{"id":"https://openalex.org/W4409156579","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10942913","title":"Comparative Analysis of ASR Methods for Speech Deepfake Detection","display_name":"Comparative Analysis of ASR Methods for Speech Deepfake Detection","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4409156579","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10942913"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf60004.2024.10942913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10942913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-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/A5033038241","display_name":"Davide Salvi","orcid":"https://orcid.org/0000-0002-5163-3364"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Davide Salvi","raw_affiliation_strings":["Politecnico di Milano,Image and Sound Processing Lab (ISPL),Milano,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Image and Sound Processing Lab (ISPL),Milano,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055125973","display_name":"Amit Kumar Singh Yadav","orcid":"https://orcid.org/0000-0001-6464-7688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amit Kumar Singh Yadav","raw_affiliation_strings":["Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA"],"affiliations":[{"raw_affiliation_string":"Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022400610","display_name":"Kratika Bhagtani","orcid":"https://orcid.org/0000-0001-7399-4876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kratika Bhagtani","raw_affiliation_strings":["Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA"],"affiliations":[{"raw_affiliation_string":"Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116925620","display_name":"Viola Negronil","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Viola Negronil","raw_affiliation_strings":["Politecnico di Milano,Image and Sound Processing Lab (ISPL),Milano,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Image and Sound Processing Lab (ISPL),Milano,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051370303","display_name":"Paolo Bestagini","orcid":"https://orcid.org/0000-0003-0406-0222"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Bestagini","raw_affiliation_strings":["Politecnico di Milano,Image and Sound Processing Lab (ISPL),Milano,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Image and Sound Processing Lab (ISPL),Milano,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089688702","display_name":"Edward J. Delp","orcid":"https://orcid.org/0000-0002-2909-7323"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward J. Delp","raw_affiliation_strings":["Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA"],"affiliations":[{"raw_affiliation_string":"Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5033038241"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":1.4504,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85928066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"329","last_page":"333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9771000146865845,"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":0.9771000146865845,"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":0.9714000225067139,"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":0.7249851226806641},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5494049787521362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37772446870803833},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35215306282043457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249851226806641},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5494049787521362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37772446870803833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35215306282043457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ieeeconf60004.2024.10942913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10942913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1287238","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1287238","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1579019551","display_name":null,"funder_award_id":"FA8750-20-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2936802426","https://openalex.org/W2989571531","https://openalex.org/W3197358873","https://openalex.org/W3201773091","https://openalex.org/W4213187648","https://openalex.org/W4225527248","https://openalex.org/W4292828964","https://openalex.org/W4294975742","https://openalex.org/W4297841787","https://openalex.org/W4311591887","https://openalex.org/W4372346093","https://openalex.org/W4381708595","https://openalex.org/W4385466335","https://openalex.org/W4385800847","https://openalex.org/W4385823150","https://openalex.org/W4392902854","https://openalex.org/W4392910532","https://openalex.org/W4392911119","https://openalex.org/W4392931772","https://openalex.org/W4402402534","https://openalex.org/W4402917138","https://openalex.org/W6780218876","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"techniques":[1],"for":[2,16,137,189],"speech":[3,31,66,83,107,139,171,195],"deepfake":[4,39,67,84,108,140,172,196],"detection":[5,109,141],"often":[6],"rely":[7],"on":[8],"pre-trained":[9,44,126],"self-supervised":[10,127],"models.":[11],"These":[12,143],"systems,":[13],"initially":[14],"developed":[15],"Automatic":[17],"Speech":[18],"Recognition":[19],"(ASR),":[20],"have":[21,145],"proved":[22],"their":[23],"ability":[24],"to":[25,53,63,105],"offer":[26,186],"a":[27,64,77,119],"meaningful":[28],"representation":[29],"of":[30,154,192],"signals,":[32],"which":[33,59],"can":[34],"benefit":[35],"various":[36],"tasks,":[37],"including":[38],"detection.":[40,85,173],"In":[41,111],"this":[42,74,87,112,116],"context,":[43],"models":[45,144],"serve":[46],"as":[47],"feature":[48],"extractors":[49],"and":[50,82,94,131,134,156,185],"are":[51,60],"used":[52],"extract":[54],"embeddings":[55],"from":[56],"input":[57],"speech,":[58],"then":[61],"fed":[62],"binary":[65],"detector.":[68],"The":[69],"remarkable":[70],"accuracy":[71],"achieved":[72],"through":[73,118],"approach":[75],"underscores":[76],"potential":[78],"relationship":[79,180],"between":[80,181],"ASR":[81,103,128,158,166],"However,":[86],"connection":[88],"is":[89],"not":[90,97],"yet":[91],"entirely":[92],"clear,":[93],"we":[95,114],"do":[96],"know":[98],"whether":[99,162],"improved":[100],"performance":[101,163],"in":[102,148,165,170],"corresponds":[104],"higher":[106],"capabilities.":[110],"paper,":[113],"address":[115],"question":[117],"systematic":[120],"analysis.":[121],"We":[122,160],"consider":[123],"two":[124,183],"different":[125],"models,":[129],"Whisper":[130],"Wav2Vec":[132],"2.0,":[133],"adapt":[135],"them":[136],"the":[138,179,190],"task.":[142],"been":[146],"released":[147],"multiple":[149],"versions,":[150],"with":[151,168],"increasing":[152],"number":[153],"parameters":[155],"enhanced":[157],"performance.":[159],"investigate":[161],"improvements":[164,169],"correlate":[167],"Our":[174],"results":[175],"provide":[176],"insights":[177],"into":[178],"these":[182],"tasks":[184],"valuable":[187],"guidance":[188],"development":[191],"more":[193],"effective":[194],"detectors.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}