{"id":"https://openalex.org/W1971791733","doi":"https://doi.org/10.1109/tpami.2011.47","title":"Multimodal Speaker Diarization","display_name":"Multimodal Speaker Diarization","publication_year":2011,"publication_date":"2011-03-15","ids":{"openalex":"https://openalex.org/W1971791733","doi":"https://doi.org/10.1109/tpami.2011.47","mag":"1971791733","pmid":"https://pubmed.ncbi.nlm.nih.gov/21383401"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2011.47","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","pubmed"],"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/A5053745317","display_name":"A. Noulas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"A. Noulas","raw_affiliation_strings":["university of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"university of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074888054","display_name":"Gwenn Englebienne","orcid":"https://orcid.org/0000-0002-3130-2082"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"G. Englebienne","raw_affiliation_strings":["university of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"university of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049349937","display_name":"Ben Kr\u00f6se","orcid":"https://orcid.org/0000-0003-1237-0618"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"B. J. A. Krose","raw_affiliation_strings":["university of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"university of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.074,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":63,"citation_normalized_percentile":{"value":0.999781,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"34","issue":"1","first_page":"79","last_page":"93"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997,"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":0.9995,"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":0.869871},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.4394396}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.869871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83400774},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6183131},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6142747},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5004289},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48854956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44912907},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.4394396},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.36794358}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2011.47","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21383401","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W1493595169","https://openalex.org/W1528056001","https://openalex.org/W1559164507","https://openalex.org/W1625255723","https://openalex.org/W166917337","https://openalex.org/W1762918658","https://openalex.org/W1797158261","https://openalex.org/W1869980952","https://openalex.org/W1876378865","https://openalex.org/W1943968395","https://openalex.org/W1986647142","https://openalex.org/W2035090801","https://openalex.org/W2044591814","https://openalex.org/W2096311759","https://openalex.org/W2105582566","https://openalex.org/W2107617395","https://openalex.org/W2123993331","https://openalex.org/W2125838338","https://openalex.org/W2130102735","https://openalex.org/W2157775762","https://openalex.org/W2159997200","https://openalex.org/W2163141813","https://openalex.org/W2171819471","https://openalex.org/W2338994564","https://openalex.org/W2397634864","https://openalex.org/W2411921399","https://openalex.org/W2492794003","https://openalex.org/W2513796559","https://openalex.org/W3083113686","https://openalex.org/W3097096317","https://openalex.org/W3214102110","https://openalex.org/W3765491","https://openalex.org/W59279772"],"related_works":["https://openalex.org/W4247736853","https://openalex.org/W2206035908","https://openalex.org/W2175373321","https://openalex.org/W2162158162","https://openalex.org/W2135672910","https://openalex.org/W2125642021","https://openalex.org/W2017210410","https://openalex.org/W1995792634","https://openalex.org/W1993009522","https://openalex.org/W1493012537"],"abstract_inverted_index":{"We":[0,104],"present":[1],"a":[2,24,34,114],"novel":[3],"probabilistic":[4],"framework":[5,22,68],"that":[6,29,52],"fuses":[7],"information":[8],"coming":[9],"from":[10,122],"the":[11,42,56,59,63,79,82,95,99,106,137,143,151],"audio":[12,57],"and":[13,40,62,85,113,148],"video":[14,60],"modality":[15,145],"to":[16,72,109],"perform":[17],"speaker":[18,131,154],"diarization.":[19,155],"The":[20,67,127],"proposed":[21,107,138],"is":[23,30,69],"Dynamic":[25],"Bayesian":[26],"Network":[27],"(DBN)":[28],"an":[31,46],"extension":[32],"of":[33,81,119,136],"factorial":[35],"Hidden":[36],"Markov":[37],"Model":[38],"(fHMM)":[39],"models":[41],"people":[43],"appearing":[44],"in":[45,55,130,134],"audiovisual":[47,65],"recording":[48,83],"as":[49,92],"multimodal":[50,139],"entities":[51],"generate":[53],"observations":[54],"stream,":[58,61],"joint":[64],"space.":[66],"very":[70],"robust":[71],"different":[73],"contexts,":[74],"makes":[75],"no":[76],"assumptions":[77],"about":[78],"location":[80],"equipment,":[84],"does":[86],"not":[87],"require":[88],"labeled":[89],"training":[90],"data":[91,125],"it":[93],"acquires":[94],"model":[96,108],"parameters":[97],"using":[98],"Expectation":[100],"Maximization":[101],"(EM)":[102],"algorithm.":[103],"apply":[105],"two":[110],"meeting":[111],"videos":[112],"news":[115],"broadcast":[116],"video,":[117],"all":[118],"which":[120,141],"come":[121],"publicly":[123],"available":[124],"sets.":[126],"results":[128,147],"acquired":[129],"diarization":[132],"are":[133],"favor":[135],"framework,":[140],"outperforms":[142],"single":[144],"analysis":[146],"improves":[149],"over":[150],"state-of-the-art":[152],"audio-based":[153]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1971791733","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":5}],"updated_date":"2025-03-18T23:52:14.697501","created_date":"2016-06-24"}