{"id":"https://openalex.org/W4386185355","doi":"https://doi.org/10.48550/arxiv.2308.12734","title":"Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion","display_name":"Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion","publication_year":2023,"publication_date":"2023-08-24","ids":{"openalex":"https://openalex.org/W4386185355","doi":"https://doi.org/10.48550/arxiv.2308.12734"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2308.12734","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.12734","pdf_url":"https://arxiv.org/pdf/2308.12734","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.12734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080362193","display_name":"Jordan J. Bird","orcid":"https://orcid.org/0000-0002-9858-1231","observed_orcids":["https://orcid.org/0000-0002-9858-1231"]},"institutions":[{"id":"https://openalex.org/I52590639","display_name":"Nottingham Trent University","ror":"https://ror.org/04xyxjd90","country_code":"GB","type":"education","lineage":["https://openalex.org/I52590639"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bird, Jordan J.","raw_affiliation_strings":["Nottingham Trent University Nottingham , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nottingham Trent University Nottingham , UK","institution_ids":["https://openalex.org/I52590639"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006193695","display_name":"Ahmad Lotfi","orcid":"https://orcid.org/0000-0002-5139-6565","observed_orcids":["https://orcid.org/0000-0002-5139-6565","https://orcid.org/0000-0001-9012-7723"]},"institutions":[{"id":"https://openalex.org/I52590639","display_name":"Nottingham Trent University","ror":"https://ror.org/04xyxjd90","country_code":"GB","type":"education","lineage":["https://openalex.org/I52590639"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lotfi, Ahmad","raw_affiliation_strings":["Nottingham Trent University Nottingham , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nottingham Trent University Nottingham , UK","institution_ids":["https://openalex.org/I52590639"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52590639"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":55,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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":0.001500000013038516,"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":0.0012000000569969416,"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/voice-cloning","display_name":"voice cloning","score":0.6520000100135803},{"id":"https://openalex.org/keywords/extreme-gradient-boosting","display_name":"extreme gradient boosting","score":0.7319999933242798},{"id":"https://openalex.org/keywords/speech-forensics","display_name":"speech forensics","score":0.503000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007034063339233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6426976919174194},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5364865064620972},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5104442834854126},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5020797252655029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4616718292236328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3605380654335022},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3246001601219177},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1618761122226715}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2308.12734","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.12734","pdf_url":"https://arxiv.org/pdf/2308.12734","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":"doi:10.48550/arxiv.2308.12734","doi":"https://doi.org/10.48550/arxiv.2308.12734","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.12734","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:2308.12734","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.12734","pdf_url":"https://arxiv.org/pdf/2308.12734","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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386185355.pdf","grobid_xml":"https://content.openalex.org/works/W4386185355.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2963609956"],"related_works":["https://openalex.org/W7120127214","https://openalex.org/W4394910569","https://openalex.org/W7127567485","https://openalex.org/W6893166067","https://openalex.org/W7152666347","https://openalex.org/W4416925377","https://openalex.org/W4408749908","https://openalex.org/W7126061192","https://openalex.org/W4391940596","https://openalex.org/W7162408132"],"abstract_inverted_index":{"There":[0],"are":[1,115],"growing":[2],"implications":[3],"surrounding":[4],"generative":[5],"AI":[6,191],"in":[7,67,167],"the":[8,58,62,98,129,134,150],"speech":[9,51,74,81,99,166,192],"domain":[10],"that":[11,113,149],"enable":[12],"voice":[13,17],"cloning":[14],"and":[15,31,38,79,163],"real-time":[16,47],"conversion":[18],"from":[19,75],"one":[20,84,174],"individual":[21,138],"to":[22,34,83,127],"another.":[23],"This":[24],"technology":[25],"poses":[26],"a":[27,92],"significant":[28],"ethical":[29],"threat":[30],"could":[32],"lead":[33],"breaches":[35],"of":[36,49,71,96,106,131,136,161,176],"privacy":[37],"misrepresentation,":[39],"thus":[40],"there":[41,114],"is":[42,65,100,121,147,184],"an":[43,157],"urgent":[44],"need":[45],"for":[46,52,123,181,187],"detection":[48],"AI-generated":[50],"DeepFake":[53],"Voice":[54,88],"Conversion.":[55,89],"To":[56],"address":[57],"above":[59],"emerging":[60],"issues,":[61],"DEEP-VOICE":[63],"dataset":[64],"generated":[66,180],"this":[68,182],"study,":[69],"comprised":[70],"real":[72,101],"human":[73],"eight":[76],"well-known":[77],"figures":[78],"their":[80],"converted":[82],"another":[85],"using":[86],"Retrieval-based":[87],"Presenting":[90],"as":[91],"binary":[93],"classification":[94,159],"problem":[95],"whether":[97],"or":[102],"AI-generated,":[103],"statistical":[104],"analysis":[105],"temporal":[107],"audio":[108],"features":[109],"through":[110],"t-testing":[111],"reveals":[112],"significantly":[116],"different":[117],"distributions.":[118],"Hyperparameter":[119],"optimisation":[120],"implemented":[122],"machine":[124,139],"learning":[125,140],"models":[126,141],"identify":[128],"source":[130],"speech.":[132,177],"Following":[133],"training":[135],"208":[137],"over":[142],"10-fold":[143],"cross":[144],"validation,":[145],"it":[146],"found":[148],"Extreme":[151],"Gradient":[152],"Boosting":[153],"model":[154],"can":[155,164],"achieve":[156],"average":[158],"accuracy":[160],"99.3%":[162],"classify":[165],"real-time,":[168],"at":[169],"around":[170],"0.004":[171],"milliseconds":[172],"given":[173],"second":[175],"All":[178],"data":[179],"study":[183],"released":[185],"publicly":[186],"future":[188],"research":[189],"on":[190],"detection.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":12}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-08-26T00:00:00"}