{"id":"https://openalex.org/W4409156546","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10942853","title":"Improving Fairness in Synthetic Speech Detectors","display_name":"Improving Fairness in Synthetic Speech Detectors","publication_year":2024,"publication_date":"2024-10-27","ids":{"openalex":"https://openalex.org/W4409156546","doi":"https://doi.org/10.1109/ieeeconf60004.2024.10942853"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf60004.2024.10942853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10942853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","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/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":true,"raw_author_name":"Amit Kumar Singh Yadav","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","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":false,"raw_author_name":"Kratika Bhagtani","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,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":["Informazione e Bioingegneria, Politecnico di Milano,Dipartimento di Elettronica,Milano,Italy"],"affiliations":[{"raw_affiliation_string":"Informazione e Bioingegneria, Politecnico di Milano,Dipartimento di Elettronica,Milano,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,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),West Lafayette,Indiana,USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055125973"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26860356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"362","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8345000147819519,"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":0.8345000147819519,"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/computer-science","display_name":"Computer science","score":0.6286659240722656},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5675637722015381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4188601076602936},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14972758293151855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6286659240722656},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5675637722015381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4188601076602936},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14972758293151855}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf60004.2024.10942853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf60004.2024.10942853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 58th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2062826588","https://openalex.org/W2103869314","https://openalex.org/W2295634712","https://openalex.org/W2590129515","https://openalex.org/W2936802426","https://openalex.org/W2972465261","https://openalex.org/W3140832216","https://openalex.org/W3161011913","https://openalex.org/W3161639065","https://openalex.org/W3170179936","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W3216567096","https://openalex.org/W4226318763","https://openalex.org/W4286750742","https://openalex.org/W4313306150","https://openalex.org/W4362684594","https://openalex.org/W4392903649","https://openalex.org/W4392942164","https://openalex.org/W4392943326","https://openalex.org/W4393258950","https://openalex.org/W4393379886","https://openalex.org/W4394593221","https://openalex.org/W4413493729","https://openalex.org/W6754235555","https://openalex.org/W6780218876","https://openalex.org/W6794996812","https://openalex.org/W6797951164","https://openalex.org/W6811340444","https://openalex.org/W6843931401","https://openalex.org/W6853768149","https://openalex.org/W6854315863"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2366906938"],"abstract_inverted_index":{"Many":[0],"methods":[1],"have":[2,50,70,157],"been":[3],"proposed":[4],"which":[5],"can":[6,49,57,100],"effectively":[7],"detect":[8],"synthetic":[9,83,132],"speech.":[10,148],"However,":[11],"a":[12,21,109],"recent":[13],"study":[14],"demonstrates":[15],"that":[16,113,152],"they":[17],"exhibit":[18],"bias":[19,48,68,74,137,162],"and":[20,53,56,84,90,125,135,185],"higher":[22],"false":[23],"positive":[24],"rate":[25],"for":[26,79,97],"bona":[27,85,145],"fide":[28,86,146],"speech":[29,87,133,140],"from":[30,72],"speakers":[31],"with":[32,88,155],"stuttering":[33,119,139,147],"speech-impairment":[34],"as":[35,46],"compared":[36,193],"to":[37,93,164,172,194],"fluent":[38],"speakers.":[39],"This":[40,67],"limits":[41],"deploy-ment":[42],"of":[43,61,111,118,177],"these":[44,80],"detectors,":[45],"this":[47,104],"significant":[51],"societal":[52],"political":[54],"consequences":[55],"erode":[58],"the":[59,73,94],"reputation":[60],"social":[62],"platforms":[63],"using":[64,141],"such":[65],"detectors.":[66,81],"may":[69],"arisen":[71],"in":[75,120,179,187],"training":[76,95],"data":[77],"used":[78],"Creating":[82],"stuttering,":[89],"adding":[91],"it":[92],"set":[96,110],"mitigating":[98],"bias,":[99],"be":[101],"time-consuming.":[102],"In":[103],"work,":[105],"we":[106],"propose":[107],"StutterAug,":[108],"augmentations":[112],"simulate":[114],"three":[115],"major":[116],"types":[117],"speech,":[121],"namely":[122],"repetition,":[123],"prolongation":[124],"blocks.":[126],"We":[127],"test":[128],"StutterAug":[129,156,169],"on":[130,138,158,182,190],"3":[131],"detectors":[134,153,196],"examine":[136],"more":[142],"than":[143],"28K":[144],"Our":[149],"results":[150],"show":[151],"trained":[154,166,197],"average":[159,174],"13%":[160],"less":[161],"relative":[163,175],"detector":[165],"without":[167,198],"StutterAug.":[168,199],"also":[170],"leads":[171],"an":[173],"improvement":[176],"27.96%":[178],"detection":[180],"performance":[181,189],"ASVspoof2019":[183],"dataset":[184,192],"11.27%":[186],"generalization":[188],"In-the-Wild":[191],"baseline":[195]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}