{"id":"https://openalex.org/W2134309369","doi":"https://doi.org/10.1109/icassp.2011.5947334","title":"Multistream speaker diarization through Information Bottleneck system outputs combination","display_name":"Multistream speaker diarization through Information Bottleneck system outputs combination","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2134309369","doi":"https://doi.org/10.1109/icassp.2011.5947334","mag":"2134309369"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/192693","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, Switzerland","IDIAP Research Institute, 1920 Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, 1920 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":"Fabio Valente","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Research Institute, 1920 Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, 1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","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","IDIAP Research Institute, 1920 Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, 1920 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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4420","last_page":"4423"},"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":0.9997000098228455,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8261261582374573},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7974710464477539},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7884804606437683},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6515016555786133},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6200137734413147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49292874336242676},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4338460862636566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42773866653442383},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42513203620910645},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.4217788279056549},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3322211503982544},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3132660984992981},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.2595818042755127}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261261582374573},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7974710464477539},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7884804606437683},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6515016555786133},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6200137734413147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49292874336242676},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4338460862636566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42773866653442383},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42513203620910645},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.4217788279056549},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3322211503982544},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3132660984992981},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2595818042755127},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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":3,"locations":[{"id":"doi:10.1109/icassp.2011.5947334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.646.9509","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.9509","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/papers/2011/Vijayasenan_ICASSP2011_2011.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:192693","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192693","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:192693","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192693","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1556474518","https://openalex.org/W1686946872","https://openalex.org/W1745746739","https://openalex.org/W2098726438","https://openalex.org/W2103723258","https://openalex.org/W2113386290","https://openalex.org/W2132990350","https://openalex.org/W2147833929","https://openalex.org/W2149402184","https://openalex.org/W2157287565","https://openalex.org/W2170695863","https://openalex.org/W2979454998","https://openalex.org/W4300666183","https://openalex.org/W6637108112","https://openalex.org/W6637485440","https://openalex.org/W6675471587"],"related_works":["https://openalex.org/W1504394672","https://openalex.org/W2622284819","https://openalex.org/W3089381707","https://openalex.org/W1963976507","https://openalex.org/W3034190530","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2741297526","https://openalex.org/W4295728955","https://openalex.org/W2185075503"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,52,74],"of":[2,12,21,41,50,71,133],"meetings":[3],"recorded":[4],"with":[5],"Multiple":[6],"Distant":[7],"Microphones":[8],"makes":[9],"extensive":[10],"use":[11],"multiple":[13,42,51],"feature":[14,33,43,82],"streams":[15,44],"like":[16],"MFCC":[17,146],"and":[18,109,147],"Time":[19],"Delay":[20],"Arrivals":[22],"(TDOA).":[23],"Typically":[24],"the":[25,39,48,61,69,79,92,105,112,118,137,141,144],"combination":[26,40,49,70,115,121],"happens":[27],"using":[28,55],"separate":[29],"models":[30],"for":[31],"each":[32],"stream.":[34],"This":[35],"work":[36],"investigates":[37],"if":[38],"can":[45],"happen":[46],"through":[47],"systems":[53,149],"performed":[54],"those":[56],"features.":[57],"The":[58,125,131],"paper":[59,93],"extends":[60],"previously":[62],"proposed":[63],"Information":[64],"Bottleneck":[65],"method":[66],"to":[67,78],"handle":[68],"several":[72],"probabilistic":[73],"outputs.":[75],"In":[76],"contrast":[77],"conventional":[80],"model-based":[81],"combination,":[83],"this":[84],"technique":[85],"is":[86],"referred":[87],"as":[88],"system-based":[89],"combination.":[90,98],"Furthermore":[91],"introduces":[94],"an":[95],"hybrid":[96,126],"model-system":[97],"Experiments":[99],"are":[100],"run":[101],"on":[102],"data":[103],"from":[104,140],"Rich":[106],"Transcription":[107],"campaigns":[108],"show":[110],"that":[111,136],"system":[113],"based":[114,120],"largely":[116],"outperforms":[117],"model":[119],"by":[122,129],"37%":[123],"relative.":[124],"approaches":[127],"improve":[128],"10-20%.":[130],"analysis":[132],"errors":[134],"shows":[135],"improvements":[138],"come":[139],"recordings":[142],"where":[143],"individual":[145],"TDOA":[148],"provide":[150],"very":[151],"different":[152],"performances.":[153]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}