{"id":"https://openalex.org/W3200796884","doi":"https://doi.org/10.1109/asru51503.2021.9688044","title":"Overlap-Aware Low-Latency Online Speaker Diarization Based on End-to-End Local Segmentation","display_name":"Overlap-Aware Low-Latency Online Speaker Diarization Based on End-to-End Local Segmentation","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3200796884","doi":"https://doi.org/10.1109/asru51503.2021.9688044","mag":"3200796884"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688044","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03375330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017320570","display_name":"Juan Manuel Coria","orcid":"https://orcid.org/0000-0002-5035-147X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Juan M. Coria","raw_affiliation_strings":["Université Paris-Saclay CNRS, LISN,Orsay,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay CNRS, LISN,Orsay,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108138275","display_name":"Herv\u00e9 Bredin","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herve Bredin","raw_affiliation_strings":["IRIT, Université de Toulouse, CNRS,Toulouse,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRIT, Université de Toulouse, CNRS,Toulouse,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4210160189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000557257","display_name":"Sahar Ghannay","orcid":"https://orcid.org/0000-0002-7531-2522"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sahar Ghannay","raw_affiliation_strings":["Université Paris-Saclay CNRS, LISN,Orsay,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay CNRS, LISN,Orsay,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001616788","display_name":"Sophie Rosset","orcid":"https://orcid.org/0000-0002-6865-4989"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sophie Rosset","raw_affiliation_strings":["Université Paris-Saclay CNRS, LISN,Orsay,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université Paris-Saclay CNRS, LISN,Orsay,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1139","last_page":"1146"},"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":0.9998999834060669,"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":0.9998000264167786,"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":0.8046867847442627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8010150194168091},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7151604294776917},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6903238296508789},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6408040523529053},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6316946148872375},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5579005479812622},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5267386436462402},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4382089674472809},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4220826029777527},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4144655466079712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.405742347240448},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3856362998485565},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3535742163658142},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12979251146316528},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09637430310249329}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8046867847442627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010150194168091},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7151604294776917},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6903238296508789},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6408040523529053},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6316946148872375},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5579005479812622},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5267386436462402},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4382089674472809},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4220826029777527},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4144655466079712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.405742347240448},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3856362998485565},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3535742163658142},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12979251146316528},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09637430310249329},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru51503.2021.9688044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688044","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03375330v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03375330","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Automatic Speech Recognition and Unserstanding Workshop, Dec 2021, Cartagena, Colombia. pp.1139-1146, ⟨10.1109/ASRU51503.2021.9688044⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03375330v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03375330","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Automatic Speech Recognition and Unserstanding Workshop, Dec 2021, Cartagena, Colombia. pp.1139-1146, ⟨10.1109/ASRU51503.2021.9688044⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2116133628","display_name":"ComPLetely Unsupervised Multimodal Character identification On TV series and movies","funder_award_id":"ANR-16-CE92-0025","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G2160114395","display_name":null,"funder_award_id":"AD011012177","funder_id":"https://openalex.org/F4320326256","funder_display_name":"Grand \u00c9quipement National De Calcul Intensif"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1608667326","https://openalex.org/W2081074144","https://openalex.org/W2083751884","https://openalex.org/W2097583714","https://openalex.org/W2106411961","https://openalex.org/W2219249508","https://openalex.org/W2555915854","https://openalex.org/W2726515241","https://openalex.org/W2750259098","https://openalex.org/W2808631503","https://openalex.org/W2889381673","https://openalex.org/W2890964092","https://openalex.org/W2963745998","https://openalex.org/W2964052309","https://openalex.org/W2969985801","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3015544392","https://openalex.org/W3015780472","https://openalex.org/W3035193494","https://openalex.org/W3038871978","https://openalex.org/W3095212884","https://openalex.org/W3105031100","https://openalex.org/W3108962419","https://openalex.org/W3123299152","https://openalex.org/W3157070662","https://openalex.org/W3163019736","https://openalex.org/W3163903701","https://openalex.org/W3166898278","https://openalex.org/W3178462146","https://openalex.org/W3196595845","https://openalex.org/W3197762688","https://openalex.org/W3198482860","https://openalex.org/W4297788887","https://openalex.org/W6636488977","https://openalex.org/W6676179485","https://openalex.org/W6688816777","https://openalex.org/W6740167877","https://openalex.org/W6743299418","https://openalex.org/W6748010250","https://openalex.org/W6754192381","https://openalex.org/W6764041223","https://openalex.org/W6777976503","https://openalex.org/W6779429391","https://openalex.org/W6784053002","https://openalex.org/W6785552926","https://openalex.org/W6786127183","https://openalex.org/W6789114347"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"We":[0],"propose":[1,57],"to":[2,17,33,48,72,76,95,126],"address":[3],"online":[4],"speaker":[5],"diarization":[6,15],"as":[7],"a":[8,18,42,58,131,138],"combination":[9],"of":[10,27,37,41,61,115,130,141,144],"incremental":[11,106],"clustering":[12,107],"and":[13,50,124,135,153],"local":[14,98],"applied":[16],"rolling":[19],"buffer":[20],"updated":[21],"every":[22],"500ms.":[23],"Every":[24],"single":[25],"step":[26,94],"the":[28,38,62,69,79,91,105,113,116,128,142,147],"proposed":[29,44,117],"pipeline":[30],"is":[31],"designed":[32],"take":[34],"full":[35],"advantage":[36],"strong":[39],"ability":[40],"recently":[43],"end-to-end":[45],"overlap-aware":[46],"segmentation":[47,80,93],"detect":[49],"separate":[51],"overlapping":[52],"speakers.":[53,84],"In":[54],"particular,":[55],"we":[56,86,110,136],"modified":[59],"version":[60],"statistics":[63],"pooling":[64],"layer":[65],"(initially":[66],"introduced":[67],"in":[68],"x-vector":[70],"architecture)":[71],"give":[73],"less":[74],"weight":[75],"frames":[77],"where":[78],"model":[81],"predicts":[82],"simultaneous":[83],"Furthermore,":[85],"derive":[87],"cannot-link":[88],"constraints":[89],"from":[90,100],"initial":[92],"prevent":[96],"two":[97],"speakers":[99],"being":[101],"wrongfully":[102],"merged":[103],"during":[104],"step.":[108],"Finally,":[109],"show":[111],"how":[112],"latency":[114,145],"approach":[118],"can":[119],"be":[120],"adjusted":[121],"between":[122],"500ms":[123],"5s":[125],"match":[127],"requirements":[129],"particular":[132],"use":[133],"case,":[134],"provide":[137],"systematic":[139],"analysis":[140],"influence":[143],"on":[146],"overall":[148],"performance":[149],"(on":[150],"AMI,":[151],"DIHARD":[152],"VoxConverse).":[154]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}