{"id":"https://openalex.org/W4392902963","doi":"https://doi.org/10.1109/icassp48485.2024.10446780","title":"Voxblink: A Large Scale Speaker Verification Dataset on Camera","display_name":"Voxblink: A Large Scale Speaker Verification Dataset on Camera","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902963","doi":"https://doi.org/10.1109/icassp48485.2024.10446780"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446780","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/A5049403564","display_name":"Yuke Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuke Lin","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075605099","display_name":"Xiaoyi Qin","orcid":"https://orcid.org/0000-0003-2521-8084"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyi Qin","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628448","display_name":"Guoqing Zhao","orcid":"https://orcid.org/0000-0001-7130-7147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoqing Zhao","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062363830","display_name":"Ming Cheng","orcid":"https://orcid.org/0000-0002-4859-2004"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Cheng","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052756710","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0003-1579-3114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023919878","display_name":"Haiying Wu","orcid":"https://orcid.org/0009-0008-8816-7791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiying Wu","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5049403564"],"corresponding_institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":5.5071,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9652811,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10271","last_page":"10275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8464667201042175},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7389262914657593},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.56939697265625},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5489721894264221},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5269185900688171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42618751525878906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3902895152568817},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3608320951461792},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35718315839767456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8464667201042175},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7389262914657593},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.56939697265625},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5489721894264221},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5269185900688171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42618751525878906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3902895152568817},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3608320951461792},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35718315839767456},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446780","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":[{"id":"https://openalex.org/G1270229601","display_name":null,"funder_award_id":"62171207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G564888837","display_name":null,"funder_award_id":"SYC2022051","funder_id":"https://openalex.org/F4320336618","funder_display_name":"Science and Technology Program of Suzhou"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336618","display_name":"Science and Technology Program of Suzhou","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2516764878","https://openalex.org/W2592168896","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2808631503","https://openalex.org/W2963371159","https://openalex.org/W2963466847","https://openalex.org/W2969985801","https://openalex.org/W3010893827","https://openalex.org/W3015503328","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3026006730","https://openalex.org/W3034552680","https://openalex.org/W3094325190","https://openalex.org/W3094374485","https://openalex.org/W3105202226","https://openalex.org/W3141035251","https://openalex.org/W3160743249","https://openalex.org/W3206287456","https://openalex.org/W4221154745","https://openalex.org/W4306867253","https://openalex.org/W4312636357","https://openalex.org/W4319862437","https://openalex.org/W4372259900","https://openalex.org/W4372265901","https://openalex.org/W4372317224","https://openalex.org/W4372338350","https://openalex.org/W4375868932","https://openalex.org/W4385822285","https://openalex.org/W4386044452","https://openalex.org/W4391827341","https://openalex.org/W6784256521","https://openalex.org/W6847363464","https://openalex.org/W6855885967"],"related_works":["https://openalex.org/W3037187668","https://openalex.org/W4234772502","https://openalex.org/W2380685755","https://openalex.org/W2252100032","https://openalex.org/W2963436428","https://openalex.org/W4400978025","https://openalex.org/W2918743509","https://openalex.org/W2734796617","https://openalex.org/W3083218341","https://openalex.org/W3034087822"],"abstract_inverted_index":{"In":[0,75],"this":[1,28],"paper,":[2],"we":[3,52,123],"introduce":[4],"a":[5,55,61,145],"large-scale":[6],"and":[7,19,72,89,119],"high-quality":[8],"audiovisual":[9],"speaker":[10,113,126],"verification":[11,114,127],"dataset,":[12,29],"named":[13,67],"VoxBlink.":[14],"We":[15],"propose":[16],"an":[17],"innovative":[18],"robust":[20],"automatic":[21],"audio-visual":[22],"data":[23,44,48],"mining":[24],"pipeline":[25],"to":[26,38,59,77,133,152],"curate":[27],"which":[30],"contains":[31],"1.45M":[32],"utterances":[33],"from":[34,83,150],"38K":[35],"speakers.":[36],"Due":[37],"the":[39,65,78,80,90,103,109,117,138,160,163,169],"inherent":[40],"nature":[41],"of":[42,64,86,108,168],"automated":[43],"collection,":[45],"introducing":[46],"noisy":[47],"is":[49,106],"inevitable.":[50],"Therefore,":[51],"also":[53],"utilize":[54],"multi-modal":[56],"purification":[57],"step":[58],"generate":[60],"cleaner":[62],"version":[63],"VoxBlink,":[66],"VoxBlink-clean,":[68],"comprising":[69],"18K":[70],"identities":[71],"1.02M":[73],"utterances.":[74],"contrast":[76],"VoxCeleb,":[79],"VoxBlink":[81,104],"sources":[82],"short":[84],"videos":[85],"ordinary":[87],"users,":[88],"covered":[91],"scenarios":[92],"can":[93,171],"better":[94],"align":[95],"with":[96,129],"real-life":[97],"situations.":[98],"To":[99],"our":[100],"best":[101],"knowledge,":[102],"dataset":[105,170],"one":[107],"largest":[110],"publicly":[111],"available":[112],"datasets.":[115],"Leveraging":[116],"VoxCeleb":[118,139],"VoxBlink-clean":[120,161],"datasets":[121],"together,":[122],"employ":[124],"diverse":[125],"models":[128],"multiple":[130],"architectural":[131],"backbones":[132],"conduct":[134],"comprehensive":[135],"evaluations":[136],"on":[137,174],"test":[140],"sets.":[141],"Experimental":[142],"results":[143],"indicate":[144],"substantial":[146],"enhancement":[147],"in":[148],"performance\u2014ranging":[149],"12%":[151],"30%":[153],"relatively\u2014across":[154],"various":[155],"backbone":[156],"architectures":[157],"upon":[158],"incorporating":[159],"into":[162],"training":[164],"process.":[165],"The":[166],"details":[167],"be":[172],"found":[173],"$\\color{Fuchsia}":[175],"{{\\text{Site}}}$.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}