{"id":"https://openalex.org/W2808631503","doi":"https://doi.org/10.21437/interspeech.2018-1929","title":"VoxCeleb2: Deep Speaker Recognition","display_name":"VoxCeleb2: Deep Speaker Recognition","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2808631503","doi":"https://doi.org/10.21437/interspeech.2018-1929","mag":"2808631503"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1929","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.05622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Visual Geometry Group, Department of Engineering Science, University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, Department of Engineering Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036002448","display_name":"Arsha Nagrani","orcid":"https://orcid.org/0000-0003-2190-9013"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arsha Nagrani","raw_affiliation_strings":["Visual Geometry Group, Department of Engineering Science, University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, Department of Engineering Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["Visual Geometry Group, Department of Engineering Science, University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, Department of Engineering Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038723822"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":147.9157,"has_fulltext":false,"cited_by_count":2247,"citation_normalized_percentile":{"value":0.99973638,"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":"1086","last_page":"1090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8389797806739807},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7351045608520508},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7211595773696899},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.701900064945221},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6892257332801819},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6716979146003723},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6226067543029785},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5667499899864197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5186406970024109},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5151961445808411},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.463477224111557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38710346817970276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2737044394016266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389797806739807},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7351045608520508},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7211595773696899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.701900064945221},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6892257332801819},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6716979146003723},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6226067543029785},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5667499899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5186406970024109},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5151961445808411},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.463477224111557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38710346817970276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2737044394016266},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1929","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1806.05622","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.05622","pdf_url":"https://arxiv.org/pdf/1806.05622","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:08ab75c5-aa1c-49fc-b36a-1280c6a309c4","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:08ab75c5-aa1c-49fc-b36a-1280c6a309c4","pdf_url":null,"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:1806.05622","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.05622","pdf_url":"https://arxiv.org/pdf/1806.05622","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","display_name":"Quality Education","score":0.5899999737739563}],"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":46,"referenced_works":["https://openalex.org/W1554705102","https://openalex.org/W1893902159","https://openalex.org/W1936725236","https://openalex.org/W1994002998","https://openalex.org/W1996950552","https://openalex.org/W2010062708","https://openalex.org/W2010114458","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2101261946","https://openalex.org/W2101306910","https://openalex.org/W2126854862","https://openalex.org/W2138621090","https://openalex.org/W2145287260","https://openalex.org/W2150769028","https://openalex.org/W2157364932","https://openalex.org/W2194775991","https://openalex.org/W2292259253","https://openalex.org/W2325939864","https://openalex.org/W2515770085","https://openalex.org/W2516764878","https://openalex.org/W2598634450","https://openalex.org/W2604379605","https://openalex.org/W2612434969","https://openalex.org/W2613087992","https://openalex.org/W2726515241","https://openalex.org/W2739192055","https://openalex.org/W2748488820","https://openalex.org/W2793493229","https://openalex.org/W2796292145","https://openalex.org/W2797090057","https://openalex.org/W2798513620","https://openalex.org/W2890964092","https://openalex.org/W2952419167","https://openalex.org/W2953066166","https://openalex.org/W2963026686","https://openalex.org/W2963173190","https://openalex.org/W2963671154","https://openalex.org/W2963801643","https://openalex.org/W2963839617","https://openalex.org/W2963887950","https://openalex.org/W2964171275","https://openalex.org/W3099206234","https://openalex.org/W3106250896","https://openalex.org/W3123318516","https://openalex.org/W4234330420"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"<p>The":[0],"objective":[1],"of":[2,97],"this":[3],"paper":[4],"is":[5,52],"speaker":[6,26,60],"recognition":[7,27,61],"under":[8,84],"noisy":[9],"and":[10,67,74],"unconstrained":[11],"conditions.</p>":[12],"<br/>":[13,63],"<p>We":[14],"make":[15],"two":[16],"key":[17],"contributions.":[18],"First,":[19],"we":[20,38,65],"introduce":[21],"a":[22,34,44,101,105],"very":[23],"large-scale":[24],"audio-visual":[25],"dataset":[28,93,103],"collected":[29],"from":[30,47,82],"open-source":[31],"media.":[32],"Using":[33],"fully":[35],"automated":[36],"pipeline,":[37],"curate":[39],"VoxCeleb2":[40,92],"which":[41],"contains":[42],"over":[43,48],"million":[45],"utterances":[46],"6,000":[49],"speakers.":[50],"This":[51],"several":[53],"times":[54],"larger":[55],"than":[56],"any":[57],"publicly":[58],"available":[59],"dataset.</p>":[62],"<p>Second,":[64],"develop":[66],"compare":[68],"Convolutional":[69],"Neural":[70],"Network":[71],"(CNN)":[72],"models":[73,88],"training":[75],"strategies":[76],"that":[77],"can":[78],"effectively":[79],"recognise":[80],"identities":[81],"voice":[83],"various":[85],"conditions.":[86],"The":[87],"trained":[89],"on":[90,100],"the":[91,95],"surpass":[94],"performance":[96],"previous":[98],"works":[99],"benchmark":[102],"by":[104],"significant":[106],"margin.</p>":[107]},"counts_by_year":[{"year":2026,"cited_by_count":61},{"year":2025,"cited_by_count":286},{"year":2024,"cited_by_count":321},{"year":2023,"cited_by_count":358},{"year":2022,"cited_by_count":347},{"year":2021,"cited_by_count":360},{"year":2020,"cited_by_count":338},{"year":2019,"cited_by_count":161},{"year":2018,"cited_by_count":15}],"updated_date":"2026-05-31T08:46:17.908082","created_date":"2025-10-10T00:00:00"}