{"id":"https://openalex.org/W1577891482","doi":"https://doi.org/10.1109/icassp.2015.7178809","title":"KL-HMM based speaker diarization system for meetings","display_name":"KL-HMM based speaker diarization system for meetings","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1577891482","doi":"https://doi.org/10.1109/icassp.2015.7178809","mag":"1577891482"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://publications.idiap.ch/attachments/reports/2014/Madikeri_Idiap-RR-19-2015.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084521938","display_name":"Srikanth Madikeri","orcid":"https://orcid.org/0000-0002-4361-784X"},"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":"Srikanth Madikeri","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"funder","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"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":"Herve Bourlard","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.414,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":5,"citation_normalized_percentile":{"value":0.65849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":80,"max":82},"biblio":{"volume":null,"issue":null,"first_page":"4435","last_page":"4439"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9996,"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":0.9996,"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":0.9995,"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":0.9963,"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":0.9475947},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.69363654},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.67786545},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5690967}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9475947},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8341466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.707039},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.69363654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.68243337},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.67786545},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6702306},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6076204},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5690967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.52858925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47916332},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46434268},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41094536},{"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":4,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Madikeri_Idiap-RR-19-2015","pdf_url":"https://publications.idiap.ch/attachments/reports/2014/Madikeri_Idiap-RR-19-2015.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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},{"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/209100","pdf_url":"https://infoscience.epfl.ch/record/209100/files/Madikeri_Idiap-RR-19-2015.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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},{"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/209079","pdf_url":"https://infoscience.epfl.ch/record/209079/files/Madikeri_ICASSP2015-2_2015.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Madikeri_Idiap-RR-19-2015","pdf_url":"https://publications.idiap.ch/attachments/reports/2014/Madikeri_Idiap-RR-19-2015.pdf","source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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},"sustainable_development_goals":[{"score":0.46,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":17,"referenced_works":["https://openalex.org/W142991516","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1526516369","https://openalex.org/W1574901103","https://openalex.org/W1589339348","https://openalex.org/W1995002252","https://openalex.org/W2044591814","https://openalex.org/W2081074144","https://openalex.org/W2098726438","https://openalex.org/W2147276082","https://openalex.org/W2151299225","https://openalex.org/W2156255174","https://openalex.org/W2289985966","https://openalex.org/W2338994564","https://openalex.org/W2400584454","https://openalex.org/W2620757702"],"related_works":["https://openalex.org/W4247736853","https://openalex.org/W2552734076","https://openalex.org/W2381158726","https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W2129090883","https://openalex.org/W2118039276","https://openalex.org/W1992796048","https://openalex.org/W1493012537","https://openalex.org/W1197719229"],"abstract_inverted_index":{"In":[0,46],"this":[1,81],"paper,":[2],"the":[3,25,39,44,47,60,84,96,110,128,162,183,191],"Kullback-Leibler":[4],"Hidden":[5],"Markov":[6],"Model":[7,118],"(KL-HMMs)":[8],"is":[9,22,93,122,133,140,159,173],"applied":[10],"for":[11,135],"unsupervised":[12],"diarization":[13,21,91,138],"of":[14,36,38,43,86,106,171,177],"speech.":[15],"A":[16,166],"general":[17],"approach":[18,51,70],"to":[19,23,52,74,114],"speaker":[20],"split":[24],"audio":[26,111],"into":[27],"uniform":[28,55,97],"segments":[29,40,56,98],"followed":[30,63],"by":[31,64,142],"one":[32],"or":[33],"more":[34],"iterations":[35],"clustering":[37,154],"and":[41,101],"resegmentation":[42,65,78],"audio.":[45],"Information":[48,147],"Bottlneck":[49],"(IB)":[50],"diarization,":[53],"short":[54],"are":[57,99],"clustered":[58,100],"using":[59,103,124],"IB":[61,192],"criterion":[62,150],"with":[66,112,190],"KL-HMM.":[67],"The":[68,120,137,156],"KL-HMM":[69,87],"has":[71],"been":[72],"shown":[73],"be":[75],"an":[76,89],"effective":[77],"procedure":[79,139],"in":[80,175],"respect.":[82],"Thus,":[83],"potential":[85],"as":[88],"independent":[90],"system":[92],"explored":[94],"where":[95],"segmented":[102],"a":[104,115,144],"sequence":[105],"posteriors":[107],"obtained":[108],"from":[109],"respect":[113],"Gaussian":[116],"Mixture":[117],"(GMM).":[119],"segmentation":[121],"performed":[123],"KL":[125],"divergence,":[126],"while":[127],"Jensen":[129],"Shanon":[130],"(JS)":[131],"divergence":[132],"used":[134],"clustering.":[136],"stopped":[141],"applying":[143],"Normalized":[145],"Mutual":[146],"(NMI)":[148],"based":[149],"between":[151],"two":[152],"consecutive":[153],"outputs.":[155],"proposed":[157],"method":[158],"tested":[160],"on":[161,182],"NIST":[163,184],"RT":[164,185],"datasets.":[165],"best":[167],"case":[168],"relative":[169],"improvement":[170],"30%":[172],"observed":[174],"terms":[176],"Speaker":[178],"Error":[179],"Rate":[180],"(SER)":[181],"09":[186],"dataset":[187],"when":[188],"compared":[189],"approach.":[193]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1577891482","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-03-16T16:07:52.165422","created_date":"2016-06-24"}