{"id":"https://openalex.org/W2132056833","doi":"https://doi.org/10.1109/icassp.2004.1326058","title":"Clustering and segmenting speakers and their locations in meetings","display_name":"Clustering and segmenting speakers and their locations in meetings","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2132056833","doi":"https://doi.org/10.1109/icassp.2004.1326058","mag":"2132056833"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/82988","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063781689","display_name":"Jitendra Ajmera","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"J. Ajmera","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007555019","display_name":"Guillaume Lathoud","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"G. Lathoud","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088383435","display_name":"L. McCowan","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"L. McCowan","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"Dalle Molle Inst. for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8816,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.97500261,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9990000128746033,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.777931809425354},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.7311369180679321},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7110278010368347},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6314711570739746},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6115704774856567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5719912052154541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5187442898750305},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5092176198959351},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4234696626663208},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.34596189856529236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777931809425354},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.7311369180679321},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7110278010368347},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6314711570739746},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6115704774856567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5719912052154541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5187442898750305},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5092176198959351},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4234696626663208},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.34596189856529236},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2004.1326058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:82988","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82988","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:83037","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83037","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:83037","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/ajmera-rr-03-55","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":"http://infoscience.epfl.ch/record/83037","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:82988","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82988","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1493595169","https://openalex.org/W1555217905","https://openalex.org/W1739876623","https://openalex.org/W2035090801","https://openalex.org/W2140672401","https://openalex.org/W2156255174","https://openalex.org/W2169525504","https://openalex.org/W4214887259","https://openalex.org/W6629645474"],"related_works":["https://openalex.org/W1974738623","https://openalex.org/W2592395359","https://openalex.org/W2045342254","https://openalex.org/W2535231171","https://openalex.org/W2206035908","https://openalex.org/W1501331687","https://openalex.org/W4255512592","https://openalex.org/W2501551404","https://openalex.org/W2326647871","https://openalex.org/W4205247302"],"abstract_inverted_index":{"The":[0,97],"paper":[1],"presents":[2],"a":[3,87,117],"new":[4],"approach":[5],"toward":[6],"automatic":[7],"annotation":[8],"of":[9,13,31,54,67,86,119,131],"meetings":[10,120],"in":[11,44,122],"terms":[12],"speaker":[14,63,108],"identities":[15,64],"and":[16,36,65,69],"their":[17],"locations.":[18],"This":[19],"is":[20,59,76,100],"achieved":[21],"by":[22],"segmenting":[23],"the":[24,42,79,84,102,107,123,129],"audio":[25],"recordings":[26],"using":[27,111],"two":[28,43],"independent":[29],"sources":[30],"information:":[32],"magnitude":[33],"spectrum":[34],"analysis":[35],"sound":[37],"source":[38],"localization.":[39],"We":[40],"combine":[41],"an":[45,93],"appropriate":[46],"HMM":[47],"framework.":[48],"There":[49],"are":[50,71,81],"three":[51],"main":[52],"advantages":[53],"this":[55,132],"approach.":[56,133],"First,":[57],"it":[58,75],"completely":[60],"unsupervised,":[61],"i.e.":[62,78],"number":[66],"speakers":[68],"locations":[70],"automatically":[72],"inferred.":[73],"Second,":[74],"threshold-free,":[77],"decisions":[80],"made":[82],"without":[83],"need":[85],"threshold":[88],"value":[89],"which":[90],"generally":[91],"requires":[92],"additional":[94],"development":[95],"dataset.":[96],"third":[98],"advantage":[99],"that":[101],"joint":[103],"segmentation":[104,109],"improves":[105],"over":[106],"derived":[110],"only":[112],"acoustic":[113],"features.":[114],"Experiments":[115],"on":[116],"series":[118],"recorded":[121],"IDIAP":[124],"smart":[125],"meeting":[126],"room":[127],"demonstrate":[128],"effectiveness":[130]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
