{"id":"https://openalex.org/W3108478409","doi":"https://doi.org/10.1109/slt48900.2021.9383502","title":"Look Who\u2019s Not Talking","display_name":"Look Who\u2019s Not Talking","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3108478409","doi":"https://doi.org/10.1109/slt48900.2021.9383502","mag":"3108478409"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/2011.14885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067505925","display_name":"Youngki Kwon","orcid":null},"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"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Youngki Kwon","raw_affiliation_strings":["Naver Corporation, South Korea","Naver Corporation,South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112876029","display_name":"Hee Soo Heo","orcid":null},"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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hee Soo Heo","raw_affiliation_strings":["Naver Corporation, South Korea","Naver Corporation,South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"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/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":"Jaesung Huh","raw_affiliation_strings":["Visual Geometry Group, University of Oxford, UK","University of Oxford,Visual Geometry Group,UK"],"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,Visual Geometry Group,UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086369397","display_name":"Bong\u2010Jin Lee","orcid":"https://orcid.org/0000-0001-7896-2961"},"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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bong-Jin Lee","raw_affiliation_strings":["Naver Corporation, South Korea","Naver Corporation,South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation, South Korea","Naver Corporation,South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Naver Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067505925"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00994716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"567","last_page":"573"},"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":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7284538745880127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6779103875160217},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.553076982498169},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5449004769325256},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4921697974205017},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.41332706809043884},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3749500513076782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3542459011077881},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34486931562423706},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.33575379848480225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7284538745880127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6779103875160217},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.553076982498169},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5449004769325256},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4921697974205017},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.41332706809043884},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3749500513076782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3542459011077881},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34486931562423706},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33575379848480225},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/slt48900.2021.9383502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.14885","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.14885","pdf_url":"https://arxiv.org/pdf/2011.14885","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:3108478409","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.14885.pdf","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.2011.14885","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.14885","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.14885","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.14885","pdf_url":"https://arxiv.org/pdf/2011.14885","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":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W1524333225","https://openalex.org/W1800068500","https://openalex.org/W1921147789","https://openalex.org/W1965819578","https://openalex.org/W1987971958","https://openalex.org/W1996950552","https://openalex.org/W1999454387","https://openalex.org/W2035890032","https://openalex.org/W2046056978","https://openalex.org/W2101261946","https://openalex.org/W2148128296","https://openalex.org/W2150769028","https://openalex.org/W2157363431","https://openalex.org/W2170644918","https://openalex.org/W2194775991","https://openalex.org/W2292259253","https://openalex.org/W2302255633","https://openalex.org/W2394699868","https://openalex.org/W2502312327","https://openalex.org/W2518108298","https://openalex.org/W2604379605","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2737406903","https://openalex.org/W2737498590","https://openalex.org/W2746574320","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2889031312","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2891247151","https://openalex.org/W2892300106","https://openalex.org/W2896538040","https://openalex.org/W2916104401","https://openalex.org/W2963371159","https://openalex.org/W2963470929","https://openalex.org/W2972446354","https://openalex.org/W2972729214","https://openalex.org/W2972949456","https://openalex.org/W2973149080","https://openalex.org/W3008357631","https://openalex.org/W3013020904","https://openalex.org/W3038871978","https://openalex.org/W6601947329","https://openalex.org/W6631362777","https://openalex.org/W6662018943","https://openalex.org/W6724804524","https://openalex.org/W6726497184","https://openalex.org/W6735927292","https://openalex.org/W6741590867","https://openalex.org/W6742126302","https://openalex.org/W6754496211","https://openalex.org/W6780525840"],"related_works":["https://openalex.org/W3146417844","https://openalex.org/W3197331597","https://openalex.org/W3131327410","https://openalex.org/W627704439","https://openalex.org/W3169801369","https://openalex.org/W1576474517","https://openalex.org/W2963796886","https://openalex.org/W2787692317","https://openalex.org/W1813780412","https://openalex.org/W2494981735","https://openalex.org/W2972362771","https://openalex.org/W2972595148","https://openalex.org/W3015923889","https://openalex.org/W3198024420","https://openalex.org/W3119492978","https://openalex.org/W2804625088","https://openalex.org/W2696990509","https://openalex.org/W3034373943","https://openalex.org/W1559425193","https://openalex.org/W2955039818"],"abstract_inverted_index":{"The":[0,14,72],"objective":[1],"of":[2,8,24,32,60,69,107],"this":[3,35],"work":[4],"is":[5,20,64],"speaker":[6,51,62,86,97],"diarisation":[7,25,87],"speech":[9,18,45,70,81,100],"recordings":[10],"'in":[11],"the":[12,50,58,61],"wild'.":[13],"ability":[15],"to":[16,88],"determine":[17],"segments":[19],"a":[21,29,39,92,105],"crucial":[22],"part":[23],"systems,":[26],"accounting":[27],"for":[28,44,80,95],"large":[30],"proportion":[31],"errors.":[33],"In":[34,53],"paper,":[36],"we":[37,55],"present":[38],"simple":[40],"but":[41],"effective":[42,67],"solution":[43],"activity":[46,82,101],"detection":[47],"based":[48],"on":[49,109],"embeddings.":[52],"particular,":[54],"discover":[56],"that":[57],"norm":[59],"embedding":[63],"an":[65,77],"extremely":[66],"indicator":[68],"activity.":[71],"method":[73,117],"does":[74],"not":[75],"require":[76],"independent":[78],"model":[79],"detection,":[83],"therefore":[84],"allows":[85],"be":[89],"performed":[90],"using":[91],"unified":[93],"representation":[94],"both":[96],"modelling":[98],"and":[99,111],"detection.":[102],"We":[103],"perform":[104],"number":[106],"experiments":[108],"in-house":[110],"public":[112],"datasets,":[113],"in":[114],"which":[115],"our":[116],"outperforms":[118],"popular":[119],"baselines.":[120]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}