{"id":"https://openalex.org/W2081817329","doi":"https://doi.org/10.1109/roman.2007.4415117","title":"Auditory and Visual Integration based Localization and Tracking of Multiple Moving Sounds in Daily-life Environments","display_name":"Auditory and Visual Integration based Localization and Tracking of Multiple Moving Sounds in Daily-life Environments","publication_year":2007,"publication_date":"2007-08-01","ids":{"openalex":"https://openalex.org/W2081817329","doi":"https://doi.org/10.1109/roman.2007.4415117","mag":"2081817329"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2007.4415117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2007.4415117","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":"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/A5054240780","display_name":"Hyun-Don Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hyun-Don Kim","raw_affiliation_strings":["Department of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","Speech Media Process. Group, Kyoto Univ., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Speech Media Process. Group, Kyoto Univ., Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["Department of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","Speech Media Process. Group, Kyoto Univ., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Speech Media Process. Group, Kyoto Univ., Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Department of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","Speech Media Process. Group, Kyoto Univ., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Speech Media Process. Group, Kyoto Univ., Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Department of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","Speech Media Process. Group, Kyoto Univ., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Speech Media Process. Group, Kyoto Univ., Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054240780"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.6331,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68848128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"399","last_page":"404"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9950000047683716,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7510389685630798},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.7473050355911255},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.571647047996521},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.534184455871582},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5122746825218201},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47907310724258423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4521591067314148},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.4321417808532715},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4196043014526367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510389685630798},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.7473050355911255},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.571647047996521},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.534184455871582},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5122746825218201},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47907310724258423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4521591067314148},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.4321417808532715},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4196043014526367},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/roman.2007.4415117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2007.4415117","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":9,"referenced_works":["https://openalex.org/W1869758581","https://openalex.org/W1912147533","https://openalex.org/W1985690171","https://openalex.org/W2101329857","https://openalex.org/W2116546045","https://openalex.org/W2119539043","https://openalex.org/W2147673046","https://openalex.org/W6639229959","https://openalex.org/W6675228299"],"related_works":["https://openalex.org/W2015530857","https://openalex.org/W1991846142","https://openalex.org/W1989212443","https://openalex.org/W2103644279","https://openalex.org/W4302986566","https://openalex.org/W1968585197","https://openalex.org/W2163445067","https://openalex.org/W4247544095","https://openalex.org/W2122155275","https://openalex.org/W2215635302"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"techniques":[3],"that":[4,26,99,152],"enable":[5],"talker":[6],"tracking":[7,118,124],"for":[8],"effective":[9],"human-robot":[10],"interaction.":[11],"To":[12],"track":[13,145],"moving":[14,21],"people":[15,146],"in":[16,157],"daily-life":[17,159],"environments,":[18],"localizing":[19],"multiple":[20,94],"sounds":[22,156],"is":[23,130,142],"necessary":[24],"so":[25],"robots":[27],"can":[28,65],"locate":[29],"talkers.":[30],"However,":[31],"the":[32,81,85,100,106,117,127,138,158],"conventional":[33,107],"method":[34,57,102],"requires":[35],"an":[36,59],"array":[37],"of":[38],"microphones":[39,72],"and":[40,58,73,88,126],"impulse":[41,77],"response":[42,78],"data.":[43,79],"Therefore,":[44],"we":[45,111],"propose":[46],"a":[47,51,113,122],"way":[48],"to":[49,91,116,120,132,144],"integrate":[50,133],"cross-power":[52],"spectrum":[53],"phase":[54],"analysis":[55],"(CSP)":[56],"expectation-maximization":[60],"(EM)":[61],"algorithm.":[62],"The":[63],"CSP":[64],"localize":[66],"sound":[67,95],"sources":[68],"using":[69],"only":[70],"two":[71],"does":[74],"not":[75],"need":[76],"Moreover,":[80],"EM":[82],"algorithm":[83],"increases":[84],"system's":[86],"effectiveness":[87],"allows":[89],"it":[90],"cope":[92],"with":[93,149],"sources.":[96],"We":[97],"confirmed":[98],"proposed":[101],"performs":[103],"better":[104],"than":[105],"method.":[108],"In":[109],"addition,":[110],"added":[112],"particle":[114,128,140],"filter":[115,129,141],"process":[119],"produce":[121],"reliable":[123],"path":[125],"able":[131,143],"audio-visual":[134],"information":[135],"effectively.":[136],"Furthermore,":[137],"applied":[139],"while":[147],"dealing":[148],"various":[150],"noises":[151],"are":[153],"even":[154],"loud":[155],"environments.":[160]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}