{"id":"https://openalex.org/W2088234478","doi":"https://doi.org/10.1109/idaacs.2011.6072771","title":"Speaker diarization using PLDA-based speaker clustering","display_name":"Speaker diarization using PLDA-based speaker clustering","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W2088234478","doi":"https://doi.org/10.1109/idaacs.2011.6072771","mag":"2088234478"},"language":"en","primary_location":{"id":"doi:10.1109/idaacs.2011.6072771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/idaacs.2011.6072771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems","raw_type":"proceedings-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/A5080421250","display_name":"Jan Pra\u017e\u00e1k","orcid":"https://orcid.org/0000-0002-0784-149X"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Prazak","raw_affiliation_strings":["Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Liberec, Czech Republic","Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Studentska 2, 461 17 Liberec 1, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Studentska 2, 461 17 Liberec 1, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022347882","display_name":"Jan Silovsk\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Silovsky","raw_affiliation_strings":["Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Liberec, Czech Republic","Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Studentska 2, 461 17 Liberec 1, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Studentska 2, 461 17 Liberec 1, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7586,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87224918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"347","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.987500011920929,"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":0.9873999953269958,"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":0.9008334279060364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7574094533920288},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7389155030250549},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.692631185054779},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6874818801879883},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6244207620620728},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5419183373451233},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5119668245315552},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4914973974227905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48453420400619507}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9008334279060364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574094533920288},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7389155030250549},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.692631185054779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6874818801879883},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6244207620620728},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5419183373451233},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5119668245315552},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4914973974227905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48453420400619507},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/idaacs.2011.6072771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/idaacs.2011.6072771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W3765491","https://openalex.org/W1482605500","https://openalex.org/W1499900670","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2407232104","https://openalex.org/W6628911050","https://openalex.org/W6629848749"],"related_works":["https://openalex.org/W2499802997","https://openalex.org/W2078150608","https://openalex.org/W2112059504","https://openalex.org/W2144208207","https://openalex.org/W1521049138","https://openalex.org/W1960256358","https://openalex.org/W2360122898","https://openalex.org/W1889843584","https://openalex.org/W2946614119","https://openalex.org/W4285793832"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"application":[3],"of":[4,27,30,62,72],"the":[5,45,52,63,73,79,86],"Probabilistic":[6],"Linear":[7],"Discriminant":[8],"Analysis":[9],"(PLDA)":[10],"for":[11],"speaker":[12,16,74],"clustering":[13,83],"within":[14],"a":[15,28],"diarization":[17],"framework.":[18],"Factor":[19],"analysis":[20],"is":[21],"employed":[22],"to":[23,78],"extract":[24],"low-dimensional":[25],"representation":[26],"sequence":[29],"acoustic":[31],"feature":[32],"vectors":[33],"-":[34,38],"so":[35],"called":[36],"i-vectors":[37,41],"and":[39,68],"these":[40],"are":[42],"modeled":[43],"using":[44,51,82],"PLDA.":[46],"Experiments":[47],"were":[48],"carried":[49],"out":[50],"COST278":[53],"broadcast":[54],"news":[55],"database.":[56],"We":[57],"achieved":[58],"33.7%":[59],"relative":[60,70],"improvement":[61,71],"Diarization":[64],"Error":[65],"Rate":[66],"(DER)":[67],"43.8%":[69],"error":[75],"rate":[76],"compared":[77],"baseline":[80],"system":[81],"based":[84],"on":[85],"Bayesian":[87],"Information":[88],"Criterion":[89],"(BIC).":[90]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}