{"id":"https://openalex.org/W1745746739","doi":"https://doi.org/10.21437/interspeech.2009-325","title":"KL realignment for speaker diarization with multiple feature streams","display_name":"KL realignment for speaker diarization with multiple feature streams","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1745746739","doi":"https://doi.org/10.21437/interspeech.2009-325","mag":"1745746739"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-325","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/index.php/publications/showcite/Vijayasenan_Idiap-RR-24-2010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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-Combe, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","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-Combe, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, 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/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":"Herv\u00e9 Bourlard","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","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":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1059","last_page":"1062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9810000061988831,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.977400004863739,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7827737331390381},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7809633016586304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7152494192123413},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6726326942443848},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6670752167701721},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6476223468780518},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6350938081741333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6182414889335632},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5942726135253906},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5636624693870544},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5531477332115173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5064684152603149},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4831118583679199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47511276602745056},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44907456636428833},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.43315446376800537},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.39175403118133545},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.1166638731956482}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7827737331390381},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7809633016586304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152494192123413},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6726326942443848},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6670752167701721},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6476223468780518},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6350938081741333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6182414889335632},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5942726135253906},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5636624693870544},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5531477332115173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5064684152603149},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4831118583679199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47511276602745056},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44907456636428833},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.43315446376800537},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.39175403118133545},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.1166638731956482},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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":6,"locations":[{"id":"doi:10.21437/interspeech.2009-325","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-325","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:146337","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/47183","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/Vijayasenan_Idiap-RR-24-2010","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":"conference proceedings"},{"id":"pmh:oai:infoscience.tind.io:150637","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/150637","pdf_url":"http://publications.idiap.ch/downloads/reports/2009/Vijayasenan_Idiap-RR-24-2010.pdf","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.9028","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.9028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/reports/2009/Vijayasenan_Idiap-RR-24-2010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.420.3262","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.420.3262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-gth.die.upm.es/research/documentation/referencias/Vijayasenan_KLRealignment.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146337","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146337","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.tind.io:146337","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/47183","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/Vijayasenan_Idiap-RR-24-2010","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":"conference proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320915","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1745746739.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1495076553","https://openalex.org/W1539780439","https://openalex.org/W1556474518","https://openalex.org/W1558086160","https://openalex.org/W1592881709","https://openalex.org/W1686946872","https://openalex.org/W2070945723","https://openalex.org/W2103723258","https://openalex.org/W2106780157","https://openalex.org/W2111677269","https://openalex.org/W2113386290","https://openalex.org/W2979454998"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W4229940372"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"at":[3],"investigating":[4],"the":[5,28,74,88,92,96,101],"use":[6,19],"of":[7,20,62,84,106,108],"Kullback-Leibler":[8],"(KL)":[9],"divergence":[10,22],"based":[11,23,98],"realignment":[12,24,38],"with":[13,36,66],"application":[14],"to":[15,49],"speaker":[16,29,51,117],"diarization.":[17],"The":[18],"KL":[21,97],"operates":[25],"directly":[26],"on":[27,73],"posterior":[30,47],"distribution":[31],"estimates":[32,48],"and":[33,113],"is":[34,53],"compared":[35],"traditional":[37],"performed":[39],"using":[40,46],"HMM/GMM":[41,102],"system.":[42],"We":[43],"hypothesize":[44],"that":[45,81],"re-align":[50],"boundaries":[52],"more":[54],"robust":[55],"than":[56],"gaussian":[57],"mixture":[58],"models":[59],"in":[60,82,104],"case":[61,83,105],"multiple":[63,109],"feature":[64,110,121],"streams":[65,111],"different":[67],"statistical":[68],"properties.":[69],"Experiments":[70],"are":[71],"run":[72],"NIST":[75],"RT06":[76],"data.":[77],"These":[78],"experiments":[79],"reveal":[80],"conventional":[85],"MFCC":[86],"features":[87],"two":[89],"approaches":[90],"yields":[91],"same":[93],"performance":[94],"while":[95],"system":[99],"outperforms":[100],"re-alignment":[103],"combination":[107,122],"(MFCC":[112],"TDOA).":[114],"Index":[115],"Terms:":[116],"diarization,":[118],"information":[119],"bottleneck,":[120]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
