{"id":"https://openalex.org/W2142333570","doi":"https://doi.org/10.1109/slt.2012.6424236","title":"Speaker diarization and linking of large corpora","display_name":"Speaker diarization and linking of large corpora","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2142333570","doi":"https://doi.org/10.1109/slt.2012.6424236","mag":"2142333570"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/bitstreams/67276425-e98f-4518-b05d-36562064871a/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027284390","display_name":"Marc Ferr\u00e0s","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":"Marc Ferras","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062838505","display_name":"Herve Boudard","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"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herve Boudard","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","Ecole Polytechnique F\u00e9d\u00e9rale, Lausanne (EPFL), Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale, Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027284390"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":6.1879,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.96341069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9977999925613403,"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":0.9976000189781189,"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":0.9274362325668335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7953715920448303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6182959675788879},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5742942690849304},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5597493052482605},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5587430000305176},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5468931794166565},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.5143874287605286},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.4519467353820801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3373510539531708},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0897459089756012}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9274362325668335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7953715920448303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6182959675788879},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5742942690849304},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5597493052482605},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5587430000305176},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5468931794166565},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.5143874287605286},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.4519467353820801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3373510539531708},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0897459089756012},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2012.6424236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:192414","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/98180","pdf_url":"https://infoscience.epfl.ch/bitstreams/67276425-e98f-4518-b05d-36562064871a/download","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.epfl.ch:192414","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192414","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:192414","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/98180","pdf_url":"https://infoscience.epfl.ch/bitstreams/67276425-e98f-4518-b05d-36562064871a/download","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2142333570.pdf","grobid_xml":"https://content.openalex.org/works/W2142333570.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2007995029","https://openalex.org/W2016381774","https://openalex.org/W2063511145","https://openalex.org/W2098726438","https://openalex.org/W2107638917","https://openalex.org/W2110023316","https://openalex.org/W2115599677","https://openalex.org/W2121415728","https://openalex.org/W2136879537","https://openalex.org/W2150769028","https://openalex.org/W2397770179"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Performing":[0],"speaker":[1,45,48,59,74,79,93,99,125,173],"diarization":[2,46,60,100,183],"of":[3,6,44,67,167,196],"a":[4,17,40,97],"collection":[5],"recordings,":[7],"where":[8],"speakers":[9],"are":[10,30,52,207],"uniquely":[11],"identified":[12],"across":[13],"the":[14,85,92,103,107,116,129,133,139,155,168,179,194,197],"database,":[15],"is":[16,120,143,162],"challenging":[18],"task.":[19],"In":[20,35],"this":[21,36,149],"context,":[22],"inter-session":[23,70],"variability":[24,71,109],"compensation":[25],"and":[26,47,61,69,151,158,174,181,189],"reasonable":[27],"computation":[28],"times":[29],"essential":[31],"to":[32,54,113,122,192],"be":[33],"addressed.":[34],"paper":[37],"we":[38],"propose":[39],"two-stage":[41],"system":[42,76,161,211],"composed":[43],"linking":[49,75],"modules":[50],"that":[51,62,90],"able":[53],"perform":[55],"data":[56,68],"set":[57],"wide":[58],"handle":[63],"both":[64],"large":[65],"volumes":[66],"compensation.":[72],"The":[73,160],"agglomeratively":[77],"clusters":[78,94,126],"factor":[80],"posterior":[81],"distributions,":[82],"obtained":[83,131,208],"within":[84,115],"Joint":[86],"Factor":[87],"Analysis":[88],"framework,":[89],"model":[91],"output":[95],"by":[96,127,132],"standard":[98],"system.":[101,199],"Therefore,":[102],"technique":[104],"inherently":[105],"compensates":[106],"channel":[108,175],"effects":[110],"from":[111],"recording":[112,114],"database.":[117],"A":[118],"threshold":[119],"used":[121],"obtain":[123],"meaningful":[124],"cutting":[128],"dendrogram":[130],"agglomerative":[134],"clustering.":[135],"We":[136,177],"show":[137],"how":[138],"Hotteling":[140],"t-square":[141],"statistic":[142],"an":[144],"interesting":[145],"distance":[146],"measure":[147,193],"for":[148,209],"task":[150],"input":[152],"data,":[153],"obtaining":[154],"best":[156],"results":[157],"stability.":[159],"evaluated":[163],"using":[164],"three":[165],"subsets":[166],"AMI":[169],"corpus":[170],"involving":[171],"different":[172],"variabilities.":[176],"use":[178],"within-recording":[180,205],"across-recording":[182],"error":[184],"rates":[185],"(DER),":[186],"cluster":[187,190],"purity":[188],"coverage":[191],"performance":[195],"proposed":[198],"Across-recording":[200],"DER":[201,206],"as":[202,204],"low":[203],"some":[210],"setups.":[212]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}