{"id":"https://openalex.org/W2029210671","doi":"https://doi.org/10.1109/mfi.2012.6343015","title":"Multiple active speaker localization based on audio-visual fusion in two stages","display_name":"Multiple active speaker localization based on audio-visual fusion in two stages","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2029210671","doi":"https://doi.org/10.1109/mfi.2012.6343015","mag":"2029210671"},"language":"en","primary_location":{"id":"doi:10.1109/mfi.2012.6343015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mfi.2012.6343015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","raw_type":"proceedings-article"},"type":"article","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/A5100730692","display_name":"Li Zhao","orcid":"https://orcid.org/0000-0001-5787-2705"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhao Li","raw_affiliation_strings":["Telecommunications Laboratory, University of Saarland, Saarbruecken, Germany","Telecommunications Lab, Saarland University Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telecommunications Laboratory, University of Saarland, Saarbruecken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Telecommunications Lab, Saarland University Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025754162","display_name":"Thorsten Herfet","orcid":"https://orcid.org/0000-0002-3746-7638"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thorsten Herfet","raw_affiliation_strings":["Telecommunications Laboratory, University of Saarland, Saarbruecken, Germany","Telecommunications Lab, Saarland University Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Telecommunications Laboratory, University of Saarland, Saarbruecken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Telecommunications Lab, Saarland University Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078725212","display_name":"Martin Grochulla","orcid":null},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Grochulla","raw_affiliation_strings":["Max-Planck-Institut f\u00fcr Informatik, Saarbruecken, Germany","Max-Planck Institut F\u00fcr Informatik, Saarbr\u00fccken, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck-Institut f\u00fcr Informatik, Saarbruecken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Max-Planck Institut F\u00fcr Informatik, Saarbr\u00fccken, Germany#TAB#","institution_ids":["https://openalex.org/I149899117"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047425002","display_name":"Thorsten Thorm\u00e4hlen","orcid":"https://orcid.org/0000-0002-8298-6373"},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thorsten Thormahlen","raw_affiliation_strings":["Max-Planck-Institut f\u00fcr Informatik, Saarbruecken, Germany","Max-Planck Institut F\u00fcr Informatik, Saarbr\u00fccken, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max-Planck-Institut f\u00fcr Informatik, Saarbruecken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"Max-Planck Institut F\u00fcr Informatik, Saarbr\u00fccken, Germany#TAB#","institution_ids":["https://openalex.org/I149899117"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7311,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/robustness","display_name":"Robustness (evolution)","score":0.7870081663131714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7732498645782471},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6645264625549316},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6457667946815491},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6342909336090088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.551642119884491},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4953676462173462},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4896855652332306},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4525352120399475},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4198814034461975},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.38397467136383057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33480948209762573},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06961920857429504},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.06341713666915894}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7870081663131714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7732498645782471},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6645264625549316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6457667946815491},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6342909336090088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551642119884491},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4953676462173462},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4896855652332306},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4525352120399475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4198814034461975},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38397467136383057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33480948209762573},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06961920857429504},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.06341713666915894},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/mfi.2012.6343015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mfi.2012.6343015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.388.3404","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.388.3404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.informatik.uni-marburg.de/~thormae/paper/MFI12.pdf","raw_type":"text"},{"id":"pmh:oai:pure.mpg.de:item_1858692","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0014-F319-D","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2012 IEEE Conference on Multisensor Fusion and Integration for Intelligent Systems","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1579918694","https://openalex.org/W1581848821","https://openalex.org/W1869980952","https://openalex.org/W2001899073","https://openalex.org/W2025127228","https://openalex.org/W2056551376","https://openalex.org/W2096464179","https://openalex.org/W2096554907","https://openalex.org/W2106071216","https://openalex.org/W2115797648","https://openalex.org/W2140831887","https://openalex.org/W2164598857","https://openalex.org/W2167206042","https://openalex.org/W2169570466","https://openalex.org/W2544981553","https://openalex.org/W6677030111","https://openalex.org/W6684340747","https://openalex.org/W6729330800"],"related_works":["https://openalex.org/W2126085626","https://openalex.org/W2545131480","https://openalex.org/W208363076","https://openalex.org/W1973693762","https://openalex.org/W2087341511","https://openalex.org/W4230495983","https://openalex.org/W1946464671","https://openalex.org/W2141917278","https://openalex.org/W1843883989","https://openalex.org/W2162533796"],"abstract_inverted_index":{"Localization":[0],"of":[1,19,93,122],"multiple":[2],"active":[3],"speakers":[4],"in":[5,57,115],"natural":[6],"environments":[7],"with":[8,33,43],"only":[9],"two":[10,58],"microphones":[11],"is":[12,66,87,110],"a":[13,83,97],"challenging":[14],"problem.":[15],"Reverberation":[16],"degrades":[17],"performance":[18,121],"speaker":[20,45,64],"localization":[21,34,100],"based":[22,53,68],"exclusively":[23],"on":[24,54,69],"directional":[25],"cues.":[26],"The":[27],"audio":[28],"modality":[29,39,108],"alone":[30,40,109],"has":[31,41],"problems":[32,42],"accuracy":[35,101],"while":[36],"the":[37,61,70,80,91,99,106,119,123],"video":[38],"false":[44,76],"activity":[46,65],"detections.":[47],"This":[48],"paper":[49],"presents":[50],"an":[51],"approach":[52],"audiovisual":[55],"fusion":[56,72,85],"stages.":[59],"In":[60,79],"first":[62],"stage,":[63,82],"detected":[67],"audio-visual":[71],"which":[73],"can":[74],"handle":[75],"lip":[77],"movements.":[78],"second":[81],"Gaussian":[84],"method":[86],"proposed":[88,124],"to":[89,105],"integrate":[90],"estimates":[92],"both":[94],"modalities.":[95],"As":[96],"consequence,":[98],"and":[102],"robustness":[103],"compared":[104],"audio/video":[107],"significantly":[111],"increased.":[112],"Experimental":[113],"results":[114],"various":[116],"scenarios":[117],"confirmed":[118],"improved":[120],"system.":[125]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
