{"id":"https://openalex.org/W4372260334","doi":"https://doi.org/10.1109/icassp49357.2023.10096249","title":"Content-Insensitive Dynamic Lip Feature Extraction for Visual Speaker Authentication Against Deepfake Attacks","display_name":"Content-Insensitive Dynamic Lip Feature Extraction for Visual Speaker Authentication Against Deepfake Attacks","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260334","doi":"https://doi.org/10.1109/icassp49357.2023.10096249"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101738022","display_name":"Zihao Guo","orcid":"https://orcid.org/0000-0001-9432-2227"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihao Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China","School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101717685","display_name":"Shilin Wang","orcid":"https://orcid.org/0000-0002-8214-6809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China","School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101738022"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70006885,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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":0.9965999722480774,"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":0.7676806449890137},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7154484391212463},{"id":"https://openalex.org/keywords/authentication","display_name":"Authentication (law)","score":0.6958903074264526},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5566575527191162},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45378679037094116},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4402048587799072},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4261763095855713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3814009130001068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3645437955856323},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2321125566959381},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0762561559677124},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.04716894030570984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676806449890137},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7154484391212463},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.6958903074264526},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5566575527191162},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45378679037094116},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4402048587799072},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4261763095855713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3814009130001068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3645437955856323},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2321125566959381},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0762561559677124},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.04716894030570984},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096249","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316092","display_name":"Science and Technology Department of Ningxia","ror":null},{"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":41,"referenced_works":["https://openalex.org/W1566709181","https://openalex.org/W1664547674","https://openalex.org/W1983364832","https://openalex.org/W2015143272","https://openalex.org/W2090861223","https://openalex.org/W2115252128","https://openalex.org/W2116923196","https://openalex.org/W2161361444","https://openalex.org/W2508015696","https://openalex.org/W2809576682","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2904573504","https://openalex.org/W2982220924","https://openalex.org/W2993240882","https://openalex.org/W3008823916","https://openalex.org/W3019200173","https://openalex.org/W3038930935","https://openalex.org/W3081492798","https://openalex.org/W3089868584","https://openalex.org/W3092709185","https://openalex.org/W3094502228","https://openalex.org/W3101631197","https://openalex.org/W3113824005","https://openalex.org/W3125803510","https://openalex.org/W3135809943","https://openalex.org/W3174508664","https://openalex.org/W3174656926","https://openalex.org/W3186090335","https://openalex.org/W3193318040","https://openalex.org/W4297808394","https://openalex.org/W4312388562","https://openalex.org/W4385245566","https://openalex.org/W6673277873","https://openalex.org/W6677618333","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757599822","https://openalex.org/W6767264202","https://openalex.org/W6784333009","https://openalex.org/W6791334480"],"related_works":["https://openalex.org/W2377297411","https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W3148217948","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2375788636","https://openalex.org/W2256933480","https://openalex.org/W1560125148"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2],"shown":[3],"that":[4,122],"lip-based":[5,49],"speaker":[6,51],"authentication":[7,12,52],"system":[8],"can":[9,20],"achieve":[10],"good":[11],"performance.":[13],"However,":[14],"with":[15,38,63],"emerging":[16],"deepfake":[17,57],"technology,":[18],"attackers":[19],"make":[21],"high":[22],"fidelity":[23],"talking":[24,74],"videos":[25],"of":[26,100],"a":[27,31,43,71,83,101],"user,":[28],"thus":[29],"posing":[30],"great":[32],"threat":[33],"to":[34,69,89,113],"these":[35],"systems.":[36],"Confronted":[37],"this":[39],"threat,":[40],"we":[41],"propose":[42],"new":[44],"deep":[45],"neural":[46],"network":[47],"for":[48],"visual":[50],"against":[53],"human":[54],"imposters":[55],"and":[56,138],"attacks.":[58],"One":[59],"dynamic":[60],"enhanced":[61],"block":[62],"context":[64],"modeling":[65],"scheme":[66],"is":[67,87],"designed":[68,88],"capture":[70],"user\u2019s":[72],"unique":[73],"habit":[75],"by":[76],"learning":[77,95],"from":[78,96],"his/her":[79],"lip":[80,98],"movement.":[81],"Meanwhile,":[82],"cross-modality":[84],"content-guided":[85],"loss":[86,107],"help":[90],"extract":[91],"discriminative":[92],"features":[93],"when":[94],"different":[97,104],"movement":[99],"user":[102],"uttering":[103],"content.":[105],"This":[106],"makes":[108],"the":[109,118,123,135,140],"proposed":[110,124],"method":[111,125],"insensitive":[112],"content":[114],"variation.":[115],"Experiments":[116],"on":[117],"GRID":[119],"dataset":[120],"show":[121],"not":[126],"only":[127],"outperforms":[128],"three":[129],"state-of-the-art":[130],"methods":[131],"but":[132],"also":[133],"simplifies":[134],"training":[136,141],"process":[137],"reduces":[139],"cost.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}