{"id":"https://openalex.org/W3094706770","doi":"https://doi.org/10.1109/slt48900.2021.9383490","title":"DOVER-Lap: A Method for Combining Overlap-Aware Diarization Outputs","display_name":"DOVER-Lap: A Method for Combining Overlap-Aware Diarization Outputs","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3094706770","doi":"https://doi.org/10.1109/slt48900.2021.9383490","mag":"3094706770"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/2011.01997","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004777817","display_name":"Desh Raj","orcid":"https://orcid.org/0000-0002-5038-9400"},"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":"Desh Raj","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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, MD, USA","Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101619225","display_name":"Zili Huang","orcid":"https://orcid.org/0000-0003-1238-8017"},"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":"Zili Huang","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corp., Beijing, China","[Xiaomi Corp, Beijing, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corp., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"[Xiaomi Corp, Beijing, China]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa Speech, Sunnyvale, CA, USA","[Amazon Alexa Speech, Sunnyvale, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa Speech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon Alexa Speech, Sunnyvale, CA, USA]","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"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":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"The Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA,21218","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"881","last_page":"888"},"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":0.9991999864578247,"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":0.8397572040557861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7358049750328064},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5714541673660278},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5539742708206177},{"id":"https://openalex.org/keywords/majority-rule","display_name":"Majority rule","score":0.47029492259025574},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46115896105766296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4297574758529663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42747583985328674},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33291399478912354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3317070007324219},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.1908811330795288},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08560758829116821}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8397572040557861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358049750328064},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5714541673660278},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5539742708206177},{"id":"https://openalex.org/C153668964","wikidata":"https://www.wikidata.org/wiki/Q27636","display_name":"Majority rule","level":2,"score":0.47029492259025574},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46115896105766296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4297574758529663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42747583985328674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33291399478912354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3317070007324219},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.1908811330795288},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08560758829116821},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.01997","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01997","pdf_url":"https://arxiv.org/pdf/2011.01997","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:3094706770","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.01997.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.2011.01997","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.01997","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/khvj-6g55","is_oa":true,"landing_page_url":"https://doi.org/10.17023/khvj-6g55","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:2011.01997","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01997","pdf_url":"https://arxiv.org/pdf/2011.01997","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":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320310366","display_name":"Hitachi","ror":"https://ror.org/02exqgm79"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094706770.pdf","grobid_xml":"https://content.openalex.org/works/W3094706770.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W80245499","https://openalex.org/W173561343","https://openalex.org/W1494198834","https://openalex.org/W1606894530","https://openalex.org/W1904457459","https://openalex.org/W1975442866","https://openalex.org/W2027499299","https://openalex.org/W2046056978","https://openalex.org/W2071016718","https://openalex.org/W2081074144","https://openalex.org/W2097978681","https://openalex.org/W2101045344","https://openalex.org/W2125336414","https://openalex.org/W2125708920","https://openalex.org/W2137560895","https://openalex.org/W2148613904","https://openalex.org/W2150769028","https://openalex.org/W2151572725","https://openalex.org/W2155806188","https://openalex.org/W2159591770","https://openalex.org/W2164502538","https://openalex.org/W2169264834","https://openalex.org/W2222512263","https://openalex.org/W2402428045","https://openalex.org/W2626961305","https://openalex.org/W2638067502","https://openalex.org/W2745338770","https://openalex.org/W2805869973","https://openalex.org/W2884797218","https://openalex.org/W2889031312","https://openalex.org/W2890964092","https://openalex.org/W2963197115","https://openalex.org/W2964391865","https://openalex.org/W2968071640","https://openalex.org/W2982471419","https://openalex.org/W2997419692","https://openalex.org/W3008849579","https://openalex.org/W3010196324","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3035111128","https://openalex.org/W3105031100","https://openalex.org/W3128293163","https://openalex.org/W3147778289","https://openalex.org/W3162347631","https://openalex.org/W6607114211","https://openalex.org/W6662018943","https://openalex.org/W6674334065","https://openalex.org/W6678809451","https://openalex.org/W6680401156","https://openalex.org/W6713312292","https://openalex.org/W6739192308","https://openalex.org/W6766380642","https://openalex.org/W6774558098","https://openalex.org/W6776918098","https://openalex.org/W6784351597","https://openalex.org/W6784769885"],"related_works":["https://openalex.org/W3094184651","https://openalex.org/W3171828425","https://openalex.org/W2990425243","https://openalex.org/W3165260809","https://openalex.org/W3152573646"],"abstract_inverted_index":{"Several":[0],"advances":[1],"have":[2],"been":[3],"made":[4],"recently":[5,45],"towards":[6],"handling":[7],"overlapping":[8,54],"speech":[9,14],"for":[10,28,136],"speaker":[11],"diarization.":[12],"Since":[13],"and":[15,71,109,117,142],"natural":[16],"language":[17],"tasks":[18],"often":[19],"benefit":[20],"from":[21,31,43,101],"ensemble":[22],"techniques,":[23],"we":[24,129],"propose":[25,72],"an":[26,73],"algorithm":[27,75],"combining":[29,99],"outputs":[30,100],"such":[32],"diarization":[33,57],"systems":[34,103],"through":[35],"majority":[36],"voting.":[37],"Our":[38],"method,":[39],"DOVER-Lap,":[40],"is":[41,50],"inspired":[42],"the":[44,62,93,124],"proposed":[46],"DOVER":[47],"algorithm,":[48],"but":[49],"designed":[51],"to":[52],"handle":[53],"segments":[55],"in":[56,69,139],"outputs.":[58],"We":[59,91],"also":[60],"modify":[61],"pair-wise":[63],"incremental":[64],"label":[65],"mapping":[66,85],"strategy":[67],"used":[68,135],"DOVER,":[70],"approximation":[74],"based":[76],"on":[77,115],"weighted":[78],"k-partite":[79],"graph":[80],"matching,":[81],"which":[82],"performs":[83],"this":[84],"using":[86],"a":[87],"global":[88],"cost":[89],"tensor.":[90],"demonstrate":[92],"strength":[94],"of":[95],"our":[96],"method":[97],"by":[98],"diverse":[102],"-":[104,114],"clustering-based,":[105],"region":[106],"proposal":[107],"networks,":[108],"target-speaker":[110],"voice":[111],"activity":[112],"detection":[113],"AMI":[116],"LibriCSS":[118],"datasets,":[119],"where":[120],"it":[121],"consistently":[122],"outperforms":[123],"single":[125],"best":[126],"system.":[127],"Additionally,":[128],"show":[130],"that":[131],"DOVER-Lap":[132],"can":[133],"be":[134],"late":[137],"fusion":[138,147],"multichannel":[140],"diarization,":[141],"compares":[143],"favorably":[144],"with":[145],"early":[146],"methods":[148],"like":[149],"beamforming.":[150]},"counts_by_year":[{"year":2023,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}