{"id":"https://openalex.org/W4386928847","doi":"https://doi.org/10.1145/3625231","title":"Voice-Face Homogeneity Tells Deepfake","display_name":"Voice-Face Homogeneity Tells Deepfake","publication_year":2023,"publication_date":"2023-09-21","ids":{"openalex":"https://openalex.org/W4386928847","doi":"https://doi.org/10.1145/3625231"},"language":"en","primary_location":{"id":"doi:10.1145/3625231","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625231","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5059602960","display_name":"Harry H. Cheng","orcid":"https://orcid.org/0000-0001-7436-0162"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Harry Cheng","raw_affiliation_strings":["Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0001-7436-0162","affiliations":[{"raw_affiliation_string":"Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054313646","display_name":"Yangyang Guo","orcid":"https://orcid.org/0000-0001-8691-5372"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yangyang Guo","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8691-5372","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399645","display_name":"Tianyi Wang","orcid":"https://orcid.org/0000-0003-2920-6099"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianyi Wang","raw_affiliation_strings":["The University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-2920-6099","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350237","display_name":"Qi Li","orcid":"https://orcid.org/0000-0002-8095-5573"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":["Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0002-8095-5573","affiliations":[{"raw_affiliation_string":"Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["University of Technology Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7778-8807","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059602960"],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":9.811,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.98791616,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"20","issue":"3","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9995999932289124,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9995999932289124,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9994000196456909,"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/T11448","display_name":"Face recognition and analysis","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8569039106369019},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7326108813285828},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5655918717384338},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5555049180984497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5189833045005798},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4636157155036926},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43188509345054626},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4220826029777527},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10512295365333557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09257251024246216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8569039106369019},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7326108813285828},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5655918717384338},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5555049180984497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5189833045005798},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4636157155036926},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43188509345054626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4220826029777527},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10512295365333557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09257251024246216},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625231","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625231","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1581253957","https://openalex.org/W2066078528","https://openalex.org/W2083192529","https://openalex.org/W2166465411","https://openalex.org/W2187089797","https://openalex.org/W2477916117","https://openalex.org/W2602441275","https://openalex.org/W2602753196","https://openalex.org/W2897663715","https://openalex.org/W2904573504","https://openalex.org/W2913738669","https://openalex.org/W3003301247","https://openalex.org/W3041229290","https://openalex.org/W3081492798","https://openalex.org/W3092813564","https://openalex.org/W3094728142","https://openalex.org/W3096831136","https://openalex.org/W3101631197","https://openalex.org/W3108854358","https://openalex.org/W3124826036","https://openalex.org/W3140587737","https://openalex.org/W3161406421","https://openalex.org/W3183780821","https://openalex.org/W3192587235","https://openalex.org/W3207505152","https://openalex.org/W3209972423","https://openalex.org/W3216470601","https://openalex.org/W4200475325","https://openalex.org/W4206982465","https://openalex.org/W4207031341","https://openalex.org/W4214809420","https://openalex.org/W4220840497","https://openalex.org/W4226184311","https://openalex.org/W4280579728","https://openalex.org/W4288084733","https://openalex.org/W4292596009","https://openalex.org/W4297808394","https://openalex.org/W4308949512","https://openalex.org/W4309764400","https://openalex.org/W4310017951","https://openalex.org/W4316660967","https://openalex.org/W4319978495","https://openalex.org/W4387968259","https://openalex.org/W6721627648","https://openalex.org/W6751692644","https://openalex.org/W6803211467","https://openalex.org/W6810651956","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4221142204"],"abstract_inverted_index":{"Detecting":[0],"forgery":[1],"videos":[2,23,104],"is":[3,74,82,235],"highly":[4,99],"desirable":[5],"due":[6,114],"to":[7,16,62,115,136,163,213],"the":[8,18,31,39,48,89,110,129,147,176,185,222],"abuse":[9],"of":[10,41,50,86,93,152,230],"deepfake.":[11],"Existing":[12],"detection":[13,65],"approaches":[14,52],"contribute":[15],"exploring":[17],"specific":[19,143],"artifacts":[20,36],"in":[21],"deepfake":[22,43,64,103,138,144,153,189,199,250],"and":[24,91,101,112,203],"fit":[25],"well":[26],"on":[27,34,76,142,178,187,232,248],"certain":[28,150],"data.":[29,190,251],"However,":[30],"growing":[32],"technique":[33],"these":[35,51,133],"keeps":[37],"challenging":[38],"robustness":[40],"traditional":[42],"detectors.":[44],"As":[45],"a":[46,55,83,123,158,167,179],"result,":[47],"development":[49],"has":[53],"reached":[54],"blockage.":[56],"In":[57],"this":[58,119],"article,":[59],"we":[60,121,173],"propose":[61],"perform":[63],"from":[66],"an":[67,94,228],"unexplored":[68],"voice-face":[69,124],"matching":[70,125,130],"view.":[71],"Our":[72,205],"approach":[73],"founded":[75],"two":[77,134],"supporting":[78],"points:":[79],"first,":[80],"there":[81],"high":[84],"degree":[85,131],"homogeneity":[87],"between":[88,109,132],"voice":[90,111],"face":[92,113],"individual":[95],"(i.e.,":[96],"they":[97],"are":[98],"correlated),":[100],"second,":[102],"often":[105],"involve":[106],"mismatched":[107],"identities":[108],"face-swapping":[116],"techniques.":[117],"To":[118],"end,":[120],"develop":[122],"method":[126,159,206,220,241],"that":[127,160,239],"measures":[128],"modalities":[135],"identify":[137],"videos.":[139],"Nevertheless,":[140],"training":[141],"datasets":[145],"makes":[146],"model":[148,177],"overfit":[149],"traits":[151],"algorithms.":[154],"We":[155,191],"instead":[156],"advocate":[157],"quickly":[161],"adapts":[162],"untapped":[164],"forgery,":[165],"with":[166],"pre-training":[168],"then":[169],"fine-tuning":[170,186],"paradigm.":[171],"Specifically,":[172],"first":[174],"pre-train":[175],"generic":[180],"audio-visual":[181],"dataset,":[182],"followed":[183],"by":[184,224],"downstream":[188],"conduct":[192],"extensive":[193],"experiments":[194],"over":[195],"three":[196],"widely":[197],"exploited":[198],"datasets:":[200],"DFDC,":[201],"FakeAVCeleb,":[202],"DeepfakeTIMIT.":[204],"obtains":[207],"significant":[208],"performance":[209],"gains":[210],"as":[211],"compared":[212],"other":[214],"state-of-the-art":[215],"competitors.":[216],"For":[217],"instance,":[218],"our":[219,240],"outperforms":[221],"baselines":[223],"nearly":[225],"2%,":[226],"achieving":[227],"AUC":[229],"86.11%":[231],"FakeAVCeleb.":[233],"It":[234],"also":[236],"worth":[237],"noting":[238],"already":[242],"achieves":[243],"competitive":[244],"results":[245],"when":[246],"fine-tuned":[247],"limited":[249]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":15}],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2025-10-10T00:00:00"}