{"id":"https://openalex.org/W2018419535","doi":"https://doi.org/10.1109/icassp.2014.6853567","title":"Bayesian analysis of similarity matrices for speaker diarization","display_name":"Bayesian analysis of similarity matrices for speaker diarization","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2018419535","doi":"https://doi.org/10.1109/icassp.2014.6853567","mag":"2018419535"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5084640883","display_name":"Alexey Sholokhov","orcid":null},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Alexey Sholokhov","raw_affiliation_strings":["School of Computing, University of Eastern Finland","Sch. of Comput., Univ. of Eastern Finland, Kuopio, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]},{"raw_affiliation_string":"Sch. of Comput., Univ. of Eastern Finland, Kuopio, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029036362","display_name":"Timur Pekhovsky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timur Pekhovsky","raw_affiliation_strings":["Speech Technology Center Ltd., St. Petersburg, Russia","Speech Technol. Center Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology Center Ltd., St. Petersburg, Russia","institution_ids":[]},{"raw_affiliation_string":"Speech Technol. Center Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113722302","display_name":"Oleg Kudashev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleg Kudashev","raw_affiliation_strings":["Speech Technology Center Ltd., St. Petersburg, Russia","Speech Technol. Center Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology Center Ltd., St. Petersburg, Russia","institution_ids":[]},{"raw_affiliation_string":"Speech Technol. Center Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072818374","display_name":"Andrei Shulipa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrei Shulipa","raw_affiliation_strings":["Speech Technology Center Ltd., St. Petersburg, Russia","Speech Technol. Center Ltd., St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology Center Ltd., St. Petersburg, Russia","institution_ids":[]},{"raw_affiliation_string":"Speech Technol. Center Ltd., St. Petersburg, Russia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["School of Computing, University of Eastern Finland","Sch. of Comput., Univ. of Eastern Finland, Kuopio, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]},{"raw_affiliation_string":"Sch. of Comput., Univ. of Eastern Finland, Kuopio, Finland","institution_ids":["https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2068,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.45455753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"4","issue":null,"first_page":"106","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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":0.9965000152587891,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9940000176429749,"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":0.9884999990463257,"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":0.8792034387588501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6776106953620911},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6351340413093567},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6031876802444458},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5820862650871277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5558197498321533},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5399681329727173},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5390810966491699},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5185959339141846},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5046612024307251},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.503933846950531},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45946264266967773},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4516073167324066},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.43390628695487976}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8792034387588501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6776106953620911},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6351340413093567},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6031876802444458},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5820862650871277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5558197498321533},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5399681329727173},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5390810966491699},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5185959339141846},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5046612024307251},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.503933846950531},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45946264266967773},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4516073167324066},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.43390628695487976},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2014.6853567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.645.8524","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.645.8524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/pages/tkinnu/webpage/pdf/ICASSP2014_diarization.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W150519110","https://openalex.org/W780134238","https://openalex.org/W1506806321","https://openalex.org/W1663973292","https://openalex.org/W1987885244","https://openalex.org/W2038101708","https://openalex.org/W2072169887","https://openalex.org/W2080972498","https://openalex.org/W2081074144","https://openalex.org/W2113481973","https://openalex.org/W2115599677","https://openalex.org/W2120636621","https://openalex.org/W2121336242","https://openalex.org/W2121812409","https://openalex.org/W2125642021","https://openalex.org/W2127498532","https://openalex.org/W2150769028","https://openalex.org/W2151967501","https://openalex.org/W2159591770","https://openalex.org/W2165874743","https://openalex.org/W2166688768","https://openalex.org/W2289985966","https://openalex.org/W2395750323","https://openalex.org/W2400584454","https://openalex.org/W6682569104","https://openalex.org/W6684578312","https://openalex.org/W6738904159"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Inspired":[0],"by":[1,32],"recent":[2],"success":[3],"of":[4,24,36,58,61,92],"speaker":[5,18],"clustering":[6],"in":[7,63],"Total":[8],"Variability":[9],"space":[10],"we":[11],"propose":[12],"a":[13],"new":[14],"probabilistic":[15,41],"model":[16,98],"for":[17,101],"diarization":[19],"based":[20],"on":[21,47,68],"Bayesian":[22,52],"modeling":[23],"pairwise":[25],"similarity":[26,34],"scores.":[27],"The":[28],"recordings":[29],"are":[30],"represented":[31],"symmetric":[33],"matrices":[35],"likelihood":[37],"ratio":[38],"scores":[39],"from":[40],"linear":[42],"discriminant":[43],"analysis":[44],"(PLDA)":[45],"trained":[46],"short-term":[48],"i-vectors.":[49],"We":[50],"employ":[51],"approach":[53],"to":[54],"address":[55],"the":[56,69,84,90,96],"problem":[57],"unknown":[59],"number":[60,91],"speakers":[62,93],"conversation.":[64],"Diarization":[65],"error":[66],"rates":[67],"NIST":[70],"2008":[71],"SRE":[72],"telephone":[73],"data":[74],"indicate":[75],"comparable":[76],"performance":[77],"with":[78],"state-of-the-art":[79],"eigenvoice-based":[80],"diarization.":[81],"But":[82],"unlike":[83],"eigenvoice":[85],"approach,":[86],"our":[87],"method":[88],"finds":[89],"automatically,":[94],"making":[95],"proposed":[97],"more":[99],"viable":[100],"practical":[102],"applications.":[103]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}