{"id":"https://openalex.org/W4210534223","doi":"https://doi.org/10.1145/3497623.3497639","title":"LightCvT: Audio Forgery Detection via Fusion of Light CNN and Transformer","display_name":"LightCvT: Audio Forgery Detection via Fusion of Light CNN and Transformer","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W4210534223","doi":"https://doi.org/10.1145/3497623.3497639"},"language":"en","primary_location":{"id":"doi:10.1145/3497623.3497639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3497623.3497639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 10th International Conference on Computing and Pattern Recognition","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/A5100731336","display_name":"Chenyu Liu","orcid":"https://orcid.org/0000-0002-4159-8892"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenyu Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101804351","display_name":"Jia Li","orcid":"https://orcid.org/0000-0002-5400-570X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","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":"Jia Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047230227","display_name":"Junxian Duan","orcid":"https://orcid.org/0000-0002-0218-6924"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junxian Duan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979003","display_name":"Haifeng Shen","orcid":"https://orcid.org/0000-0002-2654-3084"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Shen","raw_affiliation_strings":["AI Enabling Platform, Didi Chuxing, China"],"affiliations":[{"raw_affiliation_string":"AI Enabling Platform, Didi Chuxing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005195235","display_name":"Huaibo Huang","orcid":"https://orcid.org/0000-0001-5866-2283"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","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":"Huaibo Huang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100731336"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.3843,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6253268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9871000051498413,"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/T11309","display_name":"Music and Audio Processing","score":0.9725000262260437,"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":0.8353836536407471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.696198582649231},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6603032946586609},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5791209936141968},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5207162499427795},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5177997350692749},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47764742374420166},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4738093912601471},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.447482705116272},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44390198588371277},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.43638888001441956},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4162684381008148},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41457754373550415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3962475061416626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32340872287750244},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1166296899318695},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09916374087333679}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353836536407471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.696198582649231},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6603032946586609},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5791209936141968},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5207162499427795},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5177997350692749},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47764742374420166},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4738093912601471},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.447482705116272},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44390198588371277},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.43638888001441956},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4162684381008148},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41457754373550415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3962475061416626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32340872287750244},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1166296899318695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09916374087333679},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3497623.3497639","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3497623.3497639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 10th International Conference on Computing and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6224975731","display_name":null,"funder_award_id":"62006228","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2274287116","https://openalex.org/W2549139847","https://openalex.org/W2562863628","https://openalex.org/W2590129515","https://openalex.org/W2752782242","https://openalex.org/W2775315796","https://openalex.org/W2799053639","https://openalex.org/W2807325376","https://openalex.org/W2894365374","https://openalex.org/W2896457183","https://openalex.org/W2936697195","https://openalex.org/W2941956444","https://openalex.org/W2963091558","https://openalex.org/W2964350391","https://openalex.org/W2967104857","https://openalex.org/W2972526452","https://openalex.org/W2972614582","https://openalex.org/W2972786657","https://openalex.org/W2973058799","https://openalex.org/W2981413347","https://openalex.org/W2982220924","https://openalex.org/W3007151378","https://openalex.org/W3025165719","https://openalex.org/W3026777299","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3097777922","https://openalex.org/W3116489684","https://openalex.org/W3121523901","https://openalex.org/W3138516171","https://openalex.org/W3160694286","https://openalex.org/W3170874841","https://openalex.org/W3171087525","https://openalex.org/W3172509117","https://openalex.org/W3174738881","https://openalex.org/W3181925591","https://openalex.org/W4214493665","https://openalex.org/W4287025584","https://openalex.org/W4313007769","https://openalex.org/W4385245566","https://openalex.org/W6731068170","https://openalex.org/W6746034047","https://openalex.org/W6791943378","https://openalex.org/W6798442695","https://openalex.org/W7036189142"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2271369634","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W4385009901","https://openalex.org/W4304700937"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,12,22,108,126,151,159],"machine":[3],"learning":[4],"has":[5],"greatly":[6],"improved":[7],"the":[8,20,64,105,113,152,157,160,166,170,177,187,191,198],"quality":[9],"and":[10,17,38,45,99,118,136,156,186],"authenticity":[11],"artificial":[13],"intelligence-generated":[14],"audio,":[15],"image,":[16],"video.":[18],"However,":[19],"existence":[21],"such":[23],"fake":[24],"content":[25],"poses":[26],"a":[27,56,83],"risk":[28],"to":[29,36,42,77,94,103,122,132,139,148,174],"people's":[30],"daily":[31],"life.":[32],"It":[33],"is":[34],"important":[35],"explore":[37],"develop":[39],"forensic":[40],"technology":[41],"identify":[43],"real":[44],"synthesized":[46],"audio.":[47],"We":[48,81,111],"observe":[49],"that":[50,62,190],"these":[51],"deep":[52,65],"neural":[53,66],"networks":[54,67],"have":[55],"certain":[57],"uniformity":[58],"in":[59],"cross-modal":[60],"tasks,":[61],"is,":[63],"used":[68],"for":[69,88],"image":[70],"forgery":[71,79,90],"detection":[72,106],"can":[73],"also":[74],"be":[75],"applied":[76],"audio":[78,89,109],"detection.":[80,91],"propose":[82],"light":[84],"transformer-based":[85],"network":[86],"LightCvT":[87,92],"attempts":[93],"capture":[95,140],"both":[96],"local":[97,134,180],"feature":[98,135,142],"non-local":[100],"long-range":[101],"dependencies":[102,143],"improve":[104],"accuracy":[107],"forgery.":[110],"combine":[112],"enhanced":[114],"Light":[115,129],"CNN":[116],"structure":[117],"Vision":[119],"Transformer":[120],"(ViT)":[121],"take":[123],"full":[124],"advantage":[125],"them.":[127],"Specifically,":[128],"CNN's":[130],"ability":[131,138,155],"extract":[133],"ViT's":[137],"long-distance":[141],"are":[144,184],"adaptively":[145],"complementary,":[146],"leading":[147],"significant":[149],"improvement":[150],"global":[153],"perception":[154],"discriminability":[158],"system.":[161],"In":[162],"addition,":[163],"we":[164],"introduce":[165],"self-attention":[167],"mechanism":[168],"into":[169],"convolutional":[171],"token":[172],"embedding":[173],"further":[175],"model":[176],"relations":[178],"between":[179],"regions.":[181],"Comprehensive":[182],"experiments":[183],"conducted":[185],"results":[188],"show":[189],"proposed":[192],"method":[193],"achieves":[194],"better":[195],"performance":[196],"than":[197],"state-of-the-art":[199],"methods.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}