{"id":"https://openalex.org/W2122796820","doi":"https://doi.org/10.1109/iros.2003.1248800","title":"Applying scattering theory to robot audition system: robust sound source localization and extraction","display_name":"Applying scattering theory to robot audition system: robust sound source localization and extraction","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2122796820","doi":"https://doi.org/10.1109/iros.2003.1248800","mag":"2122796820"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2003.1248800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2003.1248800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)","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/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Nakadai","raw_affiliation_strings":["Honda Research Insutitute Japan, Co., Ltd., Wako-shi, Saitama, Japan","Honda Research Institute, Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Insutitute Japan, Co., Ltd., Wako-shi, Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute, Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004052704","display_name":"Daisuke Matsuura","orcid":"https://orcid.org/0000-0003-4898-4689"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"D. Matsuura","raw_affiliation_strings":["Graduate School of Science and Engineering, Tokyo Institute of Technology","Tokyo Inst. of Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Inst. of Tech","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H.G. Okuno","raw_affiliation_strings":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Wako, Japan","Kyoto univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Wako, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086835862","display_name":"Hiroaki Kitano","orcid":"https://orcid.org/0000-0002-3589-1953"},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210086780"]},{"id":"https://openalex.org/I4210110781","display_name":"ARCH Development Corporation","ror":"https://ror.org/021wdzv30","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210110781"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"H. Kitano","raw_affiliation_strings":["Kitano Symbiotic Systems Project, ERATO, Japan Science and Technology Corp","Japan Science and Technology Agency"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kitano Symbiotic Systems Project, ERATO, Japan Science and Technology Corp","institution_ids":["https://openalex.org/I4210110781"]},{"raw_affiliation_string":"Japan Science and Technology Agency","institution_ids":["https://openalex.org/I4210086780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4097,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.95895597,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":null,"first_page":"1147","last_page":"1152"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9973999857902527,"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"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/sound-localization","display_name":"Sound localization","score":0.6615477800369263},{"id":"https://openalex.org/keywords/interaural-time-difference","display_name":"Interaural time difference","score":0.6477392315864563},{"id":"https://openalex.org/keywords/head-related-transfer-function","display_name":"Head-related transfer function","score":0.5990477204322815},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.5980228781700134},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.5776782631874084},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5629047155380249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5607936978340149},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5252068638801575},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.4947945475578308},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.4865254759788513},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4770345389842987},{"id":"https://openalex.org/keywords/epipolar-geometry","display_name":"Epipolar geometry","score":0.47694316506385803},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4470948576927185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40774673223495483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.2632853388786316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2632152736186981},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.2602616548538208},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15522748231887817},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.09169867634773254},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.09118828177452087}],"concepts":[{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.6615477800369263},{"id":"https://openalex.org/C103364767","wikidata":"https://www.wikidata.org/wiki/Q1807562","display_name":"Interaural time difference","level":3,"score":0.6477392315864563},{"id":"https://openalex.org/C151382886","wikidata":"https://www.wikidata.org/wiki/Q1432854","display_name":"Head-related transfer