{"id":"https://openalex.org/W7171504625","doi":"https://doi.org/10.1016/j.csl.2026.102037","title":"Robustness in deepfake speech detection: A survey of failure mechanisms including an experimental case study","display_name":"Robustness in deepfake speech detection: A survey of failure mechanisms including an experimental case study","publication_year":2026,"publication_date":"2026-07-28","ids":{"openalex":"https://openalex.org/W7171504625","doi":"https://doi.org/10.1016/j.csl.2026.102037"},"language":"en","primary_location":{"id":"doi:10.1016/j.csl.2026.102037","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.102037","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.csl.2026.102037","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044013857","display_name":"Harry Maltby","orcid":"https://orcid.org/0000-0003-0142-6575"},"institutions":[{"id":"https://openalex.org/I157227730","display_name":"University of East London","ror":"https://ror.org/057jrqr44","country_code":"GB","type":"education","lineage":["https://openalex.org/I157227730"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Harry Maltby","raw_affiliation_strings":["School of Architecture, Computing and Engineering, University of East London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-0142-6575","affiliations":[{"raw_affiliation_string":"School of Architecture, Computing and Engineering, University of East London, United Kingdom","institution_ids":["https://openalex.org/I157227730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136477236","display_name":"Julie Wall","orcid":null},"institutions":[{"id":"https://openalex.org/I177463362","display_name":"University of West London","ror":"https://ror.org/03e5mzp60","country_code":"GB","type":"education","lineage":["https://openalex.org/I177463362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Julie Wall","raw_affiliation_strings":["University of West London, London, England, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of West London, London, England, United Kingdom","institution_ids":["https://openalex.org/I177463362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044554092","display_name":"Cornelius Glackin","orcid":"https://orcid.org/0000-0001-5114-6403"},"institutions":[{"id":"https://openalex.org/I4210138417","display_name":"Verint Systems (United States)","ror":"https://ror.org/03fqhrc68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138417"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelius Glackin","raw_affiliation_strings":["Verint Systems Inc, England, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Verint Systems Inc, England, United Kingdom","institution_ids":["https://openalex.org/I4210138417"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087019252","display_name":"M. Moniri","orcid":"https://orcid.org/0000-0002-5564-0692"},"institutions":[{"id":"https://openalex.org/I157227730","display_name":"University of East London","ror":"https://ror.org/057jrqr44","country_code":"GB","type":"education","lineage":["https://openalex.org/I157227730"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mansour Moniri","raw_affiliation_strings":["University of East London - Docklands Campus, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East London - Docklands Campus, London, United Kingdom","institution_ids":["https://openalex.org/I157227730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086212451","display_name":"Iwa Salami","orcid":"https://orcid.org/0000-0003-4864-5863"},"institutions":[{"id":"https://openalex.org/I157227730","display_name":"University of East London","ror":"https://ror.org/057jrqr44","country_code":"GB","type":"education","lineage":["https://openalex.org/I157227730"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iwa Salami","raw_affiliation_strings":["University of East London, Royal Docks Business School, London, England, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of East London, Royal Docks Business School, London, England, United Kingdom","institution_ids":["https://openalex.org/I157227730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080712003","display_name":"Letian Li","orcid":"https://orcid.org/0000-0003-0352-8946"},"institutions":[{"id":"https://openalex.org/I4210138417","display_name":"Verint Systems (United States)","ror":"https://ror.org/03fqhrc68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138417"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Letian Li","raw_affiliation_strings":["Verint Systems Inc, England, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Verint Systems Inc, England, United Kingdom","institution_ids":["https://openalex.org/I4210138417"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012466886","display_name":"Nigel Cannings","orcid":"https://orcid.org/0000-0002-5279-3968"},"institutions":[{"id":"https://openalex.org/I4210138417","display_name":"Verint Systems (United States)","ror":"https://ror.org/03fqhrc68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138417"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nigel Cannings","raw_affiliation_strings":["Verint Systems Inc, England, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Verint Systems Inc, England, United Kingdom","institution_ids":["https://openalex.org/I4210138417"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044013857"],"corresponding_institution_ids":["https://openalex.org/I157227730"],"apc_list":{"value":3530,"currency":"USD","value_usd":3530},"apc_paid":{"value":3530,"currency":"USD","value_usd":3530},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8134651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"102","issue":null,"first_page":"102037","last_page":"102037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.41019999980926514,"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":0.41019999980926514,"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":0.14270000159740448,"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":0.09849999845027924,"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/robustness","display_name":"Robustness (evolution)","score":0.8377000093460083},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.5267000198364258},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45890000462532043},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3772999942302704},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.35499998927116394},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.3449999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8906000256538391},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8377000093460083},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4706000089645386},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4169999957084656},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3765999972820282},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35499998927116394},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3449999988079071},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C137726913","wikidata":"https://www.wikidata.org/wiki/Q7353550","display_name":"Robustness testing","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.csl.2026.102037","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.102037","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"},{"id":"pmh:oai:repository.uwl.ac.uk:15273","is_oa":false,"landing_page_url":"https://orcid.org/0000-0001-6714-4867","pdf_url":null,"source":{"id":"https://openalex.org/S4306402477","display_name":"UWL Repository (University of West London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177463362","host_organization_name":"University of West London","host_organization_lineage":["https://openalex.org/I177463362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1016/j.csl.2026.102037","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.102037","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7709100842475891,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2166657701","https://openalex.org/W2176804518","https://openalex.org/W2752782242","https://openalex.org/W2990833974","https://openalex.org/W3026777299","https://openalex.org/W3033711348","https://openalex.org/W3204696009","https://openalex.org/W3207579445","https://openalex.org/W3209059054","https://openalex.org/W3209972423","https://openalex.org/W4220832730","https://openalex.org/W4223915588","https://openalex.org/W4298394324","https://openalex.org/W4298394377","https://openalex.org/W4298397149","https://openalex.org/W4298397801","https://openalex.org/W4298633873","https://openalex.org/W4298635730","https://openalex.org/W4298636010","https://openalex.org/W4377107319","https://openalex.org/W4381198892","https://openalex.org/W4381708595","https://openalex.org/W4381851764","https://openalex.org/W4385483249","https://openalex.org/W4385800847","https://openalex.org/W4385975857","https://openalex.org/W4398186462","https://openalex.org/W4408121400","https://openalex.org/W4408799803"],"related_works":[],"abstract_inverted_index":{"In":[0,51],"recent":[1],"years,":[2],"the":[3,23,66,72,102,128,166,173,257],"emergence":[4],"of":[5,28,116,229,259],"disruptive":[6],"deepfake":[7,117],"technology":[8],"(referring":[9],"here":[10],"to":[11,136,250],"computer-generated":[12],"speech/audio,":[13],"images,":[14],"video":[15],"and":[16,26,45,71,113,143,159,170,188,197,202,211,232,262,275],"text)":[17],"has":[18,98],"raised":[19],"significant":[20],"concerns":[21],"surrounding":[22],"privacy,":[24],"security,":[25],"credibility":[27],"digital":[29],"content.":[30],"Although":[31],"detection":[32],"systems":[33],"report":[34],"high":[35],"benchmark":[36],"performance,":[37],"most":[38],"are":[39,223],"evaluated":[40,171],"on":[41,165,172],"in-domain":[42],"datasets,":[43],"codecs,":[44,82],"generative":[46,79],"models":[47,187],"seen":[48,68],"during":[49,69],"training.":[50],"real":[52],"deployment,":[53],"however,":[54],"detectors":[55,261],"must":[56],"contend":[57],"with":[58,155,226,233,242],"out-of-domain":[59],"instances,":[60],"that":[61,133,182,220,255],"is,":[62],"a":[63,110,152,239],"mismatch":[64],"between":[65],"data":[67],"training":[70],"conditions":[73],"encountered":[74],"in":[75,101],"deployment":[76],"(e.g.,":[77],"unseen":[78],"methods,":[80,125],"unfamiliar":[81],"or":[83],"signals":[84],"degraded":[85],"by":[86],"transmission":[87],"channels).":[88],"Under":[89],"these":[90],"conditions,":[91],"performance":[92,194],"often":[93],"degrades":[94],"sharply.":[95],"While":[96],"robustness":[97,135,183,221],"been":[99],"acknowledged":[100],"literature,":[103],"it":[104],"remains":[105],"underexplored.":[106],"This":[107],"work":[108,247],"presents":[109],"robustness-focused":[111],"survey":[112,241],"experimental":[114,179,244],"study":[115],"speech":[118,162],"detection.":[119],"Rather":[120],"than":[121],"broadly":[122],"cataloguing":[123],"existing":[124],"we":[126,150],"organise":[127],"literature":[129],"around":[130],"three":[131],"factors":[132,254],"influence":[134],"distribution":[137],"shift:":[138],"dataset":[139,198,271],"design,":[140,272],"feature":[141,273],"representations,":[142],"model":[144],"architecture.":[145],"To":[146],"complement":[147],"this":[148,246],"synthesis,":[149],"conduct":[151],"cross-dataset":[153,243],"evaluation":[154,276],"Wav2Vec2,":[156],"HuBERT,":[157],"WavLM,":[158],"Whisper":[160],"self-supervised":[161],"models,":[163],"trained":[164],"ASVspoof":[167,174],"2019":[168],"LA":[169],"2021":[175],"Deepfake":[176],"dataset.":[177],"The":[178],"results":[180],"show":[181],"varies":[184],"considerably":[185],"across":[186,195],"conditions.":[189,280],"HuBERT":[190],"demonstrates":[191],"comparatively":[192],"stable":[193],"codec":[196],"shifts,":[199],"while":[200],"Wav2Vec2":[201],"WavLM":[203],"experience":[204],"substantial":[205],"degradation,":[206],"particularly":[207],"under":[208,277],"MP3-based":[209],"compression":[210],"neural":[212],"vocoder":[213],"synthesis.":[214],"A":[215],"diagnostic":[216],"analysis":[217],"further":[218],"reveals":[219],"failures":[222],"strongly":[224],"associated":[225],"codec-induced":[227],"masking":[228],"synthesis":[230,235],"artefacts":[231],"dataset-dependent":[234],"pipelines.":[236],"By":[237],"combining":[238],"robustness-oriented":[240],"evidence,":[245],"puts":[248],"theory":[249],"practice,":[251],"highlighting":[252],"key":[253],"limit":[256],"generalisation":[258],"current":[260],"outlining":[263],"practical":[264],"directions":[265],"for":[266],"improving":[267],"robustness,":[268],"including":[269],"diversified":[270],"fusion,":[274],"realistic":[278],"cross-domain":[279]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-29T00:00:00"}