{"id":"https://openalex.org/W2997419692","doi":"https://doi.org/10.1109/lsp.2019.2961071","title":"Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap","display_name":"Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap","publication_year":2019,"publication_date":"2019-12-24","ids":{"openalex":"https://openalex.org/W2997419692","doi":"https://doi.org/10.1109/lsp.2019.2961071","mag":"2997419692"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2019.2961071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2019.2961071","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.02405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tae Jin Park","orcid":"https://orcid.org/0000-0002-4177-7487"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tae Jin Park","raw_affiliation_strings":["Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kyu J. Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyu J. Han","raw_affiliation_strings":["ASAPP, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"ASAPP, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Manoj Kumar","orcid":"https://orcid.org/0000-0003-2100-461X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manoj Kumar","raw_affiliation_strings":["Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Signal & Image Processing Institute, University Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Signal & Image Processing Institute, University Southern California, Los Angeles, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":4.1965,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.95390566,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"381","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7294999957084656,"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":0.7294999957084656,"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/T10057","display_name":"Face and Expression Recognition","score":0.07169999927282333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.06449999660253525,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7820000052452087},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.6190999746322632},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5291000008583069},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5200999975204468},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5090000033378601},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4025999903678894},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.35019999742507935}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7820000052452087},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.6190999746322632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6014999747276306},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5200999975204468},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5090000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059000015258789},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3280999958515167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C2988995629","wikidata":"https://www.wikidata.org/wiki/Q2915729","display_name":"Matrix algebra","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2019.2961071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2019.2961071","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2003.02405","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.02405","pdf_url":"https://arxiv.org/pdf/2003.02405","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.02405","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.02405","pdf_url":"https://arxiv.org/pdf/2003.02405","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1589137271","https://openalex.org/W2038101708","https://openalex.org/W2121812409","https://openalex.org/W2132914434","https://openalex.org/W2138180870","https://openalex.org/W2150593711","https://openalex.org/W2638067502","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2915347754","https://openalex.org/W2963470929","https://openalex.org/W2963745998","https://openalex.org/W6601947329","https://openalex.org/W6631362777","https://openalex.org/W6684578312","https://openalex.org/W6712936709","https://openalex.org/W6793260802"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,71],"study,":[2],"we":[3,74],"propose":[4],"a":[5,76],"new":[6],"spectral":[7,57,123],"clustering":[8,17,91,124],"framework":[9,27],"that":[10,93],"can":[11],"auto-tune":[12],"the":[13,16,20,36,41,44,47,60,66,86,107,112,118],"parameters":[14,42],"of":[15,22,38,46,49,62,104,120],"algorithm":[18],"in":[19,52,106],"context":[21],"speaker":[23,108],"diarization.":[24],"The":[25],"proposed":[26,122],"uses":[28],"normalized":[29],"maximum":[30],"eigengap":[31],"(NME)":[32],"values":[33],"to":[34],"estimate":[35],"number":[37],"clusters":[39],"and":[40,98],"for":[43],"threshold":[45],"elements":[48],"each":[50],"row":[51],"an":[53],"affinity":[54],"matrix":[55],"during":[56],"clustering,":[58],"without":[59],"use":[61],"parameter":[63,96],"tuning":[64,97],"on":[65,111],"development":[67,99],"set.":[68],"Even":[69],"through":[70],"hands-off":[72],"approach,":[73],"achieve":[75],"comparable":[77],"or":[78],"better":[79],"performance":[80],"across":[81],"various":[82],"evaluation":[83,115],"sets":[84],"than":[85],"results":[87],"found":[88],"using":[89],"traditional":[90],"methods":[92],"apply":[94],"careful":[95],"data.":[100],"A":[101],"relative":[102],"improvement":[103],"17%":[105],"error":[109],"rate":[110],"well-known":[113],"CALLHOME":[114],"set":[116],"shows":[117],"effectiveness":[119],"our":[121],"with":[125],"auto-tuning.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":15}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2020-01-10T00:00:00"}