function","level":3,"score":0.5990477204322815},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.5980228781700134},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.5776782631874084},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5629047155380249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5607936978340149},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5252068638801575},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.4947945475578308},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.4865254759788513},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4770345389842987},{"id":"https://openalex.org/C23379248","wikidata":"https://www.wikidata.org/wiki/Q200904","display_name":"Epipolar geometry","level":3,"score":0.47694316506385803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4470948576927185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40774673223495483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2632853388786316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2632152736186981},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.2602616548538208},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15522748231887817},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.09169867634773254},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.09118828177452087},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2003.1248800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2003.1248800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.4276","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.4276","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/~okuno/paper/IROS03-Nakadai.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":23,"referenced_works":["https://openalex.org/W43463692","https://openalex.org/W70999531","https://openalex.org/W1561130515","https://openalex.org/W1573761753","https://openalex.org/W1603215226","https://openalex.org/W1973746598","https://openalex.org/W1982466904","https://openalex.org/W2013020033","https://openalex.org/W2028310195","https://openalex.org/W2117079761","https://openalex.org/W2118692040","https://openalex.org/W2121065047","https://openalex.org/W2147871138","https://openalex.org/W2315182781","https://openalex.org/W2406470551","https://openalex.org/W2416573875","https://openalex.org/W6601839116","https://openalex.org/W6634337840","https://openalex.org/W6653477362","https://openalex.org/W6657697445","https://openalex.org/W6678139903","https://openalex.org/W6681741679","https://openalex.org/W6813586354"],"related_works":["https://openalex.org/W1606499391","https://openalex.org/W4221151007","https://openalex.org/W2342093575","https://openalex.org/W2317500761","https://openalex.org/W2127418452","https://openalex.org/W3133550200","https://openalex.org/W2329131175","https://openalex.org/W2802393278","https://openalex.org/W2267719592","https://openalex.org/W1578934236"],"abstract_inverted_index":{"Robot":[0],"audition":[1],"by":[2,63],"its":[3],"own":[4],"ears":[5],"(microphones)":[6],"is":[7,18,61,77,111,181,207],"essential":[8],"for":[9,84,114,194,209],"natural":[10],"human-robot":[11],"communication":[12],"and":[13,39,50,57,66,117,138,144,168,199,211,218],"interface.":[14],"Since":[15],"a":[16,24,79,106,133,147,160],"microphone":[17],"embedded":[19],"in":[20,35,87,179],"the":[21,26,45,59,95,128,176,187],"head":[22,193],"of":[23,72,97,124,136,165,170,189,197,213],"robot,":[25],"head-related":[27],"transfer":[28],"function":[29,135],"(HRTF)":[30],"plays":[31],"an":[32,88],"important":[33],"role":[34],"sound":[36,74,214],"source":[37,75],"localization":[38,76,210],"extraction.":[40],"Usually,":[41],"from":[42,219],"binaural":[43],"input,":[44],"interaural":[46,51],"phase":[47],"difference":[48,53],"(IPD)":[49],"intensity":[52],"(IID)":[54],"are":[55],"calculated,":[56],"then":[58],"direction":[60],"determined":[62],"using":[64],"IPD":[65,137,169],"IID":[67,139,164,198],"with":[68,121,142],"HRTF.":[69],"The":[70,201],"problem":[71],"HRTF-based":[73],"that":[78,205],"HRTF":[80,100,143],"should":[81,101],"be":[82,102],"measured":[83],"each":[85],"robot":[86],"anechoic":[89],"chamber,":[90],"because":[91,109],"it":[92,110,206],"depends":[93],"on":[94],"shape":[96],"robot's":[98,192],"head;":[99],"interpolated":[103],"to":[104,140,163,183],"manipulate":[105],"moving":[107],"talker,":[108],"available":[112],"only":[113],"discrete":[115],"azimuth":[116],"elevation.":[118],"To":[119],"cope":[120],"these":[122],"problems":[123],"HRTF,":[125],"we":[126],"proposed":[127],"auditory":[129,153],"epipolar":[130,154],"geometry":[131],"as":[132],"continuous":[134],"dispense":[141],"have":[145],"developed":[146],"real-time":[148],"multiple-talker":[149],"tracking":[150],"system.":[151],"This":[152],"geometry,":[155],"however,":[156],"does":[157],"not":[158],"give":[159],"good":[161],"approximation":[162,196],"all":[166],"range":[167],"peripheral":[171],"areas.":[172],"In":[173],"this":[174],"paper,":[175],"scattering":[177],"theory":[178],"physics":[180],"employed":[182],"take":[184],"into":[185],"consideration":[186],"diffraction":[188],"sounds":[190],"around":[191],"better":[195],"IPD.":[200],"resulting":[202],"system":[203],"shows":[204],"efficient":[208],"extraction":[212],"at":[215],"higher":[216],"frequency":[217],"side":[220],"directions.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
