{"id":"https://openalex.org/W3095972178","doi":"https://doi.org/10.1109/icassp39728.2021.9413815","title":"Playing a Part: Speaker Verification at the movies","display_name":"Playing a Part: Speaker Verification at the movies","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3095972178","doi":"https://doi.org/10.1109/icassp39728.2021.9413815","mag":"3095972178"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.15716","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039721396","display_name":"Andrew Brown","orcid":"https://orcid.org/0000-0002-9556-2633"},"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/I2802123492","display_name":"Oxford Research Group","ror":"https://ror.org/00z4w4f29","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802123492"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Andrew Brown","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, UK","University of Oxford"],"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, UK","institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"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/I2802123492","display_name":"Oxford Research Group","ror":"https://ror.org/00z4w4f29","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802123492"]},{"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":"Jaesung Huh","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, UK","University of Oxford"],"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, UK","institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford","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/I2802123492","display_name":"Oxford Research Group","ror":"https://ror.org/00z4w4f29","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802123492"]},{"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, University of Oxford, UK","University of Oxford"],"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, UK","institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"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":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation, South Korea","University of Oxford"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"University of Oxford","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"]},{"id":"https://openalex.org/I2802123492","display_name":"Oxford Research Group","ror":"https://ror.org/00z4w4f29","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802123492"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, UK","University of Oxford"],"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford, UK","institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039721396"],"corresponding_institution_ids":["https://openalex.org/I2802123492","https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67317387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9994000196456909,"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":0.9988999962806702,"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":0.8016940951347351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7301002740859985},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7175110578536987},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6826780438423157},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6108774542808533},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5787351131439209},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5010976791381836},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4566894471645355},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4462658762931824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4266740679740906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3395724296569824},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11840349435806274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016940951347351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7301002740859985},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7175110578536987},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6826780438423157},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6108774542808533},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5787351131439209},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5010976791381836},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4566894471645355},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4462658762931824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4266740679740906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3395724296569824},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11840349435806274},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.15716","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15716","pdf_url":"https://arxiv.org/pdf/2010.15716","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":"","raw_type":"text"},{"id":"mag:3095972178","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.15716","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.15716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.15716","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/rvvz-va69","is_oa":true,"landing_page_url":"https://doi.org/10.17023/rvvz-va69","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.15716","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15716","pdf_url":"https://arxiv.org/pdf/2010.15716","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":"","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"},{"id":"https://openalex.org/G2018133609","display_name":"Seebibyte: Visual Search for the Era of Big Data","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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095972178.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1979621162","https://openalex.org/W1994832087","https://openalex.org/W2004497042","https://openalex.org/W2046015436","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2360384684","https://openalex.org/W2516764878","https://openalex.org/W2570431255","https://openalex.org/W2593768305","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2747419477","https://openalex.org/W2747872086","https://openalex.org/W2801581493","https://openalex.org/W2808631503","https://openalex.org/W2883440650","https://openalex.org/W2889500840","https://openalex.org/W2890964092","https://openalex.org/W2901368553","https://openalex.org/W2950864153","https://openalex.org/W2962749043","https://openalex.org/W2962788262","https://openalex.org/W2962788625","https://openalex.org/W2962808524","https://openalex.org/W2962897020","https://openalex.org/W2963371159","https://openalex.org/W2963450999","https://openalex.org/W2963839617","https://openalex.org/W2964154960","https://openalex.org/W2972703466","https://openalex.org/W2981087920","https://openalex.org/W3013020904","https://openalex.org/W3015368919","https://openalex.org/W3015443711","https://openalex.org/W3015598461","https://openalex.org/W3015734344","https://openalex.org/W3025075133","https://openalex.org/W3028436280","https://openalex.org/W3090254849","https://openalex.org/W3094665028","https://openalex.org/W3107806026","https://openalex.org/W3111481301","https://openalex.org/W6631362777","https://openalex.org/W6682600690","https://openalex.org/W6746282794","https://openalex.org/W6748663801","https://openalex.org/W6753016063","https://openalex.org/W6776909130","https://openalex.org/W6779669310","https://openalex.org/W6783527727","https://openalex.org/W6787439801"],"related_works":["https://openalex.org/W3160743249","https://openalex.org/W3048150217","https://openalex.org/W1936725236","https://openalex.org/W2186614452","https://openalex.org/W3163320179","https://openalex.org/W2464377622","https://openalex.org/W2995545690","https://openalex.org/W283543405","https://openalex.org/W3092028069","https://openalex.org/W3127127511","https://openalex.org/W3015734344","https://openalex.org/W3199506689","https://openalex.org/W155075780","https://openalex.org/W3213458023","https://openalex.org/W2050069490","https://openalex.org/W3184648662","https://openalex.org/W2809767522","https://openalex.org/W3191488649","https://openalex.org/W3025044797","https://openalex.org/W2972659941"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,10,94,103],"this":[3,124],"work":[4],"is":[5,149],"to":[6,27,75],"investigate":[7],"the":[8,33,76,101,128],"performance":[9,102,120],"popular":[11],"speaker":[12,43,83,105,116],"recognition":[13,44,84,106],"models":[14,107,132],"on":[15,108,123],"speech":[16,49],"segments":[17],"from":[18,53],"movies,":[19],"where":[20],"often":[21],"actors":[22],"intentionally":[23],"disguise":[24],"their":[25],"voice":[26],"play":[28],"a":[29,40,92],"character.":[30],"We":[31,38,90,112,138],"make":[32],"following":[34],"three":[35],"contributions:":[36],"(i)":[37],"collect":[39],"novel,":[41],"challenging":[42],"dataset":[45],"called":[46],"VoxMovies,":[47],"with":[48,61],"for":[50,153],"856":[51],"identities":[52],"almost":[54],"4000":[55],"movie":[56],"clips.":[57],"VoxMovies":[58],"contains":[59],"utterances":[60,80],"varying":[62],"emotion,":[63],"accents":[64],"and":[65,68,99,118,135],"background":[66],"noise,":[67],"therefore":[69],"comprises":[70],"an":[71],"entirely":[72],"different":[73],"domain":[74,95,142],"interview-style,":[77],"emotionally":[78],"calm":[79],"in":[81,130],"current":[82],"datasets":[85],"such":[86],"as":[87],"VoxCeleb;":[88],"(ii)":[89],"provide":[91],"number":[93],"adaptation":[96,143],"evaluation":[97,110],"sets,":[98],"benchmark":[100],"state-of-the-art":[104],"these":[109],"pairs.":[111],"demonstrate":[113],"that":[114,140],"both":[115],"verification":[117],"identification":[119],"drops":[121],"steeply":[122],"new":[125],"data,":[126],"showing":[127],"challenge":[129],"transferring":[131],"across":[133],"domains;":[134],"finally":[136],"(iii)":[137],"show":[139],"simple":[141],"paradigms":[144],"improve":[145],"performance,":[146],"but":[147],"there":[148],"still":[150],"large":[151],"room":[152],"improvement.":[154]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}