{"id":"https://openalex.org/W2159094433","doi":"https://doi.org/10.1109/tmm.2012.2233724","title":"A Multimodal Approach to Speaker Diarization on TV Talk-Shows","display_name":"A Multimodal Approach to Speaker Diarization on TV Talk-Shows","publication_year":2012,"publication_date":"2012-12-12","ids":{"openalex":"https://openalex.org/W2159094433","doi":"https://doi.org/10.1109/tmm.2012.2233724","mag":"2159094433"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2012.2233724","doi":"https://doi.org/10.1109/tmm.2012.2233724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2012.2233724","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","norway-1","poland-140","russia-white-list-1","vabb-shw"],"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 Multimedia","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036989164","display_name":"F\u00e9licien Vallet","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210125774","display_name":"Institut National de l'Audiovisuel","ror":"https://ror.org/02zwkwz55","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210125774"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"F\u00e9licien Vallet","raw_affiliation_strings":["Research Department of Institut national de laudiovisuel, Bry-sur-Marne, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Department of Institut national de laudiovisuel, Bry-sur-Marne, France","institution_ids":["https://openalex.org/I4210125774"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X","observed_orcids":["https://orcid.org/0000-0002-0028-327X"]},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Slim Essid","raw_affiliation_strings":["Telecom ParisTech; CNRS/LTCI, Institut Mines-Telecom, Paris, France","CNRS/LTCI, Institut Mines-Telecom, Paris, France","Telecom ParisTech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telecom ParisTech; CNRS/LTCI, Institut Mines-Telecom, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I190752583","https://openalex.org/I205703379","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"CNRS/LTCI, Institut Mines-Telecom, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"Telecom ParisTech","institution_ids":["https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087582941","display_name":"Jean Carrive","orcid":"https://orcid.org/0000-0002-6107-5351","observed_orcids":["https://orcid.org/0000-0002-6107-5351"]},"institutions":[{"id":"https://openalex.org/I4210125774","display_name":"Institut National de l'Audiovisuel","ror":"https://ror.org/02zwkwz55","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210125774"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean Carrive","raw_affiliation_strings":["Research Department of Institut national de laudiovisuel, Bry-sur-Marne, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Department of Institut national de laudiovisuel, Bry-sur-Marne, France","institution_ids":["https://openalex.org/I4210125774"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":2.0314,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.8788287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":"15","issue":"3","first_page":"509","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5601000189781189,"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":0.5601000189781189,"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":0.3840000033378601,"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/T12031","display_name":"Speech and dialogue systems","score":0.01730000041425228,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.9990000128746033},{"id":"https://openalex.org/keywords/television-talk-shows","display_name":"television talk shows","score":0.8379999995231628},{"id":"https://openalex.org/keywords/visual-cues","display_name":"visual cues","score":0.671999990940094},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.36399999260902405},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.9049999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8849915266036987},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.855025053024292},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5479868650436401},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49944424629211426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49881672859191895},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4964643120765686},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.449641615152359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42695707082748413},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4107336699962616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2012.2233724","doi":"https://doi.org/10.1109/tmm.2012.2233724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2012.2233724","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-a","cwts-core","dongbi-a","jufo-3","norway-1","poland-140","russia-white-list-1","vabb-shw"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02943545v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-02943545","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Multimedia, 