{"id":"https://openalex.org/W2166828255","doi":"https://doi.org/10.1109/roman.2007.4415110","title":"Particle Filter Algorithm for Single Speaker Tracking with Audio-Video Data Fusion","display_name":"Particle Filter Algorithm for Single Speaker Tracking with Audio-Video Data Fusion","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2166828255","doi":"https://doi.org/10.1109/roman.2007.4415110","mag":"2166828255"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2007.4415110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2007.4415110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102114106","display_name":"Yoon Seob Lim","orcid":null},"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":"Yoon Seob Lim","raw_affiliation_strings":["Korea Institute of Science and Technology, Center for Cognitive Robotics Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology, Center for Cognitive Robotics Research, Seoul, South Korea","institution_ids":["https://openalex.org/I58716616"]}]},{"author_position":"middle","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":"Jong-Suk Choi","raw_affiliation_strings":["Korea Institute of Science and Technology, Center for Cognitive Robotics Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology, Center for Cognitive Robotics Research, Seoul, South Korea","institution_ids":["https://openalex.org/I58716616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029001928","display_name":"Munsang Kim","orcid":null},"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":"Munsang Kim","raw_affiliation_strings":["Korea Institute of Science and Technology, Center for Cognitive Robotics Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Institute of Science and Technology, Center for Cognitive Robotics Research, Seoul, South Korea","institution_ids":["https://openalex.org/I58716616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I58716616"],"apc_list":null,"apc_paid":null,"fwci":0.3015,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52646548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"363","last_page":"367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.996999979019165,"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":0.9944000244140625,"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":0.7757977843284607},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.7173016667366028},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.656732439994812},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5610471367835999},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5119346380233765},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.5019173622131348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48424646258354187},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4534164071083069},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42779797315597534},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.40672457218170166},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.35355985164642334},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3405151963233948},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.13373252749443054},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11532115936279297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757977843284607},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.7173016667366028},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.656732439994812},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5610471367835999},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5119346380233765},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5019173622131348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48424646258354187},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4534164071083069},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42779797315597534},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.40672457218170166},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.35355985164642334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3405151963233948},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.13373252749443054},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11532115936279297},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/roman.2007.4415110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2007.4415110","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1483307070","https://openalex.org/W1513768190","https://openalex.org/W1536997931","https://openalex.org/W2107493093","https://openalex.org/W2130992468","https://openalex.org/W2133447020","https://openalex.org/W2138414774","https://openalex.org/W2142511364","https://openalex.org/W2160337655","https://openalex.org/W2161406034","https://openalex.org/W2168573944","https://openalex.org/W4247752416","https://openalex.org/W6630587866","https://openalex.org/W6679443918"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2088690926","https://openalex.org/W2098934641"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,14,21,72,128],"single":[4,132],"speaker":[5],"tracking":[6,23,114],"mechanism":[7,122],"with":[8,17,102],"particle":[9],"filter":[10],"is":[11,95,115],"presented":[12],"for":[13,71,81],"reliable":[15,112],"interaction":[16],"robot.":[18],"To":[19],"have":[20],"smooth":[22],"result,":[24],"we":[25,38,60,87,107,118],"use":[26,39,88],"not":[27],"only":[28],"audio":[29,82,103],"data":[30,120],"but":[31],"also":[32],"video":[33,85,105],"data.":[34],"For":[35,84],"sound":[36],"observation,":[37,86],"Time":[40],"Delay":[41],"Of":[42],"Arrival":[43],"(TDOA)":[44],"between":[45],"two":[46],"microphones,":[47],"and":[48,104],"in":[49,55],"order":[50],"to":[51,66,77],"expect":[52],"high":[53],"reliability":[54],"the":[56,67,79,99],"likelihood":[57,80],"of":[58,69,75,92],"localization,":[59],"apply":[61,119],"variable":[62],"sensitivity":[63],"values":[64],"according":[65],"angle":[68],"arrival":[70],"triangle":[73],"arrangement":[74],"microphones":[76],"calculate":[78],"observation.":[83],"face":[89],"detection":[90],"routine":[91],"OpenCV":[93],"which":[94],"widely":[96],"available":[97],"through":[98],"Internet.":[100],"Together":[101],"data,":[106],"found":[108],"out":[109],"that":[110],"more":[111],"source":[113],"possible":[116,125],"if":[117],"fusion":[121],"at":[123],"every":[124],"environment":[126],"on":[127],"robot":[129],"platform":[130],"than":[131],"information.":[133]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
