{"id":"https://openalex.org/W1591300715","doi":"https://doi.org/10.21437/icslp.2002-195","title":"Unknown-multiple speaker clustering using HMM","display_name":"Unknown-multiple speaker clustering using HMM","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W1591300715","doi":"https://doi.org/10.21437/icslp.2002-195","mag":"1591300715"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-195","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publications.idiap.ch/index.php/publications/showcite/ajmera-rr-02-07","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063781689","display_name":"Jitendra Ajmera","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Ajmera","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002668439","display_name":"Itshak Lapidot","orcid":"https://orcid.org/0000-0003-1066-3441"},"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":"I. Lapidot","raw_affiliation_strings":["IDIAP research institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072372659","display_name":"Iain McCowan","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":"Iain A. McCowan","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":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2082,"has_fulltext":true,"cited_by_count":95,"citation_normalized_percentile":{"value":0.96299185,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"573","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983000159263611,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7853370308876038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.735724687576294},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.729232132434845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5979006886482239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5427203178405762},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5041359663009644},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4838763475418091},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4837903678417206}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7853370308876038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735724687576294},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.729232132434845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5979006886482239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5427203178405762},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5041359663009644},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4838763475418091},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4837903678417206}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.21437/icslp.2002-195","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:82848","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228235","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/ajmera-rr-02-07","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":"conference proceedings"},{"id":"pmh:oai:infoscience.tind.io:82849","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228236","pdf_url":"https://infoscience.epfl.ch/record/82849/files/rr02-07.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:10.1.1.10.9438","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.9438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/~mccowan/pdf/ajmera-icslp2002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.8.7632","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.7632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.idiap.ch/pub/reports/2002/rr02-07.ps.gz","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:82848","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82848","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:82849","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82849","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:82848","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228235","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/ajmera-rr-02-07","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":"conference proceedings"},"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1591300715.pdf","grobid_xml":"https://content.openalex.org/works/W1591300715.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1240570839","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1547083988","https://openalex.org/W1564120349","https://openalex.org/W2095892407","https://openalex.org/W2111339787","https://openalex.org/W2141262306"],"related_works":["https://openalex.org/W1521049138","https://openalex.org/W1509309911","https://openalex.org/W2144208207","https://openalex.org/W2499802997","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W2128773298","https://openalex.org/W2160753975","https://openalex.org/W1940231550","https://openalex.org/W2118860825"],"abstract_inverted_index":{"An":[0],"HMM-based":[1],"speaker":[2,115],"clustering":[3],"framework":[4],"is":[5,33,47,64,100,118],"presented,":[6],"where":[7],"the":[8,20,67,73,78,89,95,103,121,129],"number":[9,44,122,131],"of":[10,45,75,87,94,111,123,132],"speakers":[11],"and":[12,54,91,114],"segmentation":[13],"boundaries":[14],"are":[15],"unknown":[16],"\\\\emph{a":[17],"priori}.":[18],"Ideally,":[19],"system":[21,99],"aims":[22],"to":[23,128],"create":[24],"one":[25],"pure":[26],"cluster":[27,113],"for":[28],"each":[29],"speaker.":[30],"The":[31,42,97],"HMM":[32],"ergodic":[34],"in":[35,62,109],"nature":[36],"with":[37],"a":[38,60,85],"minimum":[39],"duration":[40],"topology.":[41],"final":[43],"clusters":[46,53,124],"determined":[48],"automatically":[49],"by":[50],"merging":[51],"closest":[52],"retraining":[55],"this":[56],"new":[57],"cluster,":[58],"until":[59],"decrease":[61],"likelihood":[63],"observed.":[65],"In":[66],"same":[68],"framework,":[69],"we":[70],"also":[71],"examine":[72],"effect":[74],"using":[76],"only":[77],"features":[79],"from":[80],"highly":[81],"voiced":[82],"frames":[83],"as":[84],"means":[86],"improving":[88],"robustness":[90],"computational":[92],"complexity":[93],"algorithm.":[96],"proposed":[98],"assessed":[101],"on":[102],"1996":[104],"HUB-4":[105],"evaluation":[106],"test":[107],"set":[108],"terms":[110],"both":[112],"purity.":[116],"It":[117],"shown":[119],"that":[120],"found":[125],"often":[126],"correspond":[127],"actual":[130],"speakers.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
