{"id":"https://openalex.org/W2115861008","doi":"https://doi.org/10.1109/icassp.2012.6288843","title":"Speaker diarization of broadcast streams using two-stage clustering based on i-vectors and cosine distance scoring","display_name":"Speaker diarization of broadcast streams using two-stage clustering based on i-vectors and cosine distance scoring","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2115861008","doi":"https://doi.org/10.1109/icassp.2012.6288843","mag":"2115861008"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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, Czech Republic","Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of 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, Czech Republic#TAB#","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"last","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, Czech Republic","Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of Liberec, Czech Republic#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Technology and Electronics, Faculty of Mechatronics, Technical University of 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, Czech Republic#TAB#","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":3.9806,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9382442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4193","last_page":"4196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.993399977684021,"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":0.9918000102043152,"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":0.8445401191711426},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7280921339988708},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7183868288993835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6781725287437439},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.666248083114624},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6453460454940796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5857061743736267},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5332367420196533},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.500044584274292},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.4976678192615509},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.47146040201187134},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.46793124079704285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4467329978942871},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33404675126075745}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8445401191711426},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7280921339988708},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7183868288993835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6781725287437439},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.666248083114624},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6453460454940796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5857061743736267},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5332367420196533},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.500044584274292},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4976678192615509},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.47146040201187134},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.46793124079704285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4467329978942871},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33404675126075745},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.835.3095","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.835.3095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mirlab.org/conference_papers/International_Conference/ICASSP%202012/pdfs/0004193.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"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":12,"referenced_works":["https://openalex.org/W106647055","https://openalex.org/W1482605500","https://openalex.org/W2115599677","https://openalex.org/W2121415728","https://openalex.org/W2150769028","https://openalex.org/W2289985966","https://openalex.org/W2400614314","https://openalex.org/W2407232104","https://openalex.org/W6604245201","https://openalex.org/W6628911050","https://openalex.org/W6696885005","https://openalex.org/W6712970971"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2119836628","https://openalex.org/W2356325859","https://openalex.org/W106647055","https://openalex.org/W2185075503","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537"],"abstract_inverted_index":{"In":[0,22],"this":[1],"paper":[2],"we":[3],"present":[4],"our":[5,121],"system":[6,78,122],"for":[7],"speaker":[8,19,25,30,129],"diarization":[9],"of":[10,39,72,90,120,127],"broadcast":[11,66],"news":[12,67],"based":[13,79],"on":[14,80],"recent":[15],"advances":[16],"in":[17,103],"the":[18,23,29,63,73,76,81,104,128,133],"recognition":[20],"field.":[21],"system,":[24],"segments":[26,102],"determined":[27],"by":[28,35],"change-point":[31],"detector":[32],"are":[33],"represented":[34],"i-vectors":[36],"and":[37,86,109],"similarity":[38],"segments'":[40],"speakers":[41],"evaluated":[42],"using":[43,62],"cosine":[44],"distance":[45],"scoring.":[46],"Linear":[47],"discriminant":[48],"analysis":[49],"is":[50,107],"employed":[51],"to":[52,100,111],"cope":[53],"with":[54],"intra-speaker":[55],"variability.":[56],"The":[57,116],"experiments":[58],"were":[59],"carried":[60],"out":[61],"COST278":[64],"multilingual":[65],"database.":[68],"We":[69],"demonstrate":[70],"improvement":[71,126],"performance":[74,114],"over":[75,132],"baseline":[77],"Bayesian":[82],"Information":[83],"Criterion":[84],"(BIC)":[85],"highlight":[87],"significant":[88],"impact":[89],"cepstral":[91],"mean":[92],"normalization.":[93],"Finally,":[94],"two-stage":[95],"clustering":[96,99],"employing":[97],"BIC-based":[98],"pre-cluster":[101],"first":[105],"stage":[106],"examined":[108],"showed":[110],"yield":[112],"further":[113],"improvement.":[115],"best":[117],"performing":[118],"configuration":[119],"achieved":[123],"52.4%":[124],"relative":[125],"error":[130],"rate":[131],"baseline.":[134]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}