{"id":"https://openalex.org/W2981946421","doi":"https://doi.org/10.1109/icassp40776.2020.9053096","title":"Overlap-Aware Diarization: Resegmentation Using Neural End-to-End Overlapped Speech Detection","display_name":"Overlap-Aware Diarization: Resegmentation Using Neural End-to-End Overlapped Speech Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981946421","doi":"https://doi.org/10.1109/icassp40776.2020.9053096","mag":"2981946421"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/1910.11646","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017228751","display_name":"Latan\u00e9 Bullock","orcid":"https://orcid.org/0000-0003-1257-7221"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Latane Bullock","raw_affiliation_strings":["Rice University, Houston, USA","Rice University , Houston , USA"],"affiliations":[{"raw_affiliation_string":"Rice University, Houston, USA","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University , Houston , USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079257674","display_name":"Herv\u00e9 Bredin","orcid":"https://orcid.org/0000-0002-3739-925X"},"institutions":[{"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/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herve Bredin","raw_affiliation_strings":["LIMSI, CNRS, Univ. Paris-Sud, Universit\u00e9 Paris-Saclay, Orsay, France","LIMSI, CNRS, Univ. Paris-Sud, Universit\u00e9 Paris-Saclay,Orsay,France"],"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS, Univ. Paris-Sud, Universit\u00e9 Paris-Saclay, Orsay, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I102197404","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI, CNRS, Univ. Paris-Sud, Universit\u00e9 Paris-Saclay,Orsay,France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210115485","https://openalex.org/I102197404","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leibny Paola Garcia-Perera","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA","Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, USA#TAB#","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017228751"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":0.8228,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78165757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7114","last_page":"7118"},"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7716344594955444},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7615389823913574},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7282695770263672},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6164667010307312},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5969816446304321},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.48156335949897766},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.459094375371933},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4492350220680237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39626505970954895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3679267466068268},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.272258996963501},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22258344292640686},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08368262648582458},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06862214207649231}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7716344594955444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615389823913574},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7282695770263672},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6164667010307312},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5969816446304321},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.48156335949897766},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.459094375371933},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4492350220680237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39626505970954895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3679267466068268},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.272258996963501},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22258344292640686},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08368262648582458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06862214207649231},{"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.11646","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11646","pdf_url":"https://arxiv.org/pdf/1910.11646","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":null,"raw_type":"text"},{"id":"mag:2981946421","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.11646.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":"pmh:oai:HAL:hal-02995367v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02995367","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain. pp.7114-7118, &#x27E8;10.1109/ICASSP40776.2020.9053096&#x27E9;","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1910.11646","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.11646","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":"article"},{"id":"doi:10.17023/rmnz-9x87","is_oa":true,"landing_page_url":"https://doi.org/10.17023/rmnz-9x87","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:1910.11646","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11646","pdf_url":"https://arxiv.org/pdf/1910.11646","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981946421.pdf","grobid_xml":"https://content.openalex.org/works/W2981946421.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W72302491","https://openalex.org/W80245499","https://openalex.org/W1606894530","https://openalex.org/W2009876684","https://openalex.org/W2083751884","https://openalex.org/W2097583714","https://openalex.org/W2151572725","https://openalex.org/W2169264834","https://openalex.org/W2402428045","https://openalex.org/W2626961305","https://openalex.org/W2745338770","https://openalex.org/W2750259098","https://openalex.org/W2805869973","https://openalex.org/W2889203268","https://openalex.org/W2898395910","https://openalex.org/W2964052309","https://openalex.org/W2968071640","https://openalex.org/W2972449503","https://openalex.org/W3015783745","https://openalex.org/W3208240190","https://openalex.org/W6602944679","https://openalex.org/W6739192308","https://openalex.org/W6766542914","https://openalex.org/W6931392099"],"related_works":["https://openalex.org/W3015780472","https://openalex.org/W3157070662","https://openalex.org/W2797412426","https://openalex.org/W3210727692","https://openalex.org/W2103348173","https://openalex.org/W2972346374","https://openalex.org/W3010196324","https://openalex.org/W2971668813","https://openalex.org/W2782767377","https://openalex.org/W277919747","https://openalex.org/W79817894","https://openalex.org/W3182885906","https://openalex.org/W3160044950","https://openalex.org/W3162648834","https://openalex.org/W2188385754","https://openalex.org/W3008357631","https://openalex.org/W2921428693","https://openalex.org/W2534034218","https://openalex.org/W3191883738","https://openalex.org/W3164674954"],"abstract_inverted_index":{"We":[0,65],"address":[1],"the":[2,48,59,79],"problem":[3],"of":[4],"effectively":[5],"handling":[6,100],"overlapping":[7],"speech":[8],"in":[9,32,47,72],"a":[10,16,35,73],"diarization":[11],"system.":[12,81],"First,":[13],"we":[14],"detail":[15],"neural":[17],"Long":[18],"Short-Term":[19],"Memory-":[20],"based":[21],"architecture":[22],"for":[23,44,99],"overlap":[24,28,52],"detection.":[25],"Secondly,":[26],"detected":[27],"regions":[29],"are":[30],"exploited":[31],"conjunction":[33],"with":[34],"frame-level":[36],"speaker":[37],"posterior":[38],"matrix":[39],"to":[40,92],"make":[41],"two-speaker":[42],"assignments":[43],"overlapped":[45],"frames":[46],"resegmentation":[49,68],"step.":[50],"The":[51],"detection":[53],"module":[54],"achieves":[55],"state-of-the-art":[56],"performance":[57],"on":[58,69],"AMI,":[60,70],"DIHARD,":[61],"and":[62],"ETAPE":[63],"corpora.":[64],"apply":[66],"overlap-aware":[67,93],"resulting":[71],"20%":[74],"relative":[75],"DER":[76],"reduction":[77],"over":[78],"baseline":[80],"While":[82],"this":[83],"approach":[84],"is":[85],"by":[86],"no":[87],"means":[88],"an":[89],"end-all":[90],"solution":[91],"diarization,":[94],"it":[95],"reveals":[96],"promising":[97],"directions":[98],"overlap.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
