{"id":"https://openalex.org/W2019231209","doi":"https://doi.org/10.1109/iros.2013.6696918","title":"Nested iGMM recognition and multiple hypothesis tracking of moving sound sources for mobile robot audition","display_name":"Nested iGMM recognition and multiple hypothesis tracking of moving sound sources for mobile robot audition","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2019231209","doi":"https://doi.org/10.1109/iros.2013.6696918","mag":"2019231209"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2013.6696918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5102748358","display_name":"Yoko Sasaki","orcid":"https://orcid.org/0000-0002-1220-6124"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yoko Sasaki","raw_affiliation_strings":["Digital Human Research Center, National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan","Digital Human Res. Center, Nat. Inst. of Adv. Ind. Sci. & Technol., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Digital Human Research Center, National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Digital Human Res. Center, Nat. Inst. of Adv. Ind. Sci. & Technol., Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026606288","display_name":"Naotaka Hatao","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naotaka Hatao","raw_affiliation_strings":["Digital Human Research Center, National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan","Digital Human Res. Center, Nat. Inst. of Adv. Ind. Sci. & Technol., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Digital Human Research Center, National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Digital Human Res. Center, Nat. Inst. of Adv. Ind. Sci. & Technol., Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Digital Human Research Center, National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan","Digital Human Res. Center, Nat. Inst. of Adv. Ind. Sci. & Technol., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Digital Human Research Center, National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Digital Human Res. Center, Nat. Inst. of Adv. Ind. Sci. & Technol., Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113822737","display_name":"Satoshi Kagami","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Kagami","raw_affiliation_strings":["Digital Human Research Center, National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan","Digital Human Res. Center, Nat. Inst. of Adv. Ind. Sci. & Technol., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Digital Human Research Center, National Institute of Advanced Industrial Science and Technology, Koto-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Digital Human Res. Center, Nat. Inst. of Adv. Ind. Sci. & Technol., Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102748358"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":3.2156,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.92182185,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2","issue":null,"first_page":"3930","last_page":"3936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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/T11220","display_name":"Water Systems and Optimization","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"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/computer-science","display_name":"Computer science","score":0.720494270324707},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6262672543525696},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6064479351043701},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5655733942985535},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5417348742485046},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5079436898231506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5002598762512207},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5001797676086426},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4744454622268677},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4727010726928711},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4684619605541229},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4454871416091919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4398399293422699},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.42444390058517456},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19583997130393982},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.07201182842254639}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.720494270324707},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6262672543525696},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6064479351043701},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5655733942985535},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5417348742485046},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5079436898231506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5002598762512207},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5001797676086426},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4744454622268677},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4727010726928711},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4684619605541229},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4454871416091919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4398399293422699},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.42444390058517456},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19583997130393982},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.07201182842254639},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":2,"locations":[{"id":"doi:10.1109/iros.2013.6696918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2013.6696918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.717.1725","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.717.1725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/%7Eyoshii/papers/iros-2013-sasaki.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W42422348","https://openalex.org/W222076935","https://openalex.org/W1988030566","https://openalex.org/W2051373563","https://openalex.org/W2069429561","https://openalex.org/W2093010905","https://openalex.org/W2107456423","https://openalex.org/W2127923214","https://openalex.org/W2135131618","https://openalex.org/W2151967501","https://openalex.org/W2165802417","https://openalex.org/W6608730375","https://openalex.org/W6682569104"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W2098651198","https://openalex.org/W2126980866"],"abstract_inverted_index":{"The":[0,35,57],"paper":[1],"proposes":[2],"two":[3,97],"modules":[4,98],"for":[5,29,79],"a":[6],"mobile":[7],"robot":[8,112],"audition":[9,113],"system:":[10],"1)":[11],"recognizing":[12,30],"surrounding":[13],"acoustic":[14],"event,":[15],"2)":[16],"tracking":[17,60,116],"moving":[18,119],"sound":[19,105,123],"sources.":[20],"We":[21],"propose":[22],"nested":[23],"infinite":[24],"Gaussian":[25],"mixture":[26],"model":[27],"(iGMM)":[28],"frame":[31],"based":[32,104],"feature":[33],"vectors.":[34],"main":[36],"advantage":[37],"is":[38,44],"that":[39],"the":[40,82,110],"number":[41],"of":[42,64,91,117],"classes":[43],"allowed":[45],"to":[46,52,101],"increase":[47],"without":[48],"bound,":[49],"if":[50],"necessary,":[51],"represent":[53],"unknown":[54],"audio":[55,66],"input.":[56],"multiple":[58,94,118],"hypothesis":[59],"module":[61],"provides":[62],"time-series":[63],"separated":[65],"stream":[67,92],"using":[68],"localized":[69],"directions":[70],"and":[71,88,107,109],"recognition":[72],"results":[73],"at":[74],"each":[75],"frame.":[76],"Not":[77],"only":[78],"continuous":[80],"sounds,":[81],"proposed":[83],"tracker":[84],"automatically":[85],"detects":[86],"appearing":[87],"disappearing":[89],"point":[90],"from":[93],"hypothesis.":[95],"These":[96],"are":[99],"connected":[100],"microphone":[102],"array":[103],"localization":[106],"separation,":[108],"combined":[111],"system":[114],"achieved":[115],"sounds":[120],"including":[121],"intermittent":[122],"source.":[124]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
