{"id":"https://openalex.org/W4298054525","doi":"https://doi.org/10.48550/arxiv.2209.14098","title":"Deepfake audio detection by speaker verification","display_name":"Deepfake audio detection by speaker verification","publication_year":2022,"publication_date":"2022-09-28","ids":{"openalex":"https://openalex.org/W4298054525","doi":"https://doi.org/10.48550/arxiv.2209.14098"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.14098","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.14098","pdf_url":"https://arxiv.org/pdf/2209.14098","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.14098","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088157699","display_name":"Alessandro Pianese","orcid":"https://orcid.org/0000-0003-4765-8566"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pianese, Alessandro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085769320","display_name":"Davide Cozzolino","orcid":"https://orcid.org/0000-0001-6158-7595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cozzolino, Davide","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081981044","display_name":"Giovanni Poggi","orcid":"https://orcid.org/0000-0003-1327-4812"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Poggi, Giovanni","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080842029","display_name":"Luisa Verdoliva","orcid":"https://orcid.org/0000-0001-7286-7963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Verdoliva, Luisa","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088157699"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.8450841903686523},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.7233699560165405},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7171281576156616},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5841249823570251},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5792800188064575},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5467133522033691},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5187587738037109},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46125635504722595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4381873607635498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42784419655799866},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.421906054019928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4131908714771271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450841903686523},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.7233699560165405},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7171281576156616},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5841249823570251},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5792800188064575},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5467133522033691},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5187587738037109},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46125635504722595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4381873607635498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42784419655799866},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.421906054019928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4131908714771271},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.14098","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.14098","pdf_url":"https://arxiv.org/pdf/2209.14098","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.14098","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.14098","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.14098","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.14098","pdf_url":"https://arxiv.org/pdf/2209.14098","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4298054525.pdf","grobid_xml":"https://content.openalex.org/works/W4298054525.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W4317103504","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Thanks":[0],"to":[1,32,60,76,107,154],"recent":[2],"advances":[3],"in":[4,68],"deep":[5],"learning,":[6],"sophisticated":[7],"generation":[8],"tools":[9,23,65],"exist,":[10],"nowadays,":[11],"that":[12,95],"produce":[13],"extremely":[14],"realistic":[15],"synthetic":[16,36,61],"speech.":[17],"However,":[18],"malicious":[19],"uses":[20],"of":[21,49,101],"such":[22,138],"are":[24],"possible":[25],"and":[26,45,151],"likely,":[27],"posing":[28],"a":[29,41,46,91],"serious":[30],"threat":[31],"our":[33],"society.":[34],"Hence,":[35],"voice":[37],"detection":[38,50,93],"has":[39],"become":[40],"pressing":[42],"research":[43],"topic,":[44],"large":[47],"variety":[48],"methods":[51],"have":[52],"been":[53],"recently":[54],"proposed.":[55],"Unfortunately,":[56],"they":[57],"hardly":[58],"generalize":[59],"audios":[62],"generated":[63],"by":[64,89],"never":[66],"seen":[67],"the":[69,98,102,111],"training":[70],"phase,":[71],"which":[72],"makes":[73],"them":[74],"unfit":[75],"face":[77],"real-world":[78],"scenarios.":[79],"In":[80],"this":[81,87],"work,":[82],"we":[83],"aim":[84],"at":[85],"overcoming":[86],"issue":[88],"proposing":[90],"new":[92],"approach":[94,125],"leverages":[96],"only":[97,115],"biometric":[99],"characteristics":[100],"speaker,":[103],"with":[104],"no":[105],"reference":[106],"specific":[108],"manipulations.":[109],"Since":[110],"detector":[112],"is":[113,120],"trained":[114],"on":[116,130,140],"real":[117],"data,":[118],"generalization":[119,149],"automatically":[121],"ensured.":[122],"The":[123],"proposed":[124],"can":[126],"be":[127],"implemented":[128],"based":[129],"off-the-shelf":[131],"speaker":[132],"verification":[133],"tools.":[134],"We":[135],"test":[136,143],"several":[137],"solutions":[139],"three":[141],"popular":[142],"sets,":[144],"obtaining":[145],"good":[146],"performance,":[147],"high":[148,152],"ability,":[150],"robustness":[153],"audio":[155],"impairment.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}