{"id":"https://openalex.org/W3151768066","doi":"https://doi.org/10.21437/interspeech.2021-448","title":"Adapting Speaker Embeddings for Speaker Diarisation","display_name":"Adapting Speaker Embeddings for Speaker Diarisation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3151768066","doi":"https://doi.org/10.21437/interspeech.2021-448","mag":"3151768066"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-448","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/2104.02879","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067505925","display_name":"Youngki Kwon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Youngki Kwon","raw_affiliation_strings":["NAVER CORPORATION"],"affiliations":[{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jee-weon Jung","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"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 (South Korea), Seongnam-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver (South Korea), Seongnam-si, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022133103","display_name":"You Jin Kim","orcid":"https://orcid.org/0000-0002-4952-5532"},"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":"You Jin Kim","raw_affiliation_strings":["Naver (South Korea), Seongnam-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver (South Korea), Seongnam-si, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"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 (South Korea), Seongnam-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver (South Korea), Seongnam-si, 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 (South Korea), Seongnam-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver (South Korea), Seongnam-si, South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067505925"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04281321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3101","last_page":"3105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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":0.9973000288009644,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7911058664321899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7541662454605103},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7223824262619019},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6991296410560608},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6861464381217957},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6075913310050964},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5897940993309021},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.577301025390625},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5755822062492371},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4700022339820862},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4699796736240387},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4535572826862335},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4232838749885559},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.41380515694618225},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4109100103378296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34413450956344604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10584035515785217},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.058133870363235474}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7911058664321899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541662454605103},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7223824262619019},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6991296410560608},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6861464381217957},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6075913310050964},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5897940993309021},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.577301025390625},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5755822062492371},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4700022339820862},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4699796736240387},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4535572826862335},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4232838749885559},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.41380515694618225},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4109100103378296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34413450956344604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10584035515785217},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.058133870363235474},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-448","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.02879","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02879","pdf_url":"https://arxiv.org/pdf/2104.02879","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:3151768066","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.02879.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.2104.02879","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.02879","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:2104.02879","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.02879","pdf_url":"https://arxiv.org/pdf/2104.02879","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3151768066.pdf","grobid_xml":"https://content.openalex.org/works/W3151768066.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W1987971958","https://openalex.org/W2035890032","https://openalex.org/W2125336414","https://openalex.org/W2132914434","https://openalex.org/W2138730338","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2394699868","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2805869973","https://openalex.org/W2808631503","https://openalex.org/W2889418727","https://openalex.org/W2952191002","https://openalex.org/W2963403868","https://openalex.org/W2963460857","https://openalex.org/W2969985801","https://openalex.org/W2972449503","https://openalex.org/W2972680151","https://openalex.org/W2981087920","https://openalex.org/W2981103786","https://openalex.org/W3013020904","https://openalex.org/W3015463733","https://openalex.org/W3016400019","https://openalex.org/W3025260599","https://openalex.org/W3038871978","https://openalex.org/W3090254849","https://openalex.org/W3108962419","https://openalex.org/W3123299152","https://openalex.org/W3125596972","https://openalex.org/W3128688470","https://openalex.org/W3146417844","https://openalex.org/W3162899647","https://openalex.org/W3163019736","https://openalex.org/W3163505255","https://openalex.org/W3208240190"],"related_works":["https://openalex.org/W3197331597","https://openalex.org/W3131327410","https://openalex.org/W3108478409","https://openalex.org/W3093681215","https://openalex.org/W3015988545","https://openalex.org/W3198024420","https://openalex.org/W3015826515","https://openalex.org/W3015923889","https://openalex.org/W3015555484","https://openalex.org/W2901404901","https://openalex.org/W3016234652","https://openalex.org/W2938358845","https://openalex.org/W3164772801","https://openalex.org/W3162184950","https://openalex.org/W2108636611","https://openalex.org/W3203417382","https://openalex.org/W2972362771","https://openalex.org/W3015306128","https://openalex.org/W3109950060","https://openalex.org/W2972369255"],"abstract_inverted_index":{"The":[0,17,90],"goal":[1],"of":[2,14,19,27,82,102,111,115],"this":[3,53],"paper":[4],"is":[5,22,84],"to":[6,24,44,63,99],"adapt":[7,65],"speaker":[8,15,20,28,49,67],"embeddings":[9,21,41,68],"for":[10,69],"solving":[11],"the":[12,25,36,48,66,100,103,120],"problem":[13],"diarisation.":[16],"quality":[18],"paramount":[23],"performance":[26,101],"diarisation":[29,104,116],"systems.":[30],"Despite":[31],"this,":[32],"prior":[33],"works":[34],"in":[35,113],"field":[37],"have":[38],"directly":[39],"used":[40,62],"designed":[42],"only":[43],"be":[45,61],"effective":[46],"on":[47,86],"verification":[50],"task.":[51],"In":[52],"paper,":[54],"we":[55],"propose":[56],"three":[57,95],"techniques":[58,96],"that":[59,93],"can":[60],"better":[64],"diarisation:":[70],"dimensionality":[71],"reduction,":[72],"attention-based":[73],"embedding":[74],"aggregation,":[75],"and":[76],"non-speech":[77],"clustering.":[78],"A":[79],"wide":[80],"range":[81],"experiments":[83],"performed":[85],"various":[87],"challenging":[88],"datasets.":[89],"results":[91],"demonstrate":[92],"all":[94],"contribute":[97],"positively":[98],"system":[105],"achieving":[106],"an":[107],"average":[108],"relative":[109],"improvement":[110],"25.07%":[112],"terms":[114],"error":[117],"rate":[118],"over":[119],"baseline.":[121]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}
