{"id":"https://openalex.org/W2064543148","doi":"https://doi.org/10.1109/humanoids.2012.6651506","title":"Sound-event recognition with a companion humanoid","display_name":"Sound-event recognition with a companion humanoid","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2064543148","doi":"https://doi.org/10.1109/humanoids.2012.6651506","mag":"2064543148"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2012.6651506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2012.6651506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)","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/A5042687852","display_name":"Maxime Janvier","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":"Maxime Janvier","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes","PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"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","PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090757640","display_name":"Laurent Girinz","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"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Girinz","raw_affiliation_strings":["GIPSA-Lab, Saint Martin d'Heres, Auvergne-Rh\u00c3\u00b4ne-Alpes, FR","PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","GIPSA-MAGIC - GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-Lab, Saint Martin d'Heres, Auvergne-Rh\u00c3\u00b4ne-Alpes, FR","institution_ids":["https://openalex.org/I4210124956"]},{"raw_affiliation_string":"PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"GIPSA-MAGIC - GIPSA -  Machines parlantes, Gestes oro-faciaux, Interaction Face-\u00e0-face, Communication augment\u00e9e (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"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","PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"64","issue":null,"first_page":"104","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991999864578247,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9778000116348267,"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/computer-science","display_name":"Computer science","score":0.722424328327179},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.6442635655403137},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5758724212646484},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5650348663330078},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.546682596206665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5238199830055237},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5153438448905945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49054473638534546},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4733172655105591},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4671579897403717},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43518972396850586},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4270305633544922},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.42663419246673584},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36991947889328003},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1386837363243103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1024884283542633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722424328327179},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6442635655403137},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5758724212646484},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5650348663330078},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.546682596206665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5238199830055237},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5153438448905945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49054473638534546},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4733172655105591},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4671579897403717},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43518972396850586},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4270305633544922},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.42663419246673584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36991947889328003},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1386837363243103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1024884283542633},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/humanoids.2012.6651506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2012.6651506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00768767v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00768767","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Humanoids 2012 - IEEE International Conference on Humanoid Robotics, Nov 2012, Osaka, Japan. pp.104-111, &#x27E8;10.1109/HUMANOIDS.2012.6651506&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W129223715","https://openalex.org/W168991039","https://openalex.org/W837720621","https://openalex.org/W1604034532","https://openalex.org/W1634005169","https://openalex.org/W1965980674","https://openalex.org/W1966273763","https://openalex.org/W1988030566","https://openalex.org/W1990938546","https://openalex.org/W2032362923","https://openalex.org/W2043870814","https://openalex.org/W2046972719","https://openalex.org/W2107456423","https://openalex.org/W2109788549","https://openalex.org/W2113944432","https://openalex.org/W2124509324","https://openalex.org/W2126693545","https://openalex.org/W2135131618","https://openalex.org/W2156038773","https://openalex.org/W2157363431","https://openalex.org/W2172256532","https://openalex.org/W2186582651","https://openalex.org/W2972559627","https://openalex.org/W4285719527","https://openalex.org/W6605184672","https://openalex.org/W6606898681","https://openalex.org/W6676413359","https://openalex.org/W6677331533","https://openalex.org/W6768269516"],"related_works":["https://openalex.org/W2745063183","https://openalex.org/W4256317079","https://openalex.org/W2129850190","https://openalex.org/W2543019745","https://openalex.org/W2295425790","https://openalex.org/W4389009354","https://openalex.org/W2088677124","https://openalex.org/W1974803039","https://openalex.org/W1991876829","https://openalex.org/W2143454724"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"address":[4],"the":[5,23,27,44,63,102,135],"problem":[6,66,71],"of":[7,47,77,108,120],"recognizing":[8],"everyday":[9],"sound":[10,64],"events":[11],"in":[12,22,128,161,170],"indoor":[13],"environments":[14],"with":[15,116,124,142],"a":[16,49,53,68,75,82,89,106,117,125,129,143,162],"consumer":[17,163],"robot.":[18],"Sounds":[19],"are":[20],"represented":[21],"spectro-temporal":[24],"domain":[25],"using":[26,105],"stabilized":[28],"auditory":[29],"image":[30],"(SAI)":[31],"representation.":[32],"The":[33,112],"SAI":[34],"is":[35,114],"well":[36],"suited":[37],"for":[38],"representing":[39],"pulse-resonance":[40],"sounds":[41,97,104],"and":[42,72,98,100,152],"has":[43],"interesting":[45],"property":[46],"mapping":[48],"time-varying":[50],"signal":[51],"into":[52,67,94],"fixed-dimension":[54],"feature":[55],"vector":[56],"space.":[57],"This":[58],"allows":[59],"us":[60],"to":[61,73,168],"map":[62],"recognition":[65,140],"supervised":[69],"classification":[70],"adopt":[74],"variety":[76],"classifications":[78],"schemes.":[79],"We":[80],"present":[81],"complete":[83],"system":[84],"that":[85,134],"takes":[86],"as":[87],"input":[88],"continuous":[90],"signal,":[91],"splits":[92],"it":[93],"significant":[95],"isolated":[96,103],"noise,":[99],"classifies":[101],"catalogue":[107],"learned":[109],"sound-event":[110],"classes.":[111],"method":[113,137],"validated":[115],"large":[118],"set":[119],"audio":[121],"data":[122],"recorded":[123],"humanoid":[126],"robot":[127,164],"house.":[130],"Extended":[131],"experiments":[132],"show":[133,165],"proposed":[136],"achieves":[138],"state-of-the-art":[139],"scores":[141],"twelve-class":[144],"problem,":[145],"while":[146],"requiring":[147],"extremely":[148],"limited":[149],"memory":[150],"space":[151],"moderate":[153],"computing":[154],"power.":[155],"A":[156],"first":[157],"real-time":[158],"embedded":[159],"implementation":[160],"its":[166],"ability":[167],"work":[169],"real":[171],"conditions.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
