{"id":"https://openalex.org/W4390489170","doi":"https://doi.org/10.1109/wifs58808.2023.10374911","title":"Single and Multi-Speaker Cloned Voice Detection: From Perceptual to Learned Features","display_name":"Single and Multi-Speaker Cloned Voice Detection: From Perceptual to Learned Features","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4390489170","doi":"https://doi.org/10.1109/wifs58808.2023.10374911"},"language":"en","primary_location":{"id":"doi:10.1109/wifs58808.2023.10374911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wifs58808.2023.10374911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Workshop on Information Forensics and Security (WIFS)","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/A5061895862","display_name":"Sarah Barrington","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sarah Barrington","raw_affiliation_strings":["School of Information","University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"School of Information","institution_ids":[]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111010514","display_name":"Romit Barua","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Romit Barua","raw_affiliation_strings":["School of Information","University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"School of Information","institution_ids":[]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092491476","display_name":"Gautham Koorma","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautham Koorma","raw_affiliation_strings":["School of Information","University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"School of Information","institution_ids":[]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102969395","display_name":"Hany Farid","orcid":"https://orcid.org/0000-0002-6095-8339"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hany Farid","raw_affiliation_strings":["School of Information","University of California, Berkeley, Berkeley, CA, USA","Electrical Engineering and Computer Sciences"],"affiliations":[{"raw_affiliation_string":"School of Information","institution_ids":[]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Electrical Engineering and Computer Sciences","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061895862"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":3.4691,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.93900322,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9965999722480774,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/interpretability","display_name":"Interpretability","score":0.8845881819725037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7394975423812866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6383008360862732},{"id":"https://openalex.org/keywords/disinformation","display_name":"Disinformation","score":0.59259432554245},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.5289961099624634},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.514462947845459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4914058446884155},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48370248079299927},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4436336159706116},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4430016875267029},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43182283639907837},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4147113561630249},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3896715044975281},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3261953592300415},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.11743667721748352},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07837340235710144}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8845881819725037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394975423812866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6383008360862732},{"id":"https://openalex.org/C2776552730","wikidata":"https://www.wikidata.org/wiki/Q189656","display_name":"Disinformation","level":3,"score":0.59259432554245},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5289961099624634},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.514462947845459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4914058446884155},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48370248079299927},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4436336159706116},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4430016875267029},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43182283639907837},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4147113561630249},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3896715044975281},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3261953592300415},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.11743667721748352},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07837340235710144},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wifs58808.2023.10374911","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wifs58808.2023.10374911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Workshop on Information Forensics and Security (WIFS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320333609","display_name":"Center for Long-Term Cybersecurity, University of California Berkeley","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W2053019885","https://openalex.org/W2085662862","https://openalex.org/W2090861223","https://openalex.org/W2138878452","https://openalex.org/W2350778671","https://openalex.org/W2605311049","https://openalex.org/W2889361425","https://openalex.org/W2982436869","https://openalex.org/W3098557217","https://openalex.org/W3163596559","https://openalex.org/W3205878676","https://openalex.org/W4221138880","https://openalex.org/W4225420087","https://openalex.org/W4226246616","https://openalex.org/W4292957223","https://openalex.org/W4297841787","https://openalex.org/W4298394324","https://openalex.org/W4309825539","https://openalex.org/W4311737082","https://openalex.org/W4385466335","https://openalex.org/W6805710207","https://openalex.org/W6999741410"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2749720872","https://openalex.org/W2186375278","https://openalex.org/W2793748347","https://openalex.org/W4229940372","https://openalex.org/W4250904811","https://openalex.org/W2104528589","https://openalex.org/W2155047054","https://openalex.org/W2002404399"],"abstract_inverted_index":{"Synthetic-voice":[0],"cloning":[1],"technologies":[2],"have":[3],"seen":[4],"significant":[5],"advances":[6],"in":[7,62],"recent":[8],"years,":[9],"giving":[10],"rise":[11],"to":[12,24,32,53,77,128],"a":[13,46,49,55,101],"range":[14],"of":[15,95],"potential":[16],"harms.":[17],"From":[18],"small-":[19],"and":[20,35,81,105,122,124],"large-scale":[21],"financial":[22],"fraud":[23],"disinformation":[25],"campaigns,":[26],"the":[27,93],"need":[28],"for":[29,44],"reliable":[30],"methods":[31],"differentiate":[33],"real":[34,47],"synthesized":[36],"voices":[37],"is":[38],"imperative.":[39],"We":[40,91],"describe":[41],"three":[42,59],"techniques":[43],"differentiating":[45],"from":[48],"cloned":[50],"voice":[51,104],"designed":[52],"impersonate":[54],"specific":[56],"person.":[57],"These":[58],"approaches":[60,97],"differ":[61],"their":[63],"feature":[64],"extraction":[65],"stage":[66],"with":[67],"low-dimensional":[68],"perceptual":[69],"features":[70,84,113],"offering":[71,85],"high":[72],"interpretability":[73,87],"but":[74,88],"lower":[75],"accuracy,":[76],"generic":[78],"spectral":[79],"features,":[80],"end-to-end":[82],"learned":[83,112],"less":[86],"higher":[89],"accuracy.":[90],"show":[92],"efficacy":[94],"these":[96],"when":[98,106],"trained":[99,107],"on":[100,108],"single":[102],"speaker's":[103],"multiple":[109],"voices.":[110],"The":[111],"consistently":[114],"yield":[115],"an":[116],"equal":[117],"error":[118],"rate":[119],"between":[120],"0%":[121],"4%,":[123],"are":[125],"reasonably":[126],"robust":[127],"adversarial":[129],"laundering.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}