{"id":"https://openalex.org/W4403791411","doi":"https://doi.org/10.1145/3664647.3688979","title":"Exploring Robust Face-Voice Matching in Multilingual Environments","display_name":"Exploring Robust Face-Voice Matching in Multilingual Environments","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791411","doi":"https://doi.org/10.1145/3664647.3688979"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3688979","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5113315336","display_name":"Jiehui Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiehui Tang","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046637354","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0001-5490-5591"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100519242","display_name":"Zhen Xiao","orcid":"https://orcid.org/0009-0003-9885-5217"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xiao","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108101484","display_name":"Jiayi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126646","display_name":"Vanke (China)","ror":"https://ror.org/0329dzd04","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126646"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Liu","raw_affiliation_strings":["Vanke Meisha Academy, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Vanke Meisha Academy, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210126646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101993173","display_name":"Xueliang Liu","orcid":"https://orcid.org/0000-0003-0077-9715"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Liu","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113315336"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19213522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11335","last_page":"11341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","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/T11448","display_name":"Face recognition and analysis","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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7167025208473206},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6453908085823059},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5458862781524658},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47162842750549316},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47032129764556885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4314208924770355},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1386399269104004},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07044419646263123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7167025208473206},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6453908085823059},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5458862781524658},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47162842750549316},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47032129764556885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4314208924770355},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1386399269104004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07044419646263123},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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:10.1145/3664647.3688979","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3688979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2325939864","https://openalex.org/W2897663715","https://openalex.org/W2916104401","https://openalex.org/W2963887950","https://openalex.org/W2967735860","https://openalex.org/W2997819898","https://openalex.org/W3093411628","https://openalex.org/W3118548710","https://openalex.org/W3154848313","https://openalex.org/W3177326298","https://openalex.org/W3184648662","https://openalex.org/W4206070857","https://openalex.org/W4206097581","https://openalex.org/W4224924564","https://openalex.org/W4285603046","https://openalex.org/W4372341093","https://openalex.org/W4378976870","https://openalex.org/W4402703056"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W3154990682","https://openalex.org/W2560201613","https://openalex.org/W2171975302","https://openalex.org/W2022352247","https://openalex.org/W2488129135","https://openalex.org/W4312219546","https://openalex.org/W2377538627","https://openalex.org/W2107220315","https://openalex.org/W1589637664"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Team":[3],"Xaiofei's":[4],"innovative":[5],"approach":[6],"to":[7,64,83,91],"exploring":[8],"Face-Voice":[9],"Association":[10],"in":[11,27],"Multilingual":[12],"Environments":[13],"(FAME)":[14],"at":[15],"ACM":[16],"Multimedia":[17],"2024.":[18],"We":[19,72],"focus":[20],"on":[21,104,129,135],"the":[22,93,113,130,136],"impact":[23],"of":[24,127],"different":[25],"languages":[26],"face-voice":[28],"matching":[29,108],"by":[30],"building":[31],"upon":[32],"Fusion":[33],"and":[34,52,67,106,111,133],"Orthogonal":[35],"Projection":[36],"(FOP),":[37],"introducing":[38],"four":[39],"key":[40],"components:":[41],"a":[42,75],"dual-branch":[43,57],"structure,":[44],"dynamic":[45,76],"sample":[46,81],"pair":[47],"weighting,":[48],"robust":[49],"data":[50],"augmentation,":[51],"score":[53,100],"polarization":[54,101],"strategy.":[55],"Our":[56,116],"structure":[58],"serves":[59],"as":[60],"an":[61,122],"auxiliary":[62],"mechanism":[63,78],"better":[65],"integrate":[66],"provide":[68],"more":[69],"comprehensive":[70],"information.":[71],"also":[73],"introduce":[74],"weighting":[77],"for":[79],"various":[80],"pairs":[82],"optimize":[84],"learning.":[85],"Data":[86],"augmentation":[87],"techniques":[88],"are":[89],"employed":[90],"enhance":[92],"model's":[94],"generalization":[95],"across":[96],"diverse":[97],"conditions.":[98],"Additionally,":[99],"strategy":[102],"based":[103],"age":[105],"gender":[107],"confidence":[109],"clarifies":[110],"accentuates":[112],"final":[114],"results.":[115],"methods":[117],"demonstrate":[118],"significant":[119],"effectiveness,":[120],"achieving":[121],"equal":[123],"error":[124],"rate":[125],"(EER)":[126],"20.07":[128],"V2-EH":[131],"dataset":[132],"21.76":[134],"V1-EU":[137],"dataset.":[138],"Project":[139],"page:":[140],"https://github.com/cnzvan/Exploring-Robust-Face-Voice-Matching-in-Multilingual-Environments.":[141]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}