spoofing-Robust Automatic Speaker Verification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414819136","doi":"https://doi.org/10.1109/taslpro.2026.3688932"},"language":"en","primary_location":{"id":"doi:10.1109/taslpro.2026.3688932","doi":"https://doi.org/10.1109/taslpro.2026.3688932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslpro.2026.3688932","pdf_url":null,"source":{"id":"https://openalex.org/S5407042752","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"2998-4173","issn":["2998-4173"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-3"],"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 Transactions on Audio, Speech and Language Processing","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.01818","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100257872","display_name":"O\u011fuzhan Kurnaz","orcid":"https://orcid.org/0000-0002-4595-8031","observed_orcids":["https://orcid.org/0000-0002-4595-8031"]},"institutions":[{"id":"https://openalex.org/I192257213","display_name":"Bursa Technical University","ror":"https://ror.org/03rdpn141","country_code":"TR","type":"education","lineage":["https://openalex.org/I192257213"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"O\u011fuzhan Kurnaz","raw_affiliation_strings":["Bursa Technical University, Bursa, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0002-4595-8031","affiliations":[{"raw_affiliation_string":"Bursa Technical University, Bursa, T\u00fcrkiye","institution_ids":["https://openalex.org/I192257213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013209021","display_name":"Jagabandhu Mishra","orcid":"https://orcid.org/0000-0003-1878-6286","observed_orcids":["https://orcid.org/0000-0003-1878-6286"]},"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"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jagabandhu Mishra","raw_affiliation_strings":["University of Eastern Finland, Joensuu, Finland"],"raw_orcid":"https://orcid.org/0000-0003-1878-6286","affiliations":[{"raw_affiliation_string":"University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322","observed_orcids":["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"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi H. Kinnunen","raw_affiliation_strings":["University of Eastern Finland, Joensuu, Finland"],"raw_orcid":"https://orcid.org/0000-0002-4371-7322","affiliations":[{"raw_affiliation_string":"University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076100840","display_name":"Cemal Hanil\u00e7i","orcid":"https://orcid.org/0000-0002-9174-0367","observed_orcids":["https://orcid.org/0000-0002-9174-0367"]},"institutions":[{"id":"https://openalex.org/I192257213","display_name":"Bursa Technical University","ror":"https://ror.org/03rdpn141","country_code":"TR","type":"education","lineage":["https://openalex.org/I192257213"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Cemal Hanil\u00e7i","raw_affiliation_strings":["Bursa Technical University, Bursa, T\u00fcrkiye"],"raw_orcid":"https://orcid.org/0000-0002-9174-0367","affiliations":[{"raw_affiliation_string":"Bursa Technical University, Bursa, T\u00fcrkiye","institution_ids":["https://openalex.org/I192257213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":4.1854,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93728886,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"34","issue":null,"first_page":"2679","last_page":"2694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926999807357788,"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":0.9926999807357788,"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/T10828","display_name":"Biometric Identification and Security","score":0.004800000227987766,"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/T10860","display_name":"Speech and Audio Processing","score":0.000699999975040555,"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/asvspoof-2021","display_name":"ASVspoof 2021","score":0.7459999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8126000165939331},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6279000043869019},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5861999988555908},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5651000142097473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.539900004863739},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2840999960899353}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslpro.2026.3688932","doi":"https://doi.org/10.1109/taslpro.2026.3688932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslpro.2026.3688932","pdf_url":null,"source":{"id":"https://openalex.org/S5407042752","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"2998-4173","issn":["2998-4173"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-3"],"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 Transactions on Audio, Speech and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2510.01818","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.01818","pdf_url":"https://arxiv.org/pdf/2510.01818","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:erepo.uef.fi:123456789/38939","doi":null,"is_oa":true,"landing_page_url":"https://erepo.uef.fi/handle/123456789/38939","pdf_url":"https://erepo.uef.fi/bitstreams/73ec0fdc-960f-447d-8cb0-3d5448cd851b/download","source":{"id":"https://openalex.org/S4306402418","display_name":"UEF eRepo (University of Eastern Finland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I175532246","host_organization_name":"University of Eastern Finland","host_organization_lineage":["https://openalex.org/I175532246"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2510.01818","doi":"https://doi.org/10.48550/arxiv.2510.01818","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.01818","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.01818","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.01818","pdf_url":"https://arxiv.org/pdf/2510.01818","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414819136.pdf","grobid_xml":"https://content.openalex.org/works/W4414819136.