{"id":"https://openalex.org/W2100191526","doi":"https://doi.org/10.1109/ichr.2009.5379586","title":"Automatic speech recognition improved by two-layered audio-visual integration for robot audition","display_name":"Automatic speech recognition improved by two-layered audio-visual integration for robot audition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2100191526","doi":"https://doi.org/10.1109/ichr.2009.5379586","mag":"2100191526"},"language":"en","primary_location":{"id":"doi:10.1109/ichr.2009.5379586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichr.2009.5379586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 9th IEEE-RAS International Conference on Humanoid Robots","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":["Mechanical and Environmental Informatics, Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical and Environmental Informatics, Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","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"]},{"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":"Kazuhiro Nakadai","raw_affiliation_strings":["Honda Research Institute Japan Company Limited, Wako, Saitama, Japan","Mechanical and Environmental Informatics, Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Wako, Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Mechanical and Environmental Informatics, Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"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":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"604","last_page":"609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9983999729156494,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/computer-science","display_name":"Computer science","score":0.7945143580436707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7512359619140625},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5744108557701111},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41205042600631714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38790974020957947},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3634474277496338},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.20245641469955444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945143580436707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7512359619140625},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5744108557701111},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41205042600631714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38790974020957947},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3634474277496338},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20245641469955444}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ichr.2009.5379586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichr.2009.5379586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 9th IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.700","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.700","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/members/okuno/Public/Humanoids09-Yoshida.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W115540051","https://openalex.org/W1604074770","https://openalex.org/W1904457459","https://openalex.org/W2026257980","https://openalex.org/W2049737414","https://openalex.org/W2078639319","https://openalex.org/W2084533374","https://openalex.org/W2100820878","https://openalex.org/W2116497041","https://openalex.org/W2121065047","https://openalex.org/W2147347395","https://openalex.org/W2150444217","https://openalex.org/W2150946027","https://openalex.org/W2169896329","https://openalex.org/W2542469892","https://openalex.org/W3103998211","https://openalex.org/W3146101452","https://openalex.org/W6604677257","https://openalex.org/W6678139903","https://openalex.org/W6684878041","https://openalex.org/W6793103562"],"related_works":["https://openalex.org/W2893763841","https://openalex.org/W2312116756","https://openalex.org/W2778699561","https://openalex.org/W4304891817","https://openalex.org/W4235663262","https://openalex.org/W2132217089","https://openalex.org/W3026006730","https://openalex.org/W4255209084","https://openalex.org/W4280492125","https://openalex.org/W2547701628"],"abstract_inverted_index":{"The":[0,57,90,111,149],"robustness":[1,191],"and":[2,38,52,100,177,188],"high":[3],"performance":[4,82],"of":[5,46,83,88,97,102,113,126,180],"ASR":[6,153,181],"is":[7,79,116,129,154],"required":[8],"for":[9],"robot":[10,160],"audition,":[11],"because":[12,80],"people":[13],"usually":[14],"speak":[15],"to":[16,19,27,69],"each":[17],"other":[18],"communicate.":[20],"This":[21,78,136],"paper":[22],"presents":[23],"two-layered":[24],"audio-visual":[25],"integration":[26,139],"make":[28],"automatic":[29],"speech":[30],"recognition":[31],"(ASR)":[32],"more":[33,117,130],"robust":[34],"against":[35,192],"speaker's":[36,75],"distance":[37],"interfering":[39],"talkers":[40],"or":[41,74,147],"environmental":[42],"noises.":[43],"It":[44],"consists":[45],"Audio-Visual":[47,53],"Voice":[48],"Activity":[49],"Detection":[50],"(AV-VAD)":[51],"Speech":[54],"Recognition":[55],"(AVSR).":[56],"AV-VAD":[58],"layer":[59,92,138],"integrates":[60,93],"several":[61,193],"AV":[62,151],"features":[63,99,104,115,128],"based":[64],"on":[65,156],"a":[66,107,120,133],"Bayesian":[67],"network":[68],"robustly":[70],"detect":[71],"voice":[72],"activity,":[73],"utterance":[76],"duration.":[77],"the":[81,94],"VAD":[84],"strongly":[85],"affects":[86],"that":[87,101,125,172],"ASR.":[89],"AVSR":[91,137],"reliability":[95,112],"estimation":[96],"acoustic":[98,122],"visual":[103,127],"by":[105],"using":[106],"missing-feature":[108],"theory":[109],"method.":[110],"audio":[114],"weighted":[118,131],"in":[119,132,145],"clean":[121],"environment,":[123],"while":[124],"noisy":[134],"environment.":[135],"can":[140],"cope":[141],"with":[142,163],"dynamically-changing":[143],"environments":[144],"acoustics":[146],"vision.":[148],"proposed":[150],"integrated":[152],"implemented":[155],"HARK,":[157],"our":[158,173],"open-sourced":[159],"audition":[161],"software,":[162],"an":[164],"8":[165],"ch":[166],"microphone":[167,184],"array.":[168],"Empirical":[169],"results":[170,182],"show":[171],"system":[174],"improves":[175,190],"9.9":[176],"16.7":[178],"points":[179],"with/without":[183],"array":[185],"processing,":[186],"respectively,":[187],"also":[189],"auditory/visual":[194],"noise":[195],"conditions.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}