{"id":"https://openalex.org/W4399556715","doi":"https://doi.org/10.1145/3658664.3659658","title":"Are Recent Deepfake Speech Generators Detectable?","display_name":"Are Recent Deepfake Speech Generators Detectable?","publication_year":2024,"publication_date":"2024-06-12","ids":{"openalex":"https://openalex.org/W4399556715","doi":"https://doi.org/10.1145/3658664.3659658"},"language":"en","primary_location":{"id":"doi:10.1145/3658664.3659658","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658664.3659658","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3658664.3659658","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022400610","display_name":"Kratika Bhagtani","orcid":"https://orcid.org/0000-0001-7399-4876"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kratika Bhagtani","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055125973","display_name":"Amit Kumar Singh Yadav","orcid":"https://orcid.org/0000-0001-6464-7688"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Kumar Singh Yadav","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"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":["Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, 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":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward J. Delp","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022400610"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":2.4117,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89984297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"277","last_page":"282"},"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":0.9998999834060669,"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":0.9991999864578247,"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":0.6831070184707642},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3399566411972046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6831070184707642},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3399566411972046}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658664.3659658","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658664.3659658","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3658664.3659658","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658664.3659658","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1498436455","https://openalex.org/W2097117768","https://openalex.org/W2103869314","https://openalex.org/W2194775991","https://openalex.org/W2590129515","https://openalex.org/W2593116425","https://openalex.org/W3033711348","https://openalex.org/W3092028330","https://openalex.org/W3161011913","https://openalex.org/W3168527213","https://openalex.org/W3169317518","https://openalex.org/W3170179936","https://openalex.org/W3213515747","https://openalex.org/W3216567096","https://openalex.org/W4225527248","https://openalex.org/W4226063663","https://openalex.org/W4294975742","https://openalex.org/W4304099317","https://openalex.org/W4363671619","https://openalex.org/W4365512576","https://openalex.org/W4372263908","https://openalex.org/W4378767299","https://openalex.org/W4381198892","https://openalex.org/W4384389564","https://openalex.org/W4392943326","https://openalex.org/W4393372892","https://openalex.org/W4394947121"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"methods":[2,27,55],"can":[3,18,112],"generate":[4],"high-quality":[5,68],"synthetic":[6,43,78,83,107,134],"speech":[7,17,25,44,49,69,79,84,108,135],"which":[8,31,59],"is":[9],"perceptually":[10],"indistinguishable":[11],"from":[12,45,117],"real":[13,126],"human":[14],"speech.":[15,127],"Synthetic":[16,24],"be":[19],"maliciously":[20],"used":[21],"for":[22,67,86],"fraud.":[23],"detection":[26],"have":[28,56,98],"been":[29,57],"proposed":[30,58],"perform":[32],"well":[33,139],"on":[34,140,144],"ASVspoof2019":[35,142],"and":[36,63,148],"ASVspoof2021":[37],"Datasets.":[38],"These":[39,110],"datasets":[40],"consist":[41],"of":[42,94,124,131],"conventional":[46],"neural":[47],"network":[48],"generators.":[50,109],"Recently,":[51],"many":[52],"voice":[53,116],"cloning":[54],"use":[60],"diffusion":[61,105],"models":[62],"generative":[64],"adversarial":[65],"networks":[66],"synthesis.":[70],"In":[71],"this":[72,100,145],"work,":[73],"we":[74],"present":[75],"a":[76,91,114,121],"new":[77,146],"dataset":[80,101],"containing":[81],"25,000":[82],"signals":[85],"11":[87],"distinct":[88],"speakers,":[89],"with":[90],"total":[92],"duration":[93],"52":[95],"hours.":[96],"We":[97,128],"developed":[99],"using":[102,119,152],"5":[103],"recent":[104],"model-based":[106],"generators":[111],"clone":[113],"speaker's":[115],"text":[118],"only":[120],"few":[122],"minutes":[123],"their":[125,150],"evaluate":[129],"6":[130],"the":[132,141],"best":[133],"detectors":[136],"that":[137],"work":[138],"Dataset":[143],"dataset,":[147],"demonstrate":[149],"performance":[151],"Equal":[153],"Error":[154],"Rate":[155],"(EER).":[156]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}