{"id":"https://openalex.org/W2138730338","doi":"https://doi.org/10.1109/tasl.2008.2002085","title":"Strategies to Improve the Robustness of Agglomerative Hierarchical Clustering Under Data Source Variation for Speaker Diarization","display_name":"Strategies to Improve the Robustness of Agglomerative Hierarchical Clustering Under Data Source Variation for Speaker Diarization","publication_year":2008,"publication_date":"2008-09-29","ids":{"openalex":"https://openalex.org/W2138730338","doi":"https://doi.org/10.1109/tasl.2008.2002085","mag":"2138730338"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2002085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2002085","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038419298","display_name":"Ki Jin Han","orcid":"https://orcid.org/0000-0002-7190-8492"},"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":"K.J. Han","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071092318","display_name":"S. Kim","orcid":"https://orcid.org/0000-0001-5544-6008"},"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":"S. Kim","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"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":"S.S. Narayanan","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":8.1723,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.97251284,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"16","issue":"8","first_page":"1590","last_page":"1601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9909999966621399,"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":0.9901999831199646,"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/robustness","display_name":"Robustness (evolution)","score":0.7745007872581482},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.7379198670387268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7190342545509338},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6941524147987366},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6237672567367554},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5776933431625366},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4510197639465332},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4492199122905731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40902644395828247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40663668513298035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38989585638046265},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34884247183799744}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7745007872581482},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.7379198670387268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190342545509338},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6941524147987366},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6237672567367554},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5776933431625366},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4510197639465332},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4492199122905731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40902644395828247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40663668513298035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38989585638046265},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34884247183799744},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2008.2002085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2002085","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W21371201","https://openalex.org/W115846232","https://openalex.org/W165453733","https://openalex.org/W194245511","https://openalex.org/W1482605500","https://openalex.org/W1506281249","https://openalex.org/W1606203323","https://openalex.org/W1607302042","https://openalex.org/W2041823554","https://openalex.org/W2052269122","https://openalex.org/W2069883713","https://openalex.org/W2099111195","https://openalex.org/W2118313846","https://openalex.org/W2144125830","https://openalex.org/W2151299225","https://openalex.org/W2152615462","https://openalex.org/W2156255174","https://openalex.org/W2159591770","https://openalex.org/W2159730002","https://openalex.org/W2165880886","https://openalex.org/W2166980079","https://openalex.org/W2168175751","https://openalex.org/W2171092607","https://openalex.org/W2171700247","https://openalex.org/W3129653033","https://openalex.org/W4205687621","https://openalex.org/W4285719527","https://openalex.org/W6606651766","https://openalex.org/W6628911050","https://openalex.org/W6677982106","https://openalex.org/W6685237695"],"related_works":["https://openalex.org/W2119836628","https://openalex.org/W2206035908","https://openalex.org/W106647055","https://openalex.org/W2356325859","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021"],"abstract_inverted_index":{"Many":[0],"current":[1],"state-of-the-art":[2],"speaker":[3,13],"diarization":[4,122],"systems":[5],"exploit":[6],"agglomerative":[7],"hierarchical":[8],"clustering":[9,14,58],"(AHC)":[10],"as":[11],"their":[12],"strategy,":[15],"due":[16],"to":[17,31,105,109,207],"its":[18],"simple":[19],"processing":[20],"structure":[21],"and":[22,67,162],"acceptable":[23],"level":[24],"of":[25,170,181,192,233],"performance.":[26],"However,":[27],"AHC":[28,87,140,148,182],"is":[29,103,129,183,202,225],"known":[30],"suffer":[32],"from":[33],"performance":[34,220],"robustness":[35,209],"under":[36],"data":[37,110,200],"source":[38,111,201],"variation.":[39],"In":[40],"this":[41,45,127],"paper,":[42,144],"we":[43,79],"address":[44],"problem.":[46],"We":[47,135],"specifically":[48],"focus":[49],"on":[50,62,73,89,96,155],"the":[51,55,68,100,114,143,150,171,175,190,208,213],"issues":[52],"associated":[53],"with":[54,149],"widely":[56],"used":[57],"stopping":[59,84,152],"method":[60,85,102,128,153],"based":[61,72,88],"Bayesian":[63],"information":[64,90],"criterion":[65],"(BIC)":[66],"merging-cluster":[69,215],"selection":[70,216],"scheme":[71],"generalized":[74],"likelihood":[75],"ratio":[76],"(GLR).":[77],"First,":[78],"propose":[80],"a":[81,138,199,203],"novel":[82],"alternative":[83],"for":[86],"change":[91],"rate":[92,124],"(ICR).":[93],"Through":[94],"experiments":[95],"several":[97],"meeting":[98],"corpora,":[99],"proposed":[101],"demonstrated":[104],"be":[106],"more":[107],"robust":[108],"variation":[112],"than":[113,159],"BIC-based":[115],"one.":[116],"The":[117,218],"average":[118],"improvement":[119,221],"obtained":[120,222],"in":[121,142,198,212,231],"error":[123],"(DER)":[125],"by":[126,174,185,223],"8.76%":[130],"(absolute)":[131,227],"or":[132,228],"35.77%":[133],"(relative).":[134],"also":[136],"introduce":[137],"selective":[139],"(SAHC)":[141],"which":[145],"first":[146],"runs":[147],"ICR-based":[151],"only":[154],"speech":[156,166,194],"segments":[157,167],"longer":[158],"3":[160],"s":[161],"then":[163],"classifies":[164],"shorter":[165],"into":[168],"one":[169],"clusters":[172],"given":[173],"initial":[176],"AHC.":[177],"This":[178],"modified":[179],"version":[180],"motivated":[184],"our":[186],"previous":[187],"analysis":[188],"that":[189],"proportion":[191],"short":[193],"turns":[195],"(or":[196],"segments)":[197],"significant":[204],"factor":[205],"contributing":[206],"problem":[210],"arising":[211],"GLR-based":[214],"scheme.":[217],"additional":[219],"SAHC":[224],"3.45%":[226],"14.08%":[229],"(relative)":[230],"terms":[232],"averaged":[234],"DER.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}