{"id":"https://openalex.org/W2726515241","doi":"https://doi.org/10.21437/interspeech.2017-950","title":"VoxCeleb: A Large-Scale Speaker Identification Dataset","display_name":"VoxCeleb: A Large-Scale Speaker Identification Dataset","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2726515241","doi":"https://doi.org/10.21437/interspeech.2017-950","mag":"2726515241"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-950","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1706.08612","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036002448","display_name":"Arsha Nagrani","orcid":"https://orcid.org/0000-0003-2190-9013"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arsha Nagrani","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036002448"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":90.4326,"has_fulltext":true,"cited_by_count":2111,"citation_normalized_percentile":{"value":0.99986371,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2616","last_page":"2620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9993000030517578,"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":0.8687504529953003},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7489539980888367},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7232778072357178},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.679381251335144},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6241340041160583},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5531354546546936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5393450260162354},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.508747398853302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4852747619152069},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4670756161212921},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4404246211051941}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8687504529953003},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7489539980888367},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7232778072357178},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.679381251335144},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6241340041160583},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5531354546546936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5393450260162354},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.508747398853302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4852747619152069},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4670756161212921},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4404246211051941},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-950","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1706.08612","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.08612","pdf_url":"https://arxiv.org/pdf/1706.08612","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:3dc3662e-0043-402b-8c37-6952ac9a9523","is_oa":true,"landing_page_url":null,"pdf_url":"https://ora.ox.ac.uk/objects/uuid:3dc3662e-0043-402b-8c37-6952ac9a9523","source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference item"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1706.08612","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.08612","pdf_url":"https://arxiv.org/pdf/1706.08612","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1277543710","display_name":null,"funder_award_id":"EP/M013774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2330149154","https://openalex.org/W2526050071","https://openalex.org/W2949117887"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2160753975","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Most":[0],"existing":[1],"datasets":[2],"for":[3,112,150],"speaker":[4,33,73,90,129],"identification":[5,130,152],"contain":[6],"samples":[7],"obtained":[8],"under":[9],"quite":[10],"constrained":[11],"conditions,":[12],"and":[13,84,122,153],"are":[14],"usually":[15],"hand-annotated,":[16],"hence":[17],"limited":[18],"in":[19],"size.":[20],"The":[21],"goal":[22],"of":[23,88,106,108,126],"this":[24,98],"paper":[25],"is":[26,119],"to":[27,57,100,120,135],"generate":[28],"a":[29,48,77,142],"large":[30],"scale":[31],"text-independent":[32],"identi-":[34],"fication":[35],"dataset":[36,60,134],"collected":[37],"\u2018in":[38],"the":[39,59,86,89,127,147],"wild\u2019.":[40],"We":[41,96,139],"make":[42],"two":[43],"contributions.":[44],"First,":[45],"we":[46],"propose":[47],"fully":[49],"automated":[50],"pipeline":[51,65,99],"based":[52,93,144],"on":[53,132],"computer":[54],"vision":[55],"techniques":[56,131],"create":[58],"from":[61,69],"open-source":[62],"media.":[63],"Our":[64,116],"involves":[66],"obtaining":[67],"videos":[68],"YouTube;":[70],"performing":[71],"active":[72],"verifi-":[74],"cation":[75],"using":[76,91],"two-stream":[78],"synchronization":[79],"Convolutional":[80],"Neural":[81],"Network":[82],"(CNN),":[83],"confirming":[85],"identity":[87],"CNN":[92,143],"facial":[94],"recognition.":[95],"use":[97],"curate":[101],"VoxCeleb":[102],"which":[103],"contains":[104],"hundreds":[105],"thousands":[107],"\u2018real":[109],"world\u2019":[110],"utterances":[111],"over":[113],"1,000":[114],"celebrities.":[115],"second":[117],"contribution":[118],"apply":[121],"compare":[123],"various":[124],"state":[125],"art":[128],"our":[133],"establish":[136],"baseline":[137],"performance.":[138],"show":[140],"that":[141],"architecture":[145],"obtains":[146],"best":[148],"performance":[149],"both":[151],"verification.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":47},{"year":2025,"cited_by_count":266},{"year":2024,"cited_by_count":300},{"year":2023,"cited_by_count":356},{"year":2022,"cited_by_count":326},{"year":2021,"cited_by_count":331},{"year":2020,"cited_by_count":282},{"year":2019,"cited_by_count":153},{"year":2018,"cited_by_count":50}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}