{"id":"https://openalex.org/W2159801939","doi":"https://doi.org/10.1177/0278364914548050","title":"Vision-guided robot hearing","display_name":"Vision-guided robot hearing","publication_year":2014,"publication_date":"2014-10-27","ids":{"openalex":"https://openalex.org/W2159801939","doi":"https://doi.org/10.1177/0278364914548050","mag":"2159801939"},"language":"en","primary_location":{"id":"doi:10.1177/0278364914548050","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364914548050","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1311.2460","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xavier Alameda-Pineda","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"last","author":{"id":null,"display_name":"Radu Horaud","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2704,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96690108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"34","issue":"4-5","first_page":"437","last_page":"456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9538999795913696,"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":0.9538999795913696,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.01679999940097332,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/robot","display_name":"Robot","score":0.667900025844574},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6523000001907349},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.6333000063896179},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48159998655319214},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4075999855995178},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.3939000070095062},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.39239999651908875},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.36719998717308044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691100001335144},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.667900025844574},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6523000001907349},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6333000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5577999949455261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49410000443458557},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4036000072956085},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3939000070095062},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3804999887943268},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.36719998717308044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C2780801066","wikidata":"https://www.wikidata.org/wiki/Q323808","display_name":"Hearing aid","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.30570000410079956},{"id":"https://openalex.org/C94487597","wikidata":"https://www.wikidata.org/wiki/Q11101","display_name":"Sensory system","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C3020799230","wikidata":"https://www.wikidata.org/wiki/Q160289","display_name":"Auditory perception","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2700999975204468},{"id":"https://openalex.org/C126057942","wikidata":"https://www.wikidata.org/wiki/Q35158","display_name":"Stereoscopy","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.25769999623298645}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/0278364914548050","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364914548050","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1311.2460","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1311.2460","pdf_url":"https://arxiv.org/pdf/1311.2460","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-00990766v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00990766","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ijr.sagepub.com/content/34/4-5/437","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1311.2460","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1311.2460","pdf_url":"https://arxiv.org/pdf/1311.2460","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1965342088","https://openalex.org/W1971791733","https://openalex.org/W1975143133","https://openalex.org/W1975350514","https://openalex.org/W1980370676","https://openalex.org/W2004909598","https://openalex.org/W2010219725","https://openalex.org/W2011699475","https://openalex.org/W2017835752","https://openalex.org/W2019743084","https://openalex.org/W2026257980","https://openalex.org/W2033819227","https://openalex.org/W2049633694","https://openalex.org/W2051224630","https://openalex.org/W2069885239","https://openalex.org/W2073227393","https://openalex.org/W2082198998","https://openalex.org/W2085331248","https://openalex.org/W2096301647","https://openalex.org/W2097089247","https://openalex.org/W2098469993","https://openalex.org/W2099151709","https://openalex.org/W2099277959","https://openalex.org/W2103032457","https://openalex.org/W2105582566","https://openalex.org/W2109124605","https://openalex.org/W2111308925","https://openalex.org/W2111479516","https://openalex.org/W2119090229","https://openalex.org/W2123066336","https://openalex.org/W2132417028","https://openalex.org/W2138414774","https://openalex.org/W2140647972","https://openalex.org/W2140850178","https://openalex.org/W2141939040","https://openalex.org/W2143169494","https://openalex.org/W2154496665","https://openalex.org/W2154943827","https://openalex.org/W2158305599","https://openalex.org/W2160555827","https://openalex.org/W2163141813","https://openalex.org/W2168175751","https://openalex.org/W2169570466","https://openalex.org/W2169770604","https://openalex.org/W4313177291"],"related_works":[],"abstract_inverted_index":{"Natural":[0],"human\u2013robot":[1],"interaction":[2],"(HRI)":[3],"in":[4,31,152,168],"complex":[5],"and":[6,24,58,67,104,111,162,177,206,219,227],"unpredictable":[7],"environments":[8],"is":[9],"important":[10],"with":[11,192,201],"many":[12],"potential":[13],"applications.":[14],"While":[15],"vision-based":[16],"HRI":[17,26],"has":[18],"been":[19],"thoroughly":[20],"investigated,":[21],"robot":[22,44,187],"hearing":[23,228],"audio-based":[25],"are":[27,38,51,108,166,220],"emerging":[28],"research":[29],"topics":[30],"robotics.":[32],"In":[33,62,93],"typical":[34],"real-world":[35],"scenarios,":[36],"humans":[37],"at":[39],"some":[40],"distance":[41],"from":[42],"the":[43,47,65,82,98,138,141,146,149,163,182,185,211,217],"and,":[45],"hence,":[46],"sensory":[48],"(microphone)":[49],"data":[50,128,199,208],"strongly":[52],"impaired":[53],"by":[54],"background":[55],"noise,":[56],"reverberations":[57],"competing":[59],"auditory":[60,132,150],"sources.":[61],"this":[63,94],"context,":[64],"detection":[66],"localization":[68],"of":[69,100,137,148,184],"speakers":[70],"plays":[71],"a":[72,115,130,173],"key":[73],"role":[74],"that":[75,107],"enables":[76,140],"several":[77],"tasks,":[78],"such":[79],"as":[80],"improving":[81],"signal-to-noise":[83],"ratio":[84],"for":[85,233],"speech":[86],"recognition,":[87,89],"speaker":[88,90],"tracking,":[91],"etc.":[92],"paper":[95],"we":[96],"address":[97],"problem":[99],"how":[101,225],"to":[102,124,144,154,223],"detect":[103],"localize":[105],"people":[106],"both":[109],"seen":[110],"heard.":[112],"We":[113,189],"introduce":[114],"hybrid":[116],"deterministic/probabilistic":[117],"model.":[118],"The":[119,134,159,214],"deterministic":[120],"component":[121,136],"allows":[122],"us":[123],"map":[125],"3D":[126],"visual":[127,142],"onto":[129],"1D":[131],"space.":[133],"probabilistic":[135],"model":[139,161],"features":[143,151],"guide":[145],"grouping":[147],"order":[153],"form":[155],"audiovisual":[156,203],"(AV)":[157],"objects.":[158],"proposed":[160],"associated":[164],"algorithms":[165],"implemented":[167],"real-time":[169],"(17":[170],"FPS)":[171],"using":[172,210],"stereoscopic":[174],"camera":[175],"pair":[176],"two":[178],"microphones":[179],"embedded":[180],"into":[181],"head":[183],"humanoid":[186],"NAO.":[188],"perform":[190],"experiments":[191],"(i)":[193],"synthetic":[194],"data,":[195],"(ii)":[196],"publicly":[197],"available":[198],"gathered":[200],"an":[202,221],"robotic":[204],"head,":[205],"(iii)":[207],"acquired":[209],"NAO":[212],"robot.":[213],"results":[215],"validate":[216],"approach":[218],"encouragement":[222],"investigate":[224],"vision":[226],"could":[229],"be":[230],"further":[231],"combined":[232],"robust":[234],"HRI.":[235]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":17},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2016-06-24T00:00:00"}