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W1601717684","https://openalex.org/W1994967892","https://openalex.org/W2023238506","https://openalex.org/W2064463502","https://openalex.org/W2069883713","https://openalex.org/W2078112764","https://openalex.org/W2087046691","https://openalex.org/W2101587318","https://openalex.org/W2123299109","https://openalex.org/W2165880886","https://openalex.org/W2167768673","https://openalex.org/W2784874046","https://openalex.org/W2807550049","https://openalex.org/W2936802426","https://openalex.org/W2949676527","https://openalex.org/W2972606715","https://openalex.org/W3005214933","https://openalex.org/W3010925296","https://openalex.org/W3024869864","https://openalex.org/W3041816239","https://openalex.org/W3095259706","https://openalex.org/W3201773091","https://openalex.org/W3206886023","https://openalex.org/W3209984917","https://openalex.org/W4221140846","https://openalex.org/W4221161332","https://openalex.org/W4221162964","https://openalex.org/W4225527248","https://openalex.org/W4226048490","https://openalex.org/W4226389478","https://openalex.org/W4236329017","https://openalex.org/W4280492375","https://openalex.org/W4283734172","https://openalex.org/W4283807685","https://openalex.org/W4284689653","https://openalex.org/W4296068428","https://openalex.org/W4296068436","https://openalex.org/W4296068612","https://openalex.org/W4296068766","https://openalex.org/W4296070450","https://openalex.org/W4297841654","https://openalex.org/W4297841768","https://openalex.org/W4299551239","https://openalex.org/W4385823275","https://openalex.org/W4386609452","https://openalex.org/W4392487686","https://openalex.org/W4402111801","https://openalex.org/W4402112305","https://openalex.org/W4403954787","https://openalex.org/W4403955190","https://openalex.org/W4403955245","https://openalex.org/W4403955409","https://openalex.org/W4403955415","https://openalex.org/W4403955716","https://openalex.org/W4403956081","https://openalex.org/W4403956201","https://openalex.org/W4403956257","https://openalex.org/W4403956654","https://openalex.org/W4407899852","https://openalex.org/W4413454979","https://openalex.org/W4415319399","https://openalex.org/W4415432646","https://openalex.org/W4415433680","https://openalex.org/W4415433888"],"related_works":["https://openalex.org/W7155043904","https://openalex.org/W4294437891","https://openalex.org/W4221140846","https://openalex.org/W4375869230","https://openalex.org/W4283067891","https://openalex.org/W4407899852","https://openalex.org/W4221161332","https://openalex.org/W4297841768","https://openalex.org/W7129454955","https://openalex.org/W4413454979"],"abstract_inverted_index":{"Spoofing-robust":[0],"speaker":[1,8,25,111],"verification":[2],"(SASV)":[3],"combines":[4],"the":[5,48,68,71,84,104,133],"tasks":[6],"of":[7,24,47,106,135],"and":[9,26,102,126,140,146],"spoof":[10,27,116],"detection":[11,112,117],"to":[12,124,128],"authenticate":[13],"speakers":[14],"under":[15],"adversarial":[16],"settings.":[17],"Many":[18],"SASV":[19,73,148],"systems":[20],"rely":[21],"on":[22,36,83],"fusion":[23,95],"cues":[28],"at":[29],"embedding,":[30],"score":[31,94],"or":[32],"decision":[33],"levels,":[34],"based":[35],"independently":[37],"trained":[38],"subsystems.":[39],"In":[40,59],"this":[41],"study,":[42],"we":[43,61],"respect":[44],"similar":[45],"modularity":[46],"two":[49,89],"subsystems,":[50],"by":[51],"integrating":[52],"their":[53],"outputs":[54],"using":[55],"trainable":[56],"back-end":[57,69],"classifiers.":[58],"particular,":[60],"explore":[62],"various":[63],"approaches":[64],"for":[65,70,110,115,143],"directly":[66],"optimizing":[67],"recently-proposed":[72],"performance":[74],"metric":[75],"(a-DCF)":[76],"as":[77],"a":[78],"training":[79],"objective.":[80],"Our":[81],"experiments":[82],"ASVspoof":[85],"5":[86],"dataset":[87],"demonstrate":[88],"important":[90],"findings:":[91],"(i)":[92],"nonlinear":[93],"consistently":[96],"improves":[97],"a-DCF":[98,123],"over":[99],"linear":[100],"fusion,":[101],"(ii)":[103],"combination":[105],"weighted":[107],"cosine":[108],"scoring":[109],"with":[113],"SSL-AASIST":[114],"achieves":[118],"state-of-the-art":[119],"performance,":[120],"reducing":[121],"min":[122],"0.196":[125],"SPF-EER":[127],"7.6%.":[129],"These":[130],"contributions":[131],"highlight":[132],"importance":[134],"modular":[136],"design,":[137],"calibrated":[138],"integration,":[139],"task-aligned":[141],"optimization":[142],"advancing":[144],"robust":[145],"interpretable":[147],"systems.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2025-10-10T00:00:00"}
