{"id":"https://openalex.org/W2152615462","doi":"https://doi.org/10.1109/asru.2007.4430121","title":"Robust speaker clustering strategies to data source variation for improved speaker diarization","display_name":"Robust speaker clustering strategies to data source variation for improved speaker diarization","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2152615462","doi":"https://doi.org/10.1109/asru.2007.4430121","mag":"2152615462"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5106859201","display_name":"Kyu J. Han","orcid":null},"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":"Kyu J. Han","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762841","display_name":"Samuel Kim","orcid":"https://orcid.org/0000-0001-5237-6358"},"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":"Samuel Kim","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory (SAIL), 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":"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":"Shrikanth S. Narayanan","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","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":1.558,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84822506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"262","last_page":"267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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/T11309","display_name":"Music and Audio Processing","score":0.9878000020980835,"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/T10860","display_name":"Speech and Audio Processing","score":0.9531999826431274,"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":0.9351663589477539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7621131539344788},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7423514723777771},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.7202908396720886},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6176234483718872},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.609304666519165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6008390188217163},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5626163482666016},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4633863866329193},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.43729379773139954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4308455288410187},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1310986876487732},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06501144170761108}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9351663589477539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621131539344788},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7423514723777771},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.7202908396720886},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6176234483718872},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.609304666519165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6008390188217163},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5626163482666016},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4633863866329193},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43729379773139954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4308455288410187},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1310986876487732},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06501144170761108},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W115846232","https://openalex.org/W1482605500","https://openalex.org/W1490760466","https://openalex.org/W1607302042","https://openalex.org/W2118313846","https://openalex.org/W2144125830","https://openalex.org/W2151299225","https://openalex.org/W2159591770","https://openalex.org/W2168175751","https://openalex.org/W2169165592","https://openalex.org/W2620921085","https://openalex.org/W2623739796","https://openalex.org/W4239875977","https://openalex.org/W4285719527","https://openalex.org/W6628911050","https://openalex.org/W6682620260","https://openalex.org/W6684648996","https://openalex.org/W6738833779","https://openalex.org/W6739074287"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"Agglomerative":[0],"hierarchical":[1],"clustering":[2,52],"(AHC)":[3],"has":[4],"been":[5],"widely":[6],"used":[7],"in":[8,16,84,90],"speaker":[9,22],"diarization":[10],"systems":[11],"to":[12,27,31,64,80],"classify":[13],"speech":[14,58],"segments":[15],"a":[17],"given":[18],"data":[19,32],"source":[20,33],"by":[21],"identity,":[23],"but":[24],"is":[25],"known":[26],"be":[28],"not":[29],"robust":[30],"variation.":[34],"In":[35],"this":[36,47,66],"paper,":[37],"we":[38],"identify":[39],"one":[40],"of":[41,46,86,93],"the":[42,75,91],"key":[43],"potential":[44],"sources":[45],"variability":[48],"that":[49],"negatively":[50],"affects":[51],"error":[53],"rate":[54],"(CER),":[55],"namely":[56],"short":[57],"segments,":[59],"and":[60],"propose":[61],"three":[62],"solutions":[63],"tackle":[65],"issue.":[67],"Through":[68],"experiments":[69],"on":[70],"various":[71],"meeting":[72],"conversation":[73],"excerpts,":[74],"proposed":[76],"methods":[77],"are":[78],"shown":[79],"outperform":[81],"simple":[82],"AHC":[83],"terms":[85],"relative":[87],"CER":[88],"improvements":[89],"range":[92],"17-32%.":[94]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}