{"id":"https://openalex.org/W7125894295","doi":"https://doi.org/10.1109/smc58881.2025.11343240","title":"DeepSick: Deceiving Voice-Based Diagnostic Models with Synthetic Multilingual Pathological Speech Signals","display_name":"DeepSick: Deceiving Voice-Based Diagnostic Models with Synthetic Multilingual Pathological Speech Signals","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125894295","doi":"https://doi.org/10.1109/smc58881.2025.11343240"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124124940","display_name":"Yi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yi Zhu","raw_affiliation_strings":["Institut National de la Recherche Scientifique (INRS-EMT)"],"affiliations":[{"raw_affiliation_string":"Institut National de la Recherche Scientifique (INRS-EMT)","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055388091","display_name":"Alan Davoust","orcid":"https://orcid.org/0000-0002-3423-0942"},"institutions":[{"id":"https://openalex.org/I33217400","display_name":"Universit\u00e9 du Qu\u00e9bec en Outaouais","ror":"https://ror.org/011pqxa69","country_code":"CA","type":"education","lineage":["https://openalex.org/I33217400","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alan Davoust","raw_affiliation_strings":["University of Quebec in Outaouais"],"affiliations":[{"raw_affiliation_string":"University of Quebec in Outaouais","institution_ids":["https://openalex.org/I33217400"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112847522","display_name":"Tiago Henrik Falk","orcid":null},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tiago H. Falk","raw_affiliation_strings":["Institut National de la Recherche Scientifique (INRS-EMT)"],"affiliations":[{"raw_affiliation_string":"Institut National de la Recherche Scientifique (INRS-EMT)","institution_ids":["https://openalex.org/I39481719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5124124940"],"corresponding_institution_ids":["https://openalex.org/I39481719"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69737713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.45500001311302185,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.45500001311302185,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.11919999867677689,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.1023000031709671,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5515000224113464},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48669999837875366},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.484499990940094},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45730000734329224},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.45320001244544983},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43149998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6675999760627747},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5515000224113464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.535099983215332},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.484499990940094},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3871999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C207886595","wikidata":"https://www.wikidata.org/wiki/Q1456138","display_name":"Pathological","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2888000011444092}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4541049599647522,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2011378162","https://openalex.org/W2085662862","https://openalex.org/W2089109585","https://openalex.org/W2239141610","https://openalex.org/W2281740710","https://openalex.org/W2890964092","https://openalex.org/W2936802426","https://openalex.org/W2963701934","https://openalex.org/W3024869864","https://openalex.org/W3156027765","https://openalex.org/W3196475561","https://openalex.org/W3196831814","https://openalex.org/W3209984917","https://openalex.org/W3211424380","https://openalex.org/W4200585215","https://openalex.org/W4225276331","https://openalex.org/W4225288540","https://openalex.org/W4225527248","https://openalex.org/W4283160981","https://openalex.org/W4308216138","https://openalex.org/W4323567384","https://openalex.org/W4372260248","https://openalex.org/W4372338196","https://openalex.org/W4381198892","https://openalex.org/W4391604988","https://openalex.org/W4394938944","https://openalex.org/W4402215565","https://openalex.org/W4402351686"],"related_works":[],"abstract_inverted_index":{"Voice-based":[0],"diagnostic":[1,37,45,81,170],"systems":[2,171],"offer":[3],"a":[4,63,153],"scalable":[5],"solution":[6],"for":[7],"remote":[8,168],"health":[9],"assessment.":[10],"However,":[11],"recent":[12],"advances":[13],"in":[14,75],"generative":[15,64],"voice":[16,23,112,131,169],"models":[17,48,114],"may":[18],"enable":[19],"malicious":[20],"manipulation":[21],"of":[22,44,52],"samples":[24],"to":[25,36,49,61,66,167],"simulate":[26],"or":[27],"conceal":[28],"disease-related":[29],"speech":[30,121,137],"characteristics,":[31],"which":[32,74],"poses":[33],"new":[34],"risks":[35],"systems.":[38,82],"This":[39,158],"paper":[40],"investigates":[41],"the":[42,94],"vulnerability":[43],"and":[46,71,90,118],"detection":[47,113],"such":[50],"types":[51],"\"deepfake\"":[53],"attacks.":[54],"We":[55,106],"show":[56,127],"that":[57,128,172],"it":[58],"is":[59,85],"possible":[60],"train":[62],"model":[65],"convert":[67],"between":[68],"healthy":[69,136],"voices":[70,150],"pathological":[72,101,120,143,149],"ones,":[73],"turn,":[76],"can":[77,96],"successfully":[78],"deceive":[79],"existing":[80],"Here,":[83],"focus":[84],"placed":[86],"on":[87,115,135,141,163],"COVID-19":[88],"infection":[89],"respiratory":[91],"abnormalities,":[92],"but":[93],"method":[95],"be":[97],"applied":[98],"across":[99],"different":[100],"conditions":[102],"affecting":[103],"vocal":[104],"attributes.":[105],"also":[107],"benchmark":[108],"four":[109],"state-of-the-art":[110],"synthesized":[111],"both":[116],"real":[117,148],"generated":[119,142],"from":[122],"three":[123],"datasets.":[124],"Our":[125],"results":[126],"current":[129],"synthetic":[130],"detectors,":[132],"typically":[133],"trained":[134],"data,":[138],"perform":[139],"poorly":[140],"samples.":[144],"While":[145],"fine-tuning":[146],"with":[147],"improves":[151],"detection,":[152],"substantial":[154],"performance":[155],"gap":[156],"remains.":[157],"work":[159],"provides":[160],"initial":[161],"insights":[162],"an":[164],"emerging":[165],"threat":[166],"needs":[173],"further":[174],"work.":[175]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-29T00:00:00"}