{"id":"https://openalex.org/W2165776701","doi":"https://doi.org/10.1109/etfa.2008.4638386","title":"Speaker selection algorithm using audio and video information in a cluttered environment","display_name":"Speaker selection algorithm using audio and video information in a cluttered environment","publication_year":2008,"publication_date":"2008-09-01","ids":{"openalex":"https://openalex.org/W2165776701","doi":"https://doi.org/10.1109/etfa.2008.4638386","mag":"2165776701"},"language":"en","primary_location":{"id":"doi:10.1109/etfa.2008.4638386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/etfa.2008.4638386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Emerging Technologies and Factory Automation","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/A5027257727","display_name":"Yoonseob Lim","orcid":"https://orcid.org/0000-0003-4754-6038"},"institutions":[{"id":"https://openalex.org/I58716616","display_name":"Korea Institute of Science and Technology","ror":"https://ror.org/05kzfa883","country_code":"KR","type":"facility","lineage":["https://openalex.org/I27494661","https://openalex.org/I2801339556","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I4387152098","https://openalex.org/I58716616"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yoonseob Lim","raw_affiliation_strings":["Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Korea","Center for Cognitive Robotics Research, Korea Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I58716616"]},{"raw_affiliation_string":"Center for Cognitive Robotics Research, Korea Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I58716616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052822694","display_name":"JongSuk Choi","orcid":"https://orcid.org/0000-0002-0399-4675"},"institutions":[{"id":"https://openalex.org/I58716616","display_name":"Korea Institute of Science and Technology","ror":"https://ror.org/05kzfa883","country_code":"KR","type":"facility","lineage":["https://openalex.org/I27494661","https://openalex.org/I2801339556","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I4387152098","https://openalex.org/I58716616"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongsuk Choi","raw_affiliation_strings":["Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Korea","Center for Cognitive Robotics Research, Korea Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I58716616"]},{"raw_affiliation_string":"Center for Cognitive Robotics Research, Korea Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I58716616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027257727"],"corresponding_institution_ids":["https://openalex.org/I58716616"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19752594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"150","last_page":"155"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9979000091552734,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.8148021697998047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5497897863388062},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5288929343223572},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5236173272132874},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5171300768852234},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.504599928855896},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5045417547225952},{"id":"https://openalex.org/keywords/data-association","display_name":"Data association","score":0.5013179779052734},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4960416257381439},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43912434577941895},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4241478443145752},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.4232105612754822},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4194907248020172},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.393251895904541},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10954618453979492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148021697998047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5497897863388062},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5288929343223572},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5236173272132874},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5171300768852234},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.504599928855896},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5045417547225952},{"id":"https://openalex.org/C2983325608","wikidata":"https://www.wikidata.org/wiki/Q17084606","display_name":"Data association","level":3,"score":0.5013179779052734},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4960416257381439},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43912434577941895},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4241478443145752},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.4232105612754822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4194907248020172},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.393251895904541},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10954618453979492},{"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/etfa.2008.4638386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/etfa.2008.4638386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Emerging Technologies and Factory Automation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1483307070","https://openalex.org/W2127923214","https://openalex.org/W2130992468","https://openalex.org/W2133447020","https://openalex.org/W2138414774","https://openalex.org/W2142511364","https://openalex.org/W2167582467","https://openalex.org/W4285719527","https://openalex.org/W6679443918"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"data":[3,10,111,125],"association":[4,37,86,126],"method":[5,127],"using":[6],"audio":[7,76,107],"and":[8,19,40,49,70,89,106,115],"video":[9],"together":[11],"to":[12,24,33,82,119],"localize":[13],"targets":[14,95],"in":[15,132],"a":[16,133],"cluttered":[17,134],"environment":[18],"detect":[20],"who":[21],"is":[22,27,31,80,100],"speaking":[23,50,55],"the":[25,54,60,66,73,104,121],"robot":[26,97],"presented.":[28],"Particle":[29],"filter":[30],"applied":[32,81],"find":[34,83],"an":[35,84],"optimal":[36,85],"between":[38,68,87],"target":[39,88],"measurements":[41],"efficiently.":[42],"State":[43],"variables":[44],"are":[45],"composed":[46],"of":[47,94,123],"position":[48],"status.":[51],"To":[52],"update":[53],"state,":[56],"we":[57],"first":[58],"evaluate":[59],"upcoming":[61],"sound":[62],"signal":[63],"based":[64,102],"on":[65,103,117],"cross-correlation":[67],"microphones":[69],"then":[71],"calculate":[72],"likelihood":[74],"for":[75,128],"information.":[77,108],"Visual":[78],"measurement":[79],"visual":[90],"observations.":[91],"The":[92],"number":[93],"that":[96],"should":[98],"interact":[99],"updated":[101],"vision":[105],"Several":[109],"experimental":[110],"were":[112],"collected":[113],"beforehand":[114],"simulated":[116],"computer":[118],"verify":[120],"performance":[122],"proposed":[124],"speaker":[129],"selection":[130],"problem":[131],"environment.":[135]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
