{"id":"https://openalex.org/W2051878366","doi":"https://doi.org/10.1109/humanoids.2012.6651546","title":"Active audio-visual integration for Voice Activity Detection based on a Causal Bayesian Network","display_name":"Active audio-visual integration for Voice Activity Detection based on a Causal Bayesian Network","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2051878366","doi":"https://doi.org/10.1109/humanoids.2012.6651546","mag":"2051878366"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2012.6651546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2012.6651546","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/A5103835321","display_name":"Takami Yoshida","orcid":null},"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":"Takami Yoshida","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan","Grad. Sch. of Inf. Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Grad. Sch. of Inf. Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"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":"Kazuhiro Nakadai","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan","Grad. Sch. of Inf. Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Grad. Sch. of Inf. Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.9762,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75267473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"5","issue":null,"first_page":"370","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7583881616592407},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.7100272178649902},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6674680113792419},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5683119297027588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5591155886650085},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.49913787841796875},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.498870849609375},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.4491977393627167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3861615061759949},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.33625102043151855},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2729206681251526},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22595974802970886},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1564154326915741},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1542469561100006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583881616592407},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.7100272178649902},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6674680113792419},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5683119297027588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5591155886650085},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.49913787841796875},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.498870849609375},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.4491977393627167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3861615061759949},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.33625102043151855},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2729206681251526},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22595974802970886},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1564154326915741},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1542469561100006}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/humanoids.2012.6651546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2012.6651546","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:t2r2.star.titech.ac.jp:50503957","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100812287","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322704","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W115769679","https://openalex.org/W574305787","https://openalex.org/W1964481889","https://openalex.org/W2017835752","https://openalex.org/W2069432516","https://openalex.org/W2082120918","https://openalex.org/W2097858476","https://openalex.org/W2100191526","https://openalex.org/W2113469515","https://openalex.org/W2116147320","https://openalex.org/W2116497041","https://openalex.org/W2121065047","https://openalex.org/W2130992468","https://openalex.org/W4255209084","https://openalex.org/W6616528352","https://openalex.org/W6675288942","https://openalex.org/W6678139903","https://openalex.org/W6679443918"],"related_works":["https://openalex.org/W4402262758","https://openalex.org/W2098934641","https://openalex.org/W3096250625","https://openalex.org/W3011716530","https://openalex.org/W3135871143","https://openalex.org/W4308222513","https://openalex.org/W4382560817","https://openalex.org/W2347715673","https://openalex.org/W2405875744","https://openalex.org/W2020966186"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"an":[3],"active":[4,17,93,134],"audio-visual":[5],"integration":[6,59],"framework":[7,60,100,156],"which":[8,61,81,123],"integrates":[9,62],"audio":[10],"and":[11,65,119,129,177,201,213],"visual":[12,64],"information":[13,67,102,111],"with":[14,45,168],"a":[15,39,69,76,98,117,120,149,158],"robot's":[16,40],"motion":[18,66,135],"for":[19,28,101,136],"noise-robust":[20,52],"Voice":[21],"Activity":[22],"Detection":[23],"(VAD).":[24],"VAD":[25,89,125,192],"is":[26,42,75,82,97,166],"crucial":[27],"noise":[29,47,121],"robust":[30],"Automatic":[31],"Speech":[32],"Recognition":[33],"(ASR)":[34],"because":[35],"speech":[36],"captured":[37],"by":[38,92],"microphones":[41],"usually":[43],"contaminated":[44],"other":[46],"sources.":[48],"To":[49],"realize":[50],"such":[51,112],"VAD,":[53],"we":[54,104],"propose":[55],"Active":[56],"Audio-Visual":[57],"(AAV)":[58],"auditory,":[63],"using":[68,142,185],"Causal":[70],"Bayesian":[71,79],"Network":[72],"(CBN).":[73],"CBN":[74,96,130],"subclass":[77],"of":[78,110,116,139,171,194,207],"networks,":[80],"able":[83],"to":[84,127],"estimate":[85],"the":[86,114,132,140,154,186,191,195,208],"effect":[87],"on":[88,153,157],"performance":[90,126,193],"caused":[91],"motions.":[94],"Since":[95],"general":[99],"integration,":[103],"can":[105],"naturally":[106],"introduce":[107],"various":[108],"types":[109,170],"as":[113],"location":[115],"speaker":[118],"source":[122],"affect":[124],"CBN,":[128],"selects":[131],"optimal":[133],"better":[137],"perception":[138],"robot":[141,160],"\u201cintervention\u201d":[143],"mechanism":[144],"in":[145],"CBN.":[146],"We":[147],"implemented":[148],"prototype":[150,187],"system":[151,188],"based":[152],"proposed":[155,164,196],"humanoid":[159],"called":[161],"Hearbo.":[162],"The":[163],"AAV-VAD":[165],"compared":[167],"three":[169],"AV-VAD;":[172],"simple":[173,209],"AAV-VAD,":[174,176],"multi-regression-based":[175,211],"stationary":[178,214],"(not":[179],"active)":[180],"AV-VAD.":[181],"A":[182],"preliminary":[183],"experiment":[184],"showed":[189],"that":[190,206],"AV-VAD":[197],"was":[198],"14.4,":[199],"26.0,":[200],"30.3":[202],"points":[203],"higher":[204],"than":[205],"active,":[210,212],"AV-VAD,":[215],"respectively.":[216]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}