{"id":"https://openalex.org/W2004909598","doi":"https://doi.org/10.1109/humanoids.2012.6651509","title":"Online multimodal speaker detection for humanoid robots","display_name":"Online multimodal speaker detection for humanoid robots","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2004909598","doi":"https://doi.org/10.1109/humanoids.2012.6651509","mag":"2004909598"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2012.6651509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2012.6651509","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/A5063541182","display_name":"Jordi S\u00e0nchez-Riera","orcid":"https://orcid.org/0000-0002-4803-5742"},"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":"Jordi Sanchez-Riera","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Monbonnot, France","INRIA Grenoble Rhone-Alpes, Monbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"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, Monbonnot, France","INRIA Grenoble Rhone-Alpes, Monbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045260982","display_name":"Johannes Wienke","orcid":"https://orcid.org/0000-0003-4517-5368"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Wienke","raw_affiliation_strings":["Universitat Bielefeld, Bielefeld, Nordrhein-Westfalen, DE","CoR-Lab., Bielefeld Univ., Bielefeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Bielefeld, Bielefeld, Nordrhein-Westfalen, DE","institution_ids":["https://openalex.org/I20121455"]},{"raw_affiliation_string":"CoR-Lab., Bielefeld Univ., Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000981106","display_name":"Antoine Deleforge","orcid":"https://orcid.org/0000-0003-0339-7472"},"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":"Antoine Deleforge","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Monbonnot, France","INRIA Grenoble Rhone-Alpes, Monbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009083816","display_name":"Soraya Arias","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":"Soraya Arias","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Monbonnot, France","INRIA Grenoble Rhone-Alpes, Monbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018876350","display_name":"Jan \u010cech","orcid":"https://orcid.org/0000-0002-2181-5917"},"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":"Jan Cech","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, 655, Avenue de l'Europe, 38334 Monbonnot, France","INRIA Grenoble Rhone-Alpes, Monbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, 655, Avenue de l'Europe, 38334 Monbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067007309","display_name":"Sebastian Wrede","orcid":"https://orcid.org/0000-0003-0029-8188"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Wrede","raw_affiliation_strings":["Universitat Bielefeld, Bielefeld, Nordrhein-Westfalen, DE","CoR-Lab., Bielefeld Univ., Bielefeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Bielefeld, Bielefeld, Nordrhein-Westfalen, DE","institution_ids":["https://openalex.org/I20121455"]},{"raw_affiliation_string":"CoR-Lab., Bielefeld Univ., Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]},{"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, Monbonnot, France","INRIA Grenoble Rhone-Alpes, Monbonnot, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, Monbonnot, France","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9922999739646912,"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"}},{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8057523965835571},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7753880023956299},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5998709201812744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.529694139957428},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5192630290985107},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5140977501869202},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4937649667263031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4299311339855194},{"id":"https://openalex.org/keywords/middleware","display_name":"Middleware (distributed applications)","score":0.41575732827186584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057523965835571},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7753880023956299},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5998709201812744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.529694139957428},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5192630290985107},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5140977501869202},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4937649667263031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4299311339855194},{"id":"https://openalex.org/C169468491","wikidata":"https://www.wikidata.org/wiki/Q146923","display_name":"Middleware (distributed applications)","level":2,"score":0.41575732827186584},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/humanoids.2012.6651509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2012.6651509","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:CiteSeerX.psu:10.1.1.348.3198","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.3198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://perception.inrialpes.fr/Publications/2012/SAWDACWH12/Sanchez-Humanoids2012.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.698.3061","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.698.3061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cmp.felk.cvut.cz/ftp/articles/cech/Sanchez-Humanoids-2012.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00768764v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00768764","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.126-133, ⟨10.1109/HUMANOIDS.2012.6651509⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pub.librecat.org:2529247","is_oa":false,"landing_page_url":"https://pub.uni-bielefeld.de/record/2529247","pdf_url":null,"source":{"id":"https://openalex.org/S4306401671","display_name":"PUB \u2013 Publications at Bielefeld University (Bielefeld University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20121455","host_organization_name":"Bielefeld University","host_organization_lineage":["https://openalex.org/I20121455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sanchez-Riera J, Alameda-Pineda X, Wienke J, et al. Online Multimodal Speaker Detection for Humanoid Robots. In: <em>2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)</em>. IEEE; 2012.","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":19,"referenced_works":["https://openalex.org/W179363399","https://openalex.org/W1869980952","https://openalex.org/W1975143133","https://openalex.org/W2011699475","https://openalex.org/W2019743084","https://openalex.org/W2026257980","https://openalex.org/W2054199123","https://openalex.org/W2089337412","https://openalex.org/W2104804886","https://openalex.org/W2106995601","https://openalex.org/W2112824765","https://openalex.org/W2123066336","https://openalex.org/W2127025755","https://openalex.org/W2131486730","https://openalex.org/W2150470808","https://openalex.org/W2167709189","https://openalex.org/W2287726754","https://openalex.org/W6696018372","https://openalex.org/W7038095890"],"related_works":["https://openalex.org/W2745063183","https://openalex.org/W4256317079","https://openalex.org/W2543019745","https://openalex.org/W2129850190","https://openalex.org/W2295425790","https://openalex.org/W4389009354","https://openalex.org/W2088677124","https://openalex.org/W1974803039","https://openalex.org/W1991876829","https://openalex.org/W1569471492"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"address":[4],"the":[5,18,39,43,50,62,81,89,100,105,118,122],"problem":[6],"of":[7,71,88],"audio-visual":[8,53],"speaker":[9],"detection.":[10],"We":[11],"introduce":[12],"an":[13],"online":[14,83],"system":[15,66,90],"working":[16],"on":[17,69,99],"humanoid":[19],"robot":[20],"NAO.":[21],"The":[22,65],"scene":[23],"is":[24,67,77],"perceived":[25],"with":[26,96,111],"two":[27,30],"cameras":[28],"and":[29,45,48,75,91,104],"microphones.":[31],"A":[32,85],"multimodal":[33],"Gaussian":[34],"mixture":[35],"model":[36],"(mGMM)":[37],"fuses":[38],"information":[40,82],"extracted":[41],"from":[42],"auditory":[44],"visual":[46],"sensors":[47],"detects":[49],"most":[51],"probable":[52],"object,":[54],"e.g.,":[55],"a":[56,59,72],"person":[57],"emitting":[58],"sound,":[60],"in":[61],"3D":[63],"space.":[64],"implemented":[68],"top":[70],"platform-independent":[73],"middleware":[74],"it":[76],"able":[78],"to":[79,124],"process":[80],"(17Hz).":[84],"detailed":[86],"description":[87],"its":[92],"implementation":[93],"are":[94],"provided,":[95],"special":[97],"emphasis":[98],"on-line":[101],"processing":[102],"issues":[103],"proposed":[106,119],"solutions.":[107],"Experimental":[108],"validation,":[109],"performed":[110],"five":[112],"different":[113],"scenarios,":[114],"show":[115],"that":[116,117],"method":[120],"opens":[121],"door":[123],"robust":[125],"human-robot":[126],"interaction":[127],"scenarios.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}