{"id":"https://openalex.org/W3093864324","doi":"https://doi.org/10.1109/icassp39728.2021.9414315","title":"Analysis of the but Diarization System for Voxconverse Challenge","display_name":"Analysis of the but Diarization System for Voxconverse Challenge","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3093864324","doi":"https://doi.org/10.1109/icassp39728.2021.9414315","mag":"3093864324"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414315","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.11718","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084170554","display_name":"Federico Landini","orcid":"https://orcid.org/0000-0003-0379-9834"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Federico Landini","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008717681","display_name":"Ond\u0159ej Glembek","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ondrej Glembek","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076315361","display_name":"Pavel Mat\u011bjka","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Pavel Matejka","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043239262","display_name":"Johan Rohdin","orcid":"https://orcid.org/0000-0003-0978-2064"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Johan Rohdin","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035162271","display_name":"Mireia D\u00edez","orcid":"https://orcid.org/0000-0001-7894-8377"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Mireia Diez","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043410084","display_name":"Anna Silnova","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Anna Silnova","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5819","last_page":"5823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.8889343738555908},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.875718355178833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.674579918384552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.621152937412262},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6162468194961548},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5471295118331909},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5400207042694092},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5253828763961792},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4986996650695801},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43878239393234253},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4238688051700592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42142626643180847},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4159787893295288},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21202340722084045},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0915873646736145}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8889343738555908},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.875718355178833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.674579918384552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.621152937412262},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6162468194961548},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5471295118331909},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5400207042694092},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5253828763961792},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4986996650695801},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43878239393234253},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4238688051700592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42142626643180847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4159787893295288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21202340722084045},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0915873646736145},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414315","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:2010.11718","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11718","pdf_url":"https://arxiv.org/pdf/2010.11718","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3093864324","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.11718.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.2010.11718","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.11718","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/337r-xr98","is_oa":true,"landing_page_url":"https://doi.org/10.17023/337r-xr98","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.11718","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11718","pdf_url":"https://arxiv.org/pdf/2010.11718","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093864324.pdf","grobid_xml":"https://content.openalex.org/works/W3093864324.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W72302491","https://openalex.org/W202968570","https://openalex.org/W1524333225","https://openalex.org/W1591607137","https://openalex.org/W2097583714","https://openalex.org/W2125336414","https://openalex.org/W2164502538","https://openalex.org/W2194775991","https://openalex.org/W2288371874","https://openalex.org/W2395750323","https://openalex.org/W2406312423","https://openalex.org/W2799473636","https://openalex.org/W2808631503","https://openalex.org/W2889031312","https://openalex.org/W2890964092","https://openalex.org/W2962898354","https://openalex.org/W2963197115","https://openalex.org/W2972449503","https://openalex.org/W3015463733","https://openalex.org/W3015544392","https://openalex.org/W3015780472","https://openalex.org/W3015783745","https://openalex.org/W3038871978","https://openalex.org/W3101648800","https://openalex.org/W3210615406","https://openalex.org/W6602944679","https://openalex.org/W6608271823","https://openalex.org/W6631362777","https://openalex.org/W6678809451","https://openalex.org/W6713727690","https://openalex.org/W6766380642"],"related_works":["https://openalex.org/W180663858","https://openalex.org/W2578538565","https://openalex.org/W2972949456","https://openalex.org/W71947379","https://openalex.org/W2110783210","https://openalex.org/W3158287709","https://openalex.org/W3121485920","https://openalex.org/W3095129427","https://openalex.org/W3170555338","https://openalex.org/W202282565","https://openalex.org/W2106780157","https://openalex.org/W2142333570","https://openalex.org/W3008849579","https://openalex.org/W2981473019","https://openalex.org/W1519129566","https://openalex.org/W2042606741","https://openalex.org/W2153342002","https://openalex.org/W3008924147","https://openalex.org/W1556857061","https://openalex.org/W159467828"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,7,11,15,24,73,77,80,92,97,107],"system":[4,28,88],"developed":[5],"by":[6,45],"BUT":[8],"team":[9],"for":[10,70],"fourth":[12],"track":[13],"of":[14,30,72,79,84,96],"VoxCeleb":[16],"Speaker":[17],"Recognition":[18],"Challenge,":[19],"focusing":[20],"on":[21,23,57],"diarization":[22,46],"VoxConverse":[25],"dataset.":[26],"The":[27],"consists":[29],"signal":[31],"pre-processing,":[32],"voice":[33],"activity":[34],"detection,":[35],"speaker":[36],"embedding":[37],"extraction,":[38],"an":[39],"initial":[40],"agglomerative":[41],"hierarchical":[42],"clustering":[43],"followed":[44],"using":[47],"a":[48,53],"Bayesian":[49],"hidden":[50],"Markov":[51],"model,":[52],"reclustering":[54],"step":[55],"based":[56],"per-speaker":[58],"global":[59],"embeddings":[60],"and":[61,65,75,103],"overlapped":[62],"speech":[63],"detection":[64],"handling.":[66],"We":[67],"provide":[68],"comparisons":[69],"each":[71],"steps":[74],"share":[76],"implementation":[78],"most":[81],"relevant":[82],"modules":[83],"our":[85],"system.":[86],"Our":[87],"scored":[89],"second":[90],"in":[91,94],"challenge":[93],"terms":[95],"primary":[98],"metric":[99,109],"(diarization":[100],"error":[101,111],"rate)":[102],"first":[104],"according":[105],"to":[106],"secondary":[108],"(Jaccard":[110],"rate).":[112]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
