{"id":"https://openalex.org/W3038871978","doi":"https://doi.org/10.21437/interspeech.2020-2337","title":"Spot the Conversation: Speaker Diarisation in the Wild","display_name":"Spot the Conversation: Speaker Diarisation in the Wild","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3038871978","doi":"https://doi.org/10.21437/interspeech.2020-2337","mag":"3038871978"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.01216","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"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["GB","KR"],"is_corresponding":true,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Visual Geometry Group, Department of Engineering Science, University of Oxford, UK","Naver Corporation, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, Department of Engineering Science, University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114067866","display_name":"Jaesung Huh","orcid":"https://orcid.org/0000-0001-7247-6401"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]},{"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","KR"],"is_corresponding":false,"raw_author_name":"Jaesung Huh","raw_affiliation_strings":["Naver Corporation, South Korea","Visual Geometry Group, Department of Engineering Science, University of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"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":"middle","author":{"id":"https://openalex.org/A5018690028","display_name":"Triantafyllos Afouras","orcid":"https://orcid.org/0000-0002-3935-9681"},"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":"Triantafyllos Afouras","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":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038723822"],"corresponding_institution_ids":["https://openalex.org/I40120149","https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":12.6113,"has_fulltext":false,"cited_by_count":142,"citation_normalized_percentile":{"value":0.99262739,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"303"},"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":0.9997000098228455,"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":0.8485463261604309},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8297178745269775},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7439575791358948},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6277709007263184},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6134529709815979},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.554585874080658},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5107741355895996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46130210161209106},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3743172883987427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8485463261604309},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8297178745269775},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7439575791358948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6277709007263184},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6134529709815979},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.554585874080658},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5107741355895996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46130210161209106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3743172883987427},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2020-2337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.01216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.01216","pdf_url":"https://arxiv.org/pdf/2007.01216","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:718ffc9c-a542-4dd5-afbb-f9972ba0a1ff","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:718ffc9c-a542-4dd5-afbb-f9972ba0a1ff","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":"Symplectic Elements","raw_type":"Conference item"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.01216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.01216","pdf_url":"https://arxiv.org/pdf/2007.01216","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":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1524222317","https://openalex.org/W1579838312","https://openalex.org/W1589137271","https://openalex.org/W1591607137","https://openalex.org/W1965819578","https://openalex.org/W2035890032","https://openalex.org/W2064364374","https://openalex.org/W2101702585","https://openalex.org/W2108598243","https://openalex.org/W2125336414","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2394699868","https://openalex.org/W2405137844","https://openalex.org/W2604379605","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2889031312","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2893436174","https://openalex.org/W2896538040","https://openalex.org/W2916104401","https://openalex.org/W2942265585","https://openalex.org/W2950864153","https://openalex.org/W2963307811","https://openalex.org/W2964171275","https://openalex.org/W2972449503","https://openalex.org/W2972513594","https://openalex.org/W2972729214","https://openalex.org/W2981087920","https://openalex.org/W2981630388","https://openalex.org/W3013020904","https://openalex.org/W3015371781","https://openalex.org/W3099206234","https://openalex.org/W3123318516"],"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":{"The":[0],"goal":[1],"of":[2,8,32,62,102],"this":[3,74],"paper":[4],"is":[5],"speaker":[6,34,40,44,109],"diarisation":[7,24,69,80],"videos":[9,67],"collected":[10,84],"\u2018in":[11,86],"the":[12,60,87,96],"wild\u2019.\\n<br>\\nWe":[13],"make":[14],"three":[15],"key":[16],"contributions.":[17],"First,":[18],"we":[19,47,72,91],"propose":[20],"an":[21],"automatic":[22],"audio-visual":[23,37],"method":[25,30,50],"for":[26],"YouTube":[27],"videos.":[28],"Our":[29,99],"consists":[31,101],"active":[33],"detection":[35],"using":[36,42],"methods":[38],"and":[39,107,111],"verification":[41],"self-enrolled":[43],"models.":[45],"Second,":[46],"integrate":[48],"our":[49],"into":[51],"a":[52,78,105],"semi-automatic":[53],"dataset":[54,81,100],"creation":[55],"pipeline":[56,75],"which":[57,90],"significantly":[58],"reduces":[59],"number":[61],"hours":[63],"required":[64],"to":[65,76,95],"annotate":[66],"with":[68],"labels.":[70],"Finally,":[71],"use":[73],"create":[77],"large-scale":[79],"called":[82],"VoxConverse,":[83],"from":[85],"wild\u2019":[88],"videos,":[89],"will":[92],"release":[93],"publicly":[94],"research":[97],"community.":[98],"overlapping":[103],"speech,":[104],"large":[106],"diverse":[108],"pool,":[110],"challenging":[112],"background":[113],"conditions.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}