{"id":"https://openalex.org/W2001183000","doi":"https://doi.org/10.1109/mlsp.2014.6958874","title":"Audio-visual speaker localization via weighted clustering","display_name":"Audio-visual speaker localization via weighted clustering","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2001183000","doi":"https://doi.org/10.1109/mlsp.2014.6958874","mag":"2001183000"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2014.6958874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2014.6958874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01053732","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072548521","display_name":"Israel D. Gebru","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Israel D. Gebru","raw_affiliation_strings":["INRIA Grenoble Rhone-Alpes, FRANCE","Inria Grenoble Rh\u00f4ne-Alpes, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, FRANCE","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, France#TAB#","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["INRIA Grenoble Rhone-Alpes, FRANCE","Inria Grenoble Rh\u00f4ne-Alpes, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, FRANCE","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, France#TAB#","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["INRIA Grenoble Rhone-Alpes, FRANCE","Inria Grenoble Rh\u00f4ne-Alpes, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, FRANCE","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, France#TAB#","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088691547","display_name":"Florence Forbes","orcid":"https://orcid.org/0000-0003-3639-0226"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florence Forbes","raw_affiliation_strings":["INRIA Grenoble Rhone-Alpes, FRANCE","Inria Grenoble Rh\u00f4ne-Alpes, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, FRANCE","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Inria Grenoble Rh\u00f4ne-Alpes, France#TAB#","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"62","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9914000034332275,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8511157035827637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.789527177810669},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6957950592041016},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.693246066570282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5246139764785767},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5031716227531433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4545305669307709},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4459637701511383},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4419103264808655},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4403773546218872},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.37831127643585205},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2574056386947632},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08626478910446167}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8511157035827637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789527177810669},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6957950592041016},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.693246066570282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246139764785767},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5031716227531433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4545305669307709},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4459637701511383},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4419103264808655},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4403773546218872},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.37831127643585205},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2574056386947632},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08626478910446167},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp.2014.6958874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2014.6958874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01053732v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01053732","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Workshop on Machine Learning for Signal Processing, Sep 2014, Reims, France. pp.1-6, ⟨10.1109/MLSP.2014.6958874⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01053732v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01053732","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Workshop on Machine Learning for Signal Processing, Sep 2014, Reims, France. pp.1-6, ⟨10.1109/MLSP.2014.6958874⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1564251190","https://openalex.org/W1869980952","https://openalex.org/W1971791733","https://openalex.org/W1975143133","https://openalex.org/W2011699475","https://openalex.org/W2022699039","https://openalex.org/W2047508432","https://openalex.org/W2096464179","https://openalex.org/W2124247842","https://openalex.org/W2133916961","https://openalex.org/W2164899449","https://openalex.org/W2167709189","https://openalex.org/W2168010845","https://openalex.org/W2169570466","https://openalex.org/W2169770604","https://openalex.org/W2915001123","https://openalex.org/W4293352877","https://openalex.org/W6639402332","https://openalex.org/W6662335928","https://openalex.org/W6678755322","https://openalex.org/W6679740376","https://openalex.org/W6684193366","https://openalex.org/W6684806894","https://openalex.org/W6759766560","https://openalex.org/W6842821731"],"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":{"In":[0],"this":[1,17],"paper":[2],"we":[3,69],"address":[4,16],"the":[5,20,39,72,82,118,121],"problem":[6,18,83],"of":[7,22,41,44,84,120],"detecting":[8,85],"and":[9,68,86,95,103,133,137],"locating":[10],"speakers":[11],"using":[12,92],"audiovisual":[13],"data.":[14],"We":[15,24,62,116],"in":[19,55,125],"framework":[21],"clustering.":[23],"propose":[25],"a":[26,33,56,64,88,100,112,134,139,143],"novel":[27],"weighted":[28],"clustering":[29,47,77],"method":[30,122],"based":[31],"on":[32],"finite":[34],"mixture":[35,66],"model":[36,67],"which":[37],"explores":[38],"idea":[40],"non-uniform":[42],"weighting":[43,114],"observations.":[45],"Weighted-data":[46],"techniques":[48],"have":[49],"already":[50],"been":[51],"proposed,":[52],"but":[53],"not":[54],"generative":[57],"setting":[58],"as":[59],"presented":[60],"here.":[61],"introduce":[63],"weighted-data":[65],"formally":[70],"devise":[71],"associated":[73],"EM":[74],"procedure.":[75],"The":[76],"algorithm":[78],"is":[79,108],"applied":[80],"to":[81],"localizing":[87],"speaker":[89],"over":[90],"time":[91],"both":[93],"visual":[94],"auditory":[96],"observations":[97],"gathered":[98],"with":[99,123,142],"single":[101],"camera":[102],"two":[104,126],"microphones.":[105],"Audiovisual":[106],"fusion":[107],"enforced":[109],"by":[110],"introducing":[111],"cross-modal":[113],"scheme.":[115],"test":[117],"robustness":[119],"experiments":[124],"challenging":[127],"scenarios:":[128],"disambiguate":[129],"between":[130],"an":[131],"active":[132],"non-active":[135],"speaker,":[136],"associate":[138],"speech":[140],"signal":[141],"person.":[144]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}