{"id":"https://openalex.org/W2168025753","doi":"https://doi.org/10.1109/icassp.2010.5495087","title":"Variational Bayesian speaker diarization of meeting recordings","display_name":"Variational Bayesian speaker diarization of meeting recordings","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2168025753","doi":"https://doi.org/10.1109/icassp.2010.5495087","mag":"2168025753"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/163174","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061495800","display_name":"Fabio Valente","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabio Valente","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080162701","display_name":"Deepu Vijayasenan","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Deepu Vijayasenan","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4954","last_page":"4957"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976999759674072,"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":0.9976999759674072,"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":0.8589404821395874},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.755690336227417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.724629819393158},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5392886400222778},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5272097587585449},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5230252146720886},{"id":"https://openalex.org/keywords/marginal-likelihood","display_name":"Marginal likelihood","score":0.5128071904182434},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.5103480219841003},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4880462884902954},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4464768171310425},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4434126019477844},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.432763934135437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40933263301849365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3207205533981323},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16973823308944702},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1519097089767456},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07906332612037659}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8589404821395874},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.755690336227417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724629819393158},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5392886400222778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5272097587585449},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5230252146720886},{"id":"https://openalex.org/C95923904","wikidata":"https://www.wikidata.org/wiki/Q6760420","display_name":"Marginal likelihood","level":3,"score":0.5128071904182434},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.5103480219841003},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4880462884902954},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4464768171310425},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4434126019477844},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.432763934135437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40933263301849365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3207205533981323},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16973823308944702},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1519097089767456},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07906332612037659},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:163174","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/163174","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:163174","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/163174","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W125260059","https://openalex.org/W1482605500","https://openalex.org/W1502693945","https://openalex.org/W1528993561","https://openalex.org/W2098084154","https://openalex.org/W2122899485","https://openalex.org/W2139701068","https://openalex.org/W2140807505","https://openalex.org/W2156255174","https://openalex.org/W2159591770","https://openalex.org/W2171700247","https://openalex.org/W2172085063","https://openalex.org/W4244577065","https://openalex.org/W6605093602","https://openalex.org/W6628911050","https://openalex.org/W6674643302","https://openalex.org/W6678297943","https://openalex.org/W6680853393"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W184241528","https://openalex.org/W2119836628","https://openalex.org/W2356325859","https://openalex.org/W106647055","https://openalex.org/W2176075850","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"This":[0],"paper":[1,74],"investigates":[2],"the":[3,6,37,51,56,62,65,76,103,107,112,115,118,131],"use":[4,77],"of":[5,14,78,110,114,143,148],"Variational":[7],"Bayesian":[8],"(VB)":[9],"framework":[10],"for":[11,135],"speaker":[12,85,149],"diarization":[13,104,138],"meetings":[15],"data":[16,134],"extending":[17],"previous":[18],"related":[19],"works":[20],"on":[21,36,130],"Broadcast":[22],"News":[23],"audio.":[24],"VB":[25],"learning":[26,45],"aims":[27],"at":[28],"maximizing":[29],"a":[30,70,126],"bound,":[31],"known":[32],"as":[33,81],"Free":[34,66,79],"Energy,":[35],"model":[38,44,47],"marginal":[39],"likelihood":[40],"and":[41,46,117,139],"allows":[42],"joint":[43],"selection":[48],"according":[49],"to":[50,91],"same":[52],"objective":[53,82],"function.":[54],"While":[55],"BIC":[57],"is":[58,68,123],"valid":[59,71],"only":[60],"in":[61,84,146],"asymptotic":[63],"limit,":[64],"Energy":[67,80],"always":[69],"bound.":[72],"The":[73,120],"proposes":[75],"function":[83],"diarization.":[86],"It":[87],"can":[88],"be":[89],"used":[90],"select":[92],"dynamically":[93],"without":[94],"any":[95],"supervision":[96],"or":[97],"tuning,":[98],"elements":[99],"that":[100],"typically":[101],"affect":[102],"performance":[105],"i.e.":[106],"inferred":[108],"number":[109],"speakers,":[111],"size":[113],"GMM":[116],"initialization.":[119],"proposed":[121],"approach":[122],"compared":[124],"with":[125],"conventional":[127],"state-of-the-art":[128],"system":[129],"RT06":[132],"evaluation":[133],"meeting":[136],"recordings":[137],"shows":[140],"an":[141],"improvement":[142],"8.4%":[144],"relative":[145],"terms":[147],"error.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}