{"id":"https://openalex.org/W1964481889","doi":"https://doi.org/10.1109/iros.2010.5651205","title":"Two-layered audio-visual speech recognition for robots in noisy environments","display_name":"Two-layered audio-visual speech recognition for robots in noisy environments","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W1964481889","doi":"https://doi.org/10.1109/iros.2010.5651205","mag":"1964481889"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2010.5651205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2010.5651205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5041106588","display_name":"Toshiyuki Yoshida","orcid":"https://orcid.org/0000-0002-2468-5388"},"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":"T 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":"K 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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H G Okuno","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"988","last_page":"993"},"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":0.9979000091552734,"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":0.9977999925613403,"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/robustness","display_name":"Robustness (evolution)","score":0.798848032951355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7734079360961914},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7001741528511047},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5041455030441284},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.49820709228515625},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4926925301551819},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.48412665724754333},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4306629002094269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4139775037765503},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3342474699020386},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.27600663900375366},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08495146036148071}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.798848032951355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734079360961914},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7001741528511047},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5041455030441284},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.49820709228515625},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4926925301551819},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.48412665724754333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4306629002094269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4139775037765503},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3342474699020386},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27600663900375366},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08495146036148071},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iros.2010.5651205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2010.5651205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.8749","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.8749","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/IROS2010-Yoshida.pdf","raw_type":"text"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50504110","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100812440","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W115540051","https://openalex.org/W115769679","https://openalex.org/W1604074770","https://openalex.org/W1904457459","https://openalex.org/W1972486275","https://openalex.org/W1984867864","https://openalex.org/W2049737414","https://openalex.org/W2100191526","https://openalex.org/W2100820878","https://openalex.org/W2102863932","https://openalex.org/W2116497041","https://openalex.org/W2116529913","https://openalex.org/W2121065047","https://openalex.org/W2150444217","https://openalex.org/W2150946027","https://openalex.org/W2171244697","https://openalex.org/W2542469892","https://openalex.org/W3103998211","https://openalex.org/W3140321225","https://openalex.org/W3146101452","https://openalex.org/W4255209084","https://openalex.org/W6604677257","https://openalex.org/W6646525595","https://openalex.org/W6677131165","https://openalex.org/W6678139903","https://openalex.org/W6685272952","https://openalex.org/W6793103562"],"related_works":["https://openalex.org/W2103866630","https://openalex.org/W2132423630","https://openalex.org/W2170660557","https://openalex.org/W2145189396","https://openalex.org/W1576996184","https://openalex.org/W2134867751","https://openalex.org/W2154353037","https://openalex.org/W2146531872","https://openalex.org/W2572023240","https://openalex.org/W2790326622","https://openalex.org/W191108438","https://openalex.org/W2150946027","https://openalex.org/W2098265087","https://openalex.org/W1502314398","https://openalex.org/W2088992427","https://openalex.org/W37288447","https://openalex.org/W141701120","https://openalex.org/W2134749286","https://openalex.org/W1628467322","https://openalex.org/W2145334935"],"abstract_inverted_index":{"Audio-visual":[0],"(AV)":[1],"integration":[2,39],"is":[3,155],"one":[4],"of":[5,145,152,167],"the":[6,50,86,133,143,150,153,158,165],"key":[7],"ideas":[8],"to":[9,23,106],"improve":[10,24],"perception":[11],"in":[12,85],"noisy":[13],"real-world":[14],"environments.":[15],"This":[16],"paper":[17],"describes":[18],"automatic":[19],"speech":[20],"recognition":[21],"(ASR)":[22],"human-robot":[25],"interaction":[26],"based":[27],"on":[28],"AV":[29,38,168],"integration.":[30,169],"We":[31,131],"developed":[32],"AV-integrated":[33],"ASR,":[34],"which":[35],"has":[36,52],"two":[37],"layers,":[40],"that":[41,74,142],"is,":[42],"voice":[43],"activity":[44],"detection":[45],"(VAD)":[46],"and":[47,57,71,89,96,124,157],"ASR.":[48],"However,":[49],"system":[51],"three":[53],"difficulties:":[54],"1)":[55],"VAD":[56,70,117,146],"ASR":[58,72,120],"have":[59],"been":[60],"separately":[61],"studied":[62],"although":[63,80],"these":[64,111],"processes":[65],"are":[66,78],"mutually":[67],"dependent,":[68],"2)":[69],"assumed":[73],"high":[75],"resolution":[76,151],"images":[77,154],"available":[79],"this":[81],"assumption":[82],"never":[83],"holds":[84],"real":[87],"world,":[88],"3)":[90],"an":[91],"optimal":[92,127],"weight":[93,128,163],"between":[94],"audio":[95],"visual":[97],"stream":[98,162],"was":[99],"fixed":[100],"while":[101],"their":[102],"reliabilities":[103],"change":[104],"according":[105],"environmental":[107],"changes.":[108],"To":[109],"solve":[110],"problems,":[112],"we":[113],"propose":[114],"a":[115,125],"new":[116],"algorithm":[118,134],"taking":[119],"characteristics":[121],"into":[122],"account,":[123],"linear-regression-based":[126],"estimation":[129],"method.":[130],"evaluate":[132],"for":[135],"auditory-and/or":[136],"visually-contaminated":[137],"data.":[138],"Preliminary":[139],"results":[140],"show":[141],"robustness":[144],"improved":[147],"even":[148],"when":[149],"low,":[156],"AVSR":[159],"using":[160],"estimated":[161],"shows":[164],"effectiveness":[166]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
