{"id":"https://openalex.org/W4298635730","doi":"https://doi.org/10.1145/3552466.3556526","title":"Audio Deepfake Detection Based on a Combination of F0 Information and Real Plus Imaginary Spectrogram Features","display_name":"Audio Deepfake Detection Based on a Combination of F0 Information and Real Plus Imaginary Spectrogram Features","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4298635730","doi":"https://doi.org/10.1145/3552466.3556526"},"language":"en","primary_location":{"id":"doi:10.1145/3552466.3556526","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3552466.3556526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102858419","display_name":"Jun Xue","orcid":"https://orcid.org/0009-0001-8465-011X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xue","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026466982","display_name":"Zhao Lv","orcid":"https://orcid.org/0000-0003-4530-4422"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Lv","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070266277","display_name":"Chengshi Zheng","orcid":"https://orcid.org/0000-0001-5656-994X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengshi Zheng","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Qiyuan Laboratory, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qiyuan Laboratory, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091727143","display_name":"Minmin Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]},{"id":"https://openalex.org/I4210139553","display_name":"Research Institute of Highway","ror":"https://ror.org/0335kqk33","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216","https://openalex.org/I4210139553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minmin Yuan","raw_affiliation_strings":["National Environmental Protection Engineering and Technology Center for Road Traffic Noise Control, Research Institute of Highway Ministry of Transport, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Environmental Protection Engineering and Technology Center for Road Traffic Noise Control, Research Institute of Highway Ministry of Transport, Beijing, China","institution_ids":["https://openalex.org/I4210139553","https://openalex.org/I4210127216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110739750","display_name":"Shegang Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]},{"id":"https://openalex.org/I4210139553","display_name":"Research Institute of Highway","ror":"https://ror.org/0335kqk33","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216","https://openalex.org/I4210139553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shegang Shao","raw_affiliation_strings":["National Environmental Protection Engineering and Technology Center for Road Traffic Noise Control, Research Institute of Highway Ministry of Transport, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Environmental Protection Engineering and Technology Center for Road Traffic Noise Control, Research Institute of Highway Ministry of Transport, Beijing, China","institution_ids":["https://openalex.org/I4210139553","https://openalex.org/I4210127216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9977999925613403,"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/spectrogram","display_name":"Spectrogram","score":0.9543061852455139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7306015491485596},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6270649433135986},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5664225816726685},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5472753047943115},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5382558703422546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46566084027290344},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42325711250305176},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37291860580444336}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9543061852455139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7306015491485596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6270649433135986},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5664225816726685},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5472753047943115},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5382558703422546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46566084027290344},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42325711250305176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37291860580444336},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3552466.3556526","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3552466.3556526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W15681643","https://openalex.org/W2069883713","https://openalex.org/W2070126272","https://openalex.org/W2128466129","https://openalex.org/W2176804518","https://openalex.org/W2398758564","https://openalex.org/W2403139431","https://openalex.org/W2406845569","https://openalex.org/W2596411757","https://openalex.org/W2606361731","https://openalex.org/W2752782242","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W2972811785","https://openalex.org/W2973164265","https://openalex.org/W2990833974","https://openalex.org/W3010851250","https://openalex.org/W3015805741","https://openalex.org/W3025210871","https://openalex.org/W3034598492","https://openalex.org/W3086958808","https://openalex.org/W3096333737","https://openalex.org/W3150572638","https://openalex.org/W3155308523","https://openalex.org/W3160325739","https://openalex.org/W3163596559","https://openalex.org/W3196897556","https://openalex.org/W3197358873","https://openalex.org/W3198486673","https://openalex.org/W3203575608","https://openalex.org/W4221138880","https://openalex.org/W4401201189"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"Recently,":[0],"pioneer":[1],"research":[2],"works":[3],"have":[4,36],"proposed":[5,203],"a":[6],"large":[7],"number":[8],"of":[9,48,68,82,88,100,133,141,154,183,220],"acoustic":[10],"features":[11,57,169,173,189],"(log":[12],"power":[13],"spectrogram,":[14],"linear":[15],"frequency":[16,73,137],"cepstral":[17,21],"coefficients,":[18,22],"constant":[19],"Q":[20],"etc.)":[23],"for":[24,208],"audio":[25,40,210],"deepfake":[26,41,211],"detection,":[27],"obtaining":[28],"good":[29],"performance,":[30],"and":[31,55,118,157,166,174,186],"showing":[32],"that":[33,99,106,201],"different":[34,37],"subbands":[35,178],"contributions":[38],"to":[39,78,114,129,150,163],"detection.":[42],"However,":[43],"this":[44,122],"lacks":[45],"an":[46,215],"explanation":[47],"the":[49,53,66,71,80,86,130,136,146,155,176,181,195,209],"specific":[50],"information":[51,60,75,113,123],"in":[52],"subband,":[54],"these":[56],"also":[58,161],"lose":[59],"such":[61],"as":[62,111,145,170],"phase.":[63],"Inspired":[64],"by":[65],"mechanism":[67],"synthetic":[69,83,89],"speech,":[70,84,120],"fundamental":[72],"(F0)":[74],"is":[76,91,104,143,205],"used":[77,110,126],"improve":[79],"quality":[81],"while":[85,121],"F0":[87,107,142],"speech":[90],"still":[92],"too":[93],"average,":[94],"which":[95,222],"differs":[96],"significantly":[97],"from":[98],"real":[101,165,185],"speech.":[102],"It":[103],"expected":[105],"can":[108],"be":[109,125],"important":[112],"discriminate":[115],"between":[116],"bonafide":[117],"fake":[119],"cannot":[124],"directly":[127],"due":[128],"irregular":[131],"distribution":[132],"F0.":[134],"Insteadly,":[135],"band":[138],"containing":[139],"most":[140],"selected":[144],"input":[147,172],"feature.":[148],"Meanwhile,":[149],"make":[151],"full":[152],"use":[153,164],"phase":[156],"full-band":[158],"information,":[159],"we":[160],"propose":[162],"imaginary":[167,187],"spectrogram":[168,188],"complementary":[171],"model":[175],"disjoint":[177],"separately.":[179],"Finally,":[180],"results":[182,193],"F0,":[184],"are":[190],"fused.":[191],"Experimental":[192],"on":[194],"ASVspoof":[196],"2019":[197],"LA":[198],"dataset":[199],"show":[200],"our":[202],"system":[204],"very":[206],"effective":[207],"detection":[212],"task,":[213],"achieving":[214],"equivalent":[216],"error":[217],"rate":[218],"(EER)":[219],"0.43%,":[221],"surpasses":[223],"almost":[224],"all":[225],"systems.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-10-02T00:00:00"}