{"id":"https://openalex.org/W2154353037","doi":"https://doi.org/10.1109/ichr.2010.5686828","title":"Robust hands-free Automatic Speech Recognition for human-machine interaction","display_name":"Robust hands-free Automatic Speech Recognition for human-machine interaction","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2154353037","doi":"https://doi.org/10.1109/ichr.2010.5686828","mag":"2154353037"},"language":"en","primary_location":{"id":"doi:10.1109/ichr.2010.5686828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichr.2010.5686828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th 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/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"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":"Randy Gomez","raw_affiliation_strings":["Academic Center of Computing and Media Studies, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center of Computing and Media Studies, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"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":"Tatsuya Kawahara","raw_affiliation_strings":["Academic Center of Computing and Media Studies, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center of Computing and Media Studies, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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/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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HONDA Research Institute Japan Company Limited, Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"138","last_page":"143"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7817609310150146},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7540316581726074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7116855382919312},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6040198802947998},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5701698064804077},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5165561437606812},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4976864159107208},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4675527811050415},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43885189294815063},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.430919885635376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4084147810935974},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3743952512741089},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20150598883628845},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1279717981815338},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10324722528457642}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817609310150146},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7540316581726074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7116855382919312},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6040198802947998},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5701698064804077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5165561437606812},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4976864159107208},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4675527811050415},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43885189294815063},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.430919885635376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4084147810935974},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3743952512741089},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20150598883628845},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1279717981815338},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10324722528457642},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ichr.2010.5686828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichr.2010.5686828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1585936487","https://openalex.org/W1963844140","https://openalex.org/W2009106392","https://openalex.org/W2037740282","https://openalex.org/W2051057783","https://openalex.org/W2053241019","https://openalex.org/W2100969003","https://openalex.org/W2128653836","https://openalex.org/W2132214945","https://openalex.org/W2141418660","https://openalex.org/W2146871184","https://openalex.org/W6680865276"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W3110551121","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2851491717"],"abstract_inverted_index":{"In":[0,65,80],"enclosed":[1],"environments":[2],"where":[3],"robots":[4],"are":[5,89],"deployed