{"id":"https://openalex.org/W3096363420","doi":"https://doi.org/10.1109/slt48900.2021.9383602","title":"Multi-Class Spectral Clustering with Overlaps for Speaker Diarization","display_name":"Multi-Class Spectral Clustering with Overlaps for Speaker Diarization","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3096363420","doi":"https://doi.org/10.1109/slt48900.2021.9383602","mag":"3096363420"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383602","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/2011.02900","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","Johns Hopkins University"],"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":"Johns Hopkins University","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","Johns Hopkins University"],"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":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"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","Johns Hopkins University"],"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":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"589"},"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":0.9991000294685364,"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":0.9987000226974487,"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":0.7142809629440308},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6817054748535156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5828418731689453},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5385019183158875},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.5357770919799805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4969079792499542},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.48853620886802673},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4330369234085083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43205076456069946},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42305970191955566},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4212697744369507},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41388845443725586},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32448476552963257},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.22806650400161743}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7142809629440308},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6817054748535156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5828418731689453},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5385019183158875},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.5357770919799805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4969079792499542},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.48853620886802673},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4330369234085083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43205076456069946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42305970191955566},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4212697744369507},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41388845443725586},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32448476552963257},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.22806650400161743},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383602","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:2011.02900","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02900","pdf_url":"https://arxiv.org/pdf/2011.02900","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":"doi:10.48550/arxiv.2011.02900","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.02900","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/pd9t-z569","is_oa":true,"landing_page_url":"https://doi.org/10.17023/pd9t-z569","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"},{"id":"mag:3096363420","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.02900","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02900","pdf_url":"https://arxiv.org/pdf/2011.02900","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096363420.pdf","grobid_xml":"https://content.openalex.org/works/W3096363420.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W80245499","https://openalex.org/W658559791","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1577043569","https://openalex.org/W1587744656","https://openalex.org/W1606894530","https://openalex.org/W2046056978","https://openalex.org/W2081074144","https://openalex.org/W2101234009","https://openalex.org/W2116673996","https://openalex.org/W2125336414","https://openalex.org/W2132914434","https://openalex.org/W2135674549","https://openalex.org/W2150769028","https://openalex.org/W2151572725","https://openalex.org/W2159591770","https://openalex.org/W2165874743","https://openalex.org/W2169264834","https://openalex.org/W2219249508","https://openalex.org/W2400584454","https://openalex.org/W2402146185","https://openalex.org/W2626961305","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2745338770","https://openalex.org/W2805869973","https://openalex.org/W2889031312","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2963745998","https://openalex.org/W2968071640","https://openalex.org/W2972680151","https://openalex.org/W2997419692","https://openalex.org/W3010196324","https://openalex.org/W3015463733","https://openalex.org/W3015780472","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3105031100","https://openalex.org/W3146998960","https://openalex.org/W4214556932","https://openalex.org/W6621858757","https://openalex.org/W6631362777","https://openalex.org/W6662018943","https://openalex.org/W6675354045","https://openalex.org/W6678809451","https://openalex.org/W6684578312","https://openalex.org/W6688816777","https://openalex.org/W6712930963","https://openalex.org/W6713312292","https://openalex.org/W6739192308","https://openalex.org/W6769168142","https://openalex.org/W6774558098","https://openalex.org/W6793260802"],"related_works":["https://openalex.org/W3147778289","https://openalex.org/W180663858","https://openalex.org/W2110783210","https://openalex.org/W2981473019","https://openalex.org/W71947379","https://openalex.org/W2972949456","https://openalex.org/W202282565","https://openalex.org/W2538493831","https://openalex.org/W2153342002","https://openalex.org/W1787748203","https://openalex.org/W2130531588","https://openalex.org/W1607072098","https://openalex.org/W2142333570","https://openalex.org/W3095129427","https://openalex.org/W2963745998","https://openalex.org/W2400584454","https://openalex.org/W3105031100","https://openalex.org/W2038101708","https://openalex.org/W1998280908","https://openalex.org/W2017552746"],"abstract_inverted_index":{"This":[0,33],"paper":[1],"describes":[2],"a":[3,14,43,64,103,122,128],"method":[4,19,101,154],"for":[5],"overlap-aware":[6,139],"speaker":[7,15],"diarization.":[8],"Given":[9],"an":[10,83],"overlap":[11,31,78,86,157],"detector":[12,87],"and":[13,63,92,134],"embedding":[16],"extractor,":[17],"our":[18],"performs":[20,89],"spectral":[21],"clustering":[22,40,132],"of":[23,29,67,76,109,115,125,151],"segments":[24],"informed":[25],"by":[26,36,50,57,73],"the":[27,30,38,55,74,77,112,116,145,149,152],"output":[28,75],"detector.":[32,79],"is":[34,48,71,121],"achieved":[35],"transforming":[37],"discrete":[39],"problem":[41,46],"into":[42],"convex":[44],"optimization":[45],"which":[47,70,88,120],"solved":[49],"eigen-decomposition.":[51],"Thereafter,":[52],"we":[53,81],"discretize":[54],"solution":[56],"alternatively":[58],"using":[59],"singular":[60],"value":[61],"decomposition":[62],"modified":[65],"version":[66],"non-maximal":[68],"suppression":[69],"constrained":[72],"Furthermore,":[80],"detail":[82],"HMM-DNN":[84],"based":[85],"frame-level":[90],"classification":[91],"enforces":[93],"duration":[94],"constraints":[95],"through":[96],"HMM":[97],"state":[98],"transitions.":[99],"Our":[100],"achieves":[102],"test":[104],"diarization":[105,140],"error":[106],"rate":[107],"(DER)":[108],"24.0%":[110],"on":[111,144],"mixed-headset":[113],"setting":[114],"AMI":[117],"meeting":[118],"corpus,":[119],"relative":[123],"improvement":[124],"15.2%":[126],"over":[127],"strong":[129],"agglomerative":[130],"hierarchical":[131],"baseline,":[133],"compares":[135],"favorably":[136],"with":[137],"other":[138],"methods.":[141],"Further":[142],"analysis":[143],"LibriCSS":[146],"data":[147],"demonstrates":[148],"effectiveness":[150],"proposed":[153],"in":[155],"high":[156],"conditions.":[158]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}