{"id":"https://openalex.org/W4405845326","doi":"https://doi.org/10.1109/apccas62602.2024.10808404","title":"Detecting Speech Deepfakes through Improved Speech Features and Cost Functions","display_name":"Detecting Speech Deepfakes through Improved Speech Features and Cost Functions","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405845326","doi":"https://doi.org/10.1109/apccas62602.2024.10808404"},"language":"en","primary_location":{"id":"doi:10.1109/apccas62602.2024.10808404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas62602.2024.10808404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","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/A5034641497","display_name":"Oscal Tzyh-Chiang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Oscal Tzyh-Chiang Chen","raw_affiliation_strings":["National Chung Cheng University,Department of Electrical Engineering,Chiayi,Taiwan,621"],"affiliations":[{"raw_affiliation_string":"National Chung Cheng University,Department of Electrical Engineering,Chiayi,Taiwan,621","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109008030","display_name":"Y.F. Hsu","orcid":"https://orcid.org/0009-0002-0014-4832"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yun-Chia Hsu","raw_affiliation_strings":["National Chung Cheng University,Department of Electrical Engineering,Chiayi,Taiwan,621"],"affiliations":[{"raw_affiliation_string":"National Chung Cheng University,Department of Electrical Engineering,Chiayi,Taiwan,621","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101626594","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0002-7698-3117"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tun-Sheng Yang","raw_affiliation_strings":["National Chung Cheng University,Department of Electrical Engineering,Chiayi,Taiwan,621"],"affiliations":[{"raw_affiliation_string":"National Chung Cheng University,Department of Electrical Engineering,Chiayi,Taiwan,621","institution_ids":["https://openalex.org/I148099254"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034641497"],"corresponding_institution_ids":["https://openalex.org/I148099254"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21686906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9865999817848206,"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":0.9865999817848206,"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":0.9775999784469604,"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":0.9241999983787537,"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/speech-recognition","display_name":"Speech recognition","score":0.7061581611633301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6797968149185181},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4728444218635559},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43967074155807495},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4304627478122711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3543473184108734},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33811384439468384}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7061581611633301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797968149185181},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4728444218635559},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43967074155807495},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4304627478122711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3543473184108734},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33811384439468384}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apccas62602.2024.10808404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas62602.2024.10808404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2936802426","https://openalex.org/W3026777299","https://openalex.org/W3127781933","https://openalex.org/W3161011913","https://openalex.org/W3170179936","https://openalex.org/W3197134965","https://openalex.org/W3198123200","https://openalex.org/W3198486673","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W4205137415","https://openalex.org/W4205679927","https://openalex.org/W4312736272","https://openalex.org/W4372347465","https://openalex.org/W6776700526","https://openalex.org/W6798697749"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351","https://openalex.org/W596245619"],"abstract_inverted_index":{"Due":[0],"to":[1,12,21],"the":[2,30,50,54,64,75,89,97,103,133,138,158,162,169,173,177],"rapid":[3],"development":[4],"of":[5,33,53,66,77,91,106,147,153,172,179],"artificial":[6],"intelligence,":[7],"deepfakes":[8],"have":[9],"given":[10],"rise":[11],"malicious":[13],"individuals":[14],"exploiting":[15],"voice":[16,180],"manipulation":[17],"as":[18],"a":[19,67],"means":[20],"deceive":[22],"unsuspecting":[23],"victims.":[24],"In":[25],"this":[26,110],"study,":[27],"we":[28],"address":[29],"crucial":[31],"task":[32],"defining":[34],"acoustic":[35],"feature":[36,98],"parameters":[37],"suited":[38],"for":[39],"capturing":[40],"both":[41],"breathing":[42],"sounds":[43],"and":[44,93,124,150],"low-frequency":[45],"burst":[46],"characteristics,":[47],"achieved":[48],"through":[49],"meticulous":[51],"configuration":[52],"constant":[55],"Q":[56],"transform.":[57],"The":[58],"proposed":[59,139,174],"model":[60,140,175],"is":[61],"constructed":[62],"upon":[63],"foundation":[65],"multi-group":[68],"channel-wise":[69],"gated":[70],"Res2Net-50":[71],"architecture,":[72],"complemented":[73],"by":[74,117],"incorporation":[76],"three":[78],"refined":[79],"highway":[80],"units":[81],"equipped":[82],"with":[83,128],"residual":[84],"connections.":[85],"To":[86],"effectively":[87],"separate":[88],"distributions":[90],"positive":[92],"negative":[94],"samples":[95],"within":[96,161],"space,":[99],"we\u2019ve":[100],"ingeniously":[101],"tailored":[102],"cost":[104,115],"function":[105,116],"one-class":[107,119,126],"learning.":[108],"Furthermore,":[109],"study":[111],"introduces":[112],"an":[113,142],"improved":[114],"synergizing":[118],"learning,":[120,123],"supervised":[121],"contrastive":[122],"modified":[125],"learning":[127],"learnable":[129],"ratios.":[130],"By":[131],"using":[132],"ASVspoof":[134],"2019":[135],"LA":[136],"dataset,":[137],"achieves":[141],"Equal":[143],"Error":[144],"Rate":[145],"(EER)":[146],"0.6":[148],"8%":[149],"min":[151],"t-DCF":[152],"0.0194":[154],"in":[155,176],"testing,":[156],"surpassing":[157],"conventional":[159],"models":[160],"single":[163],"system":[164],"category.":[165],"These":[166],"results":[167],"highlight":[168],"superior":[170],"performance":[171],"realm":[178],"deception":[181],"detection.":[182]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}