{"id":"https://openalex.org/W3095678104","doi":"https://doi.org/10.1109/icassp39728.2021.9413948","title":"The ins and outs of speaker recognition: lessons from VoxSRC 2020","display_name":"The ins and outs of speaker recognition: lessons from VoxSRC 2020","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3095678104","doi":"https://doi.org/10.1109/icassp39728.2021.9413948","mag":"3095678104"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413948","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/2010.15809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019238472","display_name":"Yoohwan Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]},{"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":"Yoohwan Kwon","raw_affiliation_strings":["Naver Corporation","Yonsei University","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"Yonsei University","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070613375","display_name":"Hee-Soo Heo","orcid":"https://orcid.org/0000-0003-1567-123X"},"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","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"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","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"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","NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"Naver Corporation","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019238472"],"corresponding_institution_ids":["https://openalex.org/I193775966","https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00938037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5809","last_page":"5813"},"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/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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.8438066244125366},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.8014137744903564},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7914068698883057},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6801614165306091},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5129244327545166},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45666933059692383},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4321375787258148},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42339983582496643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3858979642391205}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438066244125366},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.8014137744903564},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7914068698883057},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6801614165306091},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5129244327545166},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45666933059692383},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4321375787258148},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42339983582496643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3858979642391205},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413948","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:2010.15809","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15809","pdf_url":"https://arxiv.org/pdf/2010.15809","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:3095678104","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.15809.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.2010.15809","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.15809","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/awgv-3k67","is_oa":true,"landing_page_url":"https://doi.org/10.17023/awgv-3k67","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:2010.15809","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15809","pdf_url":"https://arxiv.org/pdf/2010.15809","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":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095678104.pdf","grobid_xml":"https://content.openalex.org/works/W3095678104.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W2117671523","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2502312327","https://openalex.org/W2601450892","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2802488037","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2938358845","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2963371159","https://openalex.org/W2964052309","https://openalex.org/W2969985801","https://openalex.org/W2973149080","https://openalex.org/W2981461916","https://openalex.org/W2991951409","https://openalex.org/W3013020904","https://openalex.org/W3014217528","https://openalex.org/W3015368919","https://openalex.org/W3015443711","https://openalex.org/W3024869864","https://openalex.org/W3025075133","https://openalex.org/W3044308976","https://openalex.org/W3090254849","https://openalex.org/W3096235116","https://openalex.org/W3097256596","https://openalex.org/W3103152812","https://openalex.org/W6688816777","https://openalex.org/W6724804524","https://openalex.org/W6735236233","https://openalex.org/W6769178842","https://openalex.org/W6771538394","https://openalex.org/W6781368565","https://openalex.org/W6783527727"],"related_works":["https://openalex.org/W3163505255","https://openalex.org/W2165340520","https://openalex.org/W3107647211","https://openalex.org/W3021321596","https://openalex.org/W3176848203","https://openalex.org/W2899351468","https://openalex.org/W2808631503","https://openalex.org/W13110487","https://openalex.org/W2092160942","https://openalex.org/W2914876604","https://openalex.org/W2294192652","https://openalex.org/W2951130829","https://openalex.org/W3185349949","https://openalex.org/W3044308976","https://openalex.org/W3008613924","https://openalex.org/W2558547107","https://openalex.org/W3135281744","https://openalex.org/W3206252155","https://openalex.org/W3026496355","https://openalex.org/W3209984917"],"abstract_inverted_index":{"The":[0,25,102],"VoxCeleb":[1],"Speaker":[2],"Recognition":[3],"Challenge":[4],"(VoxSRC)":[5],"at":[6],"Interspeech":[7],"2020":[8],"offers":[9],"a":[10,57,99],"challenging":[11,39],"evaluation":[12],"for":[13,49],"speaker":[14,32,50],"recognition":[15,33,51],"systems,":[16],"which":[17],"includes":[18],"celebrities":[19],"playing":[20],"different":[21],"parts":[22],"in":[23,37,111],"movies.":[24],"goal":[26],"of":[27,34,44,59],"this":[28,66],"work":[29],"is":[30],"robust":[31],"utterances":[35],"recorded":[36],"these":[38],"environments.":[40],"We":[41],"utilise":[42],"variants":[43],"the":[45,105,112],"popular":[46],"ResNet":[47],"architecture":[48],"and":[52,62,84,98],"perform":[53],"extensive":[54],"experiments":[55],"using":[56],"range":[58],"loss":[60],"functions":[61],"training":[63,72],"parameters.":[64],"To":[65],"end,":[67],"we":[68],"optimise":[69],"an":[70],"efficient":[71],"framework":[73],"that":[74],"allows":[75],"powerful":[76],"models":[77,88,97],"to":[78],"be":[79],"trained":[80,87],"with":[81,95],"limited":[82],"time":[83],"resources.":[85],"Our":[86],"demonstrate":[89],"improvements":[90],"over":[91],"most":[92],"existing":[93],"works":[94],"lighter":[96],"simple":[100],"pipeline.":[101],"paper":[103],"shares":[104],"lessons":[106],"learned":[107],"from":[108],"our":[109],"participation":[110],"challenge.":[113]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
