{"id":"https://openalex.org/W4392902854","doi":"https://doi.org/10.1109/icassp48485.2024.10447923","title":"Audio Deepfake Detection With Self-Supervised Wavlm And Multi-Fusion Attentive Classifier","display_name":"Audio Deepfake Detection With Self-Supervised Wavlm And Multi-Fusion Attentive Classifier","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902854","doi":"https://doi.org/10.1109/icassp48485.2024.10447923"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101319159","display_name":"Yinlin Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141176","display_name":"Communication University of Zhejiang","ror":"https://ror.org/04t7gxr16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141176"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinlin Guo","raw_affiliation_strings":["Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I4210141176"]},{"raw_affiliation_string":"Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014360407","display_name":"Haofan Huang","orcid":"https://orcid.org/0000-0002-3505-9972"},"institutions":[{"id":"https://openalex.org/I4210141176","display_name":"Communication University of Zhejiang","ror":"https://ror.org/04t7gxr16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141176"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofan Huang","raw_affiliation_strings":["Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I4210141176"]},{"raw_affiliation_string":"Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329900","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-0571-6177"},"institutions":[{"id":"https://openalex.org/I4210141176","display_name":"Communication University of Zhejiang","ror":"https://ror.org/04t7gxr16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141176"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I4210141176"]},{"raw_affiliation_string":"Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100315046","display_name":"He Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141176","display_name":"Communication University of Zhejiang","ror":"https://ror.org/04t7gxr16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141176"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Zhao","raw_affiliation_strings":["Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I4210141176"]},{"raw_affiliation_string":"Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064952252","display_name":"Yuehai Wang","orcid":"https://orcid.org/0000-0002-5084-0572"},"institutions":[{"id":"https://openalex.org/I4210141176","display_name":"Communication University of Zhejiang","ror":"https://ror.org/04t7gxr16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141176"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehai Wang","raw_affiliation_strings":["Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Department of Information and Electronic Engineering,HangZhou,China","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I4210141176"]},{"raw_affiliation_string":"Department of Information and Electronic Engineering, Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":22.0791,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.9959232,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"12702","last_page":"12706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8439260125160217},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.733740508556366},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6997954249382019},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5686081051826477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5627259016036987},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.5099750757217407},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.505450963973999},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4248164892196655},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4170321822166443},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3662651777267456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439260125160217},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.733740508556366},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6997954249382019},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5686081051826477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5627259016036987},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.5099750757217407},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.505450963973999},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4248164892196655},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4170321822166443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3662651777267456},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":27,"referenced_works":["https://openalex.org/W2790784932","https://openalex.org/W2794506738","https://openalex.org/W2799053639","https://openalex.org/W2936802426","https://openalex.org/W2963508548","https://openalex.org/W2967606780","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3170179936","https://openalex.org/W3197358873","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3198486673","https://openalex.org/W3198529186","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W3206189675","https://openalex.org/W3209984917","https://openalex.org/W3212117663","https://openalex.org/W3213029956","https://openalex.org/W4225527248","https://openalex.org/W4226264925","https://openalex.org/W4302011308","https://openalex.org/W4323022270","https://openalex.org/W4386363146","https://openalex.org/W6780218876","https://openalex.org/W6845091008"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2953234277"],"abstract_inverted_index":{"With":[0],"the":[1,19,44,59,73,87,96,117,127],"rapid":[2],"development":[3],"of":[4,33,99],"speech":[5],"synthesis":[6],"and":[7,48,105,122,130],"voice":[8],"conversion":[9],"technologies,":[10],"Audio":[11],"Deepfake":[12],"has":[13],"become":[14],"a":[15,79],"serious":[16],"threat":[17],"to":[18,29,42,62,69],"Automatic":[20],"Speaker":[21],"Verification":[22],"(ASV)":[23],"system.":[24],"Numerous":[25],"countermeasures":[26],"are":[27,66],"proposed":[28],"detect":[30],"this":[31,36],"type":[32],"attack.":[34],"In":[35],"paper,":[37],"we":[38,77],"report":[39],"our":[40,111],"efforts":[41],"combine":[43],"self-supervised":[45],"WavLM":[46,60],"model":[47,61],"Multi-Fusion":[49,81],"Attentive":[50,82,88],"classifier":[51,84],"for":[52,72],"audio":[53,100],"deepfake":[54],"detection.":[55],"Our":[56],"method":[57],"exploits":[58],"extract":[63],"features":[64,101],"that":[65,110],"more":[67],"conducive":[68],"spoofing":[70],"detection":[71],"first":[74],"time.":[75],"Then,":[76],"propose":[78],"novel":[80],"(MFA)":[83],"based":[85],"on":[86,116,126],"Statistics":[89],"Pooling":[90],"(ASP)":[91],"layer.":[92],"The":[93],"MFA":[94],"captures":[95],"complementary":[97],"information":[98],"at":[102],"both":[103],"time":[104],"layer":[106],"levels.":[107],"Experiments":[108],"demonstrate":[109],"methods":[112],"achieve":[113],"state-of-the-art":[114],"results":[115,125],"ASVspoof":[118,128],"2021":[119,131],"DF":[120],"set":[121],"provide":[123],"competitive":[124],"2019":[129],"LA":[132],"set.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":9}],"updated_date":"2026-06-17T08:01:34.144755","created_date":"2025-10-10T00:00:00"}