{"id":"https://openalex.org/W2098726438","doi":"https://doi.org/10.1109/tasl.2009.2015698","title":"An Information Theoretic Approach to Speaker Diarization of Meeting Data","display_name":"An Information Theoretic Approach to Speaker Diarization of Meeting Data","publication_year":2009,"publication_date":"2009-07-17","ids":{"openalex":"https://openalex.org/W2098726438","doi":"https://doi.org/10.1109/tasl.2009.2015698","mag":"2098726438"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2015698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2015698","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/record/146338/files/Vijayasenan_TASLP_2009.pdf","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":true,"raw_author_name":"D. Vijayasenan","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, 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":"F. Valente","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108291827","display_name":"H. 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":"H. Bourlard","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080162701"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":10.8399,"has_fulltext":true,"cited_by_count":97,"citation_normalized_percentile":{"value":0.9839276,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"17","issue":"7","first_page":"1382","last_page":"1393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9351413249969482},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6917151808738708},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.6161728501319885},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.496429979801178},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4799533188343048},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.45755067467689514},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33133628964424133},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.31064170598983765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2995492219924927}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9351413249969482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6917151808738708},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.6161728501319885},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.496429979801178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4799533188343048},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45755067467689514},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33133628964424133},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31064170598983765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2995492219924927}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/tasl.2009.2015698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2015698","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:infoscience.tind.io:146338","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/47184","pdf_url":"https://infoscience.epfl.ch/record/146338/files/Vijayasenan_TASLP_2009.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":"research article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.260.1060","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.260.1060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/146505/files/vijayasenan-idiap-rr-08-58.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.420.5925","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.420.5925","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_AnInformation.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146338","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146338","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"},{"id":"pmh:oai:infoscience.epfl.ch:146505","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146505","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"},{"id":"pmh:oai:infoscience.tind.io:146505","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/47365","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":"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":null,"raw_type":"report"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:146338","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/47184","pdf_url":"https://infoscience.epfl.ch/record/146338/files/Vijayasenan_TASLP_2009.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":"research article"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G374041500","display_name":"Representation and symbolic functioning in young children (Repr\u00e9sentation et fonctionnement symbolique chez le jeune enfant).","funder_award_id":"33812","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2098726438.pdf","grobid_xml":"https://content.openalex.org/works/W2098726438.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W76945434","https://openalex.org/W1482605500","https://openalex.org/W1495076553","https://openalex.org/W1556474518","https://openalex.org/W1558086160","https://openalex.org/W1686946872","https://openalex.org/W1920021574","https://openalex.org/W2010425028","https://openalex.org/W2041823554","https://openalex.org/W2099111195","https://openalex.org/W2103723258","https://openalex.org/W2106015547","https://openalex.org/W2106780157","https://openalex.org/W2110783210","https://openalex.org/W2113386290","https://openalex.org/W2116310860","https://openalex.org/W2130531588","https://openalex.org/W2136752740","https://openalex.org/W2139672812","https://openalex.org/W2144155988","https://openalex.org/W2146950091","https://openalex.org/W2155995145","https://openalex.org/W2156255174","https://openalex.org/W2166980079","https://openalex.org/W2168175751","https://openalex.org/W2171700247","https://openalex.org/W2915347754","https://openalex.org/W2979454998","https://openalex.org/W2990138404","https://openalex.org/W6601947329","https://openalex.org/W6603105437","https://openalex.org/W6628911050","https://openalex.org/W6629558825","https://openalex.org/W6675471587"],"related_works":["https://openalex.org/W2381356463","https://openalex.org/W2939693078","https://openalex.org/W2783047733","https://openalex.org/W2206035908","https://openalex.org/W4301016710","https://openalex.org/W4287238667","https://openalex.org/W2162158162","https://openalex.org/W3149287595","https://openalex.org/W4247736853","https://openalex.org/W1493012537"],"abstract_inverted_index":{"A":[0],"speaker":[1,30,90,145],"diarization":[2,91,116,146,154],"system":[3,131,135,151],"based":[4,170,182],"on":[5,136,171],"an":[6],"information":[7,19,45,94],"theoretic":[8,95],"framework":[9,96],"is":[10,14,32],"described.":[11],"The":[12,149],"problem":[13,53,63],"formulated":[15],"according":[16],"to":[17,89,160],"the":[18,27,35,39,43,52,56,62,66,73,80,99,103,107,115,119,123,129,137,163,179],"bottleneck":[20],"(IB)":[21],"principle.":[22],"Unlike":[23],"other":[24],"approaches":[25],"where":[26],"distance":[28,67],"between":[29,46,58,68,109],"segments":[31],"arbitrarily":[33],"introduced,":[34],"IB":[36,81],"method":[37],"seeks":[38],"partition":[40],"that":[41],"maximizes":[42],"mutual":[44],"observations":[47],"and":[48,111,118],"variables":[49],"relevant":[50],"for":[51,101,121,144,162],"while":[54],"minimizing":[55],"distortion":[57],"observations.":[59],"This":[60,166],"solves":[61],"of":[64,105,147,157],"choosing":[65],"speech":[69],"segments,":[70],"which":[71],"becomes":[72],"Jensen-Shannon":[74],"divergence":[75],"as":[76,98],"it":[77,174],"arises":[78],"from":[79],"objective":[82,124],"function":[83],"optimization.":[84],"We":[85],"discuss":[86],"issues":[87],"related":[88],"using":[92],"this":[93],"such":[97],"criteria":[100],"inferring":[102],"number":[104],"speakers,":[106],"tradeoff":[108],"quality":[110],"compression":[112],"achieved":[113],"by":[114],"system,":[117,183],"algorithms":[120],"optimizing":[122],"function.":[125],"Furthermore,":[126],"we":[127],"benchmark":[128],"proposed":[130],"against":[132],"a":[133,153],"state-of-the-art":[134],"NIST":[138],"RT06":[139],"(rich":[140],"transcription)":[141],"data":[142],"set":[143],"meetings.":[148],"IB-based":[150],"achieves":[152],"error":[155],"rate":[156],"23.2%":[158],"compared":[159],"23.6%":[161],"baseline":[164,180],"system.":[165],"approach":[167],"being":[168],"mainly":[169],"nonparametric":[172],"clustering,":[173],"runs":[175],"significantly":[176],"faster":[177],"than":[178],"HMM/GMM":[181],"resulting":[184],"in":[185],"faster-than-real-time":[186],"diarization.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