2013, 15 (3), pp.509-520. &#x27E8;10.1109/TMM.2012.2233724&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W613294932","https://openalex.org/W1510526001","https://openalex.org/W1560013842","https://openalex.org/W1560724230","https://openalex.org/W1587845029","https://openalex.org/W1673039069","https://openalex.org/W1988910659","https://openalex.org/W2002256968","https://openalex.org/W2011646888","https://openalex.org/W2015293542","https://openalex.org/W2027283140","https://openalex.org/W2030536784","https://openalex.org/W2033620616","https://openalex.org/W2036365100","https://openalex.org/W2042608483","https://openalex.org/W2053667957","https://openalex.org/W2081074144","https://openalex.org/W2083976588","https://openalex.org/W2088362548","https://openalex.org/W2094386595","https://openalex.org/W2098923380","https://openalex.org/W2099403067","https://openalex.org/W2100973746","https://openalex.org/W2104804886","https://openalex.org/W2106131881","https://openalex.org/W2107283705","https://openalex.org/W2114708606","https://openalex.org/W2114981053","https://openalex.org/W2115130489","https://openalex.org/W2115175902","https://openalex.org/W2118877769","https://openalex.org/W2125336414","https://openalex.org/W2134380836","https://openalex.org/W2153557299","https://openalex.org/W2153635508","https://openalex.org/W2159591770","https://openalex.org/W2161448797","https://openalex.org/W2167537125","https://openalex.org/W2168996682","https://openalex.org/W2169570466","https://openalex.org/W3097096317","https://openalex.org/W3195149063","https://openalex.org/W3214102110","https://openalex.org/W4234640999","https://openalex.org/W4251308012"],"related_works":["https://openalex.org/W1595802121","https://openalex.org/W2525932165","https://openalex.org/W4405621913","https://openalex.org/W2294443754","https://openalex.org/W2004419043","https://openalex.org/W4412944939","https://openalex.org/W3113144688","https://openalex.org/W4224925049","https://openalex.org/W2991553872","https://openalex.org/W4403618680"],"abstract_inverted_index":{"In":[0],"this":[1,49,70,138],"article,":[2],"we":[3,36],"propose":[4,37],"solutions":[5],"to":[6,58,182],"the":[7,46,54,59,94,104,124,127,169],"problem":[8,16],"of":[9,12,26,48,51,69,93,106,126,137,171,185],"speaker":[10,183],"diarization":[11,65,184],"TV":[13,95,133,190],"talk-shows,":[14],"a":[15,80,114,131],"for":[17,62,90,123],"which":[18],"adapted":[19],"multimodal":[20,180],"approaches,":[21],"relying":[22],"on":[23,45,143],"other":[24],"streams":[25],"data":[27,100,129],"than":[28],"only":[29],"audio,":[30],"remain":[31],"largely":[32],"under":[33],"exploited.":[34],"Hence":[35],"an":[38,63,87],"original":[39],"system":[40,71,163],"that":[41,160],"leverages":[42],"prior":[43],"knowledge":[44],"structure":[47],"type":[50],"content,":[52],"especially":[53],"visual":[55,107,177],"information":[56],"relating":[57],"active":[60],"speakers,":[61],"improved":[64],"performance.":[66],"The":[67,135,157],"architecture":[68,140],"can":[72],"be":[73],"decomposed":[74],"into":[75],"two":[76,144],"main":[77],"stages.":[78],"First":[79],"reliable":[81],"training":[82],"set":[83],"is":[84,101,141],"created,":[85],"in":[86,113,179],"unsupervised":[88],"fashion,":[89],"each":[91],"participant":[92],"program":[96],"being":[97],"processed.":[98],"This":[99],"assembled":[102],"by":[103],"association":[105],"and":[108,151],"audio":[109],"descriptors":[110],"carefully":[111],"selected":[112],"clustering":[115],"cascade.":[116],"Then,":[117],"Support":[118],"Vector":[119],"Machines":[120],"are":[121],"used":[122],"classification":[125],"speech":[128],"(of":[130],"given":[132],"program).":[134],"performance":[136],"new":[139,162],"assessed":[142],"French":[145],"talk-show":[146],"collections:":[147],"Le":[148],"Grand":[149],"\u00c9chiquier":[150],"On":[152],"n'a":[153],"pas":[154],"tout":[155],"dit.":[156],"results":[158],"show":[159],"our":[161],"outperforms":[164],"state-of-the-art":[165],"methods,":[166,173],"thus":[167],"evidencing":[168],"effectiveness":[170],"kernel-based":[172],"as":[174,176,189],"well":[175],"cues,":[178],"approaches":[181],"challenging":[186],"contents":[187],"such":[188],"talk-shows.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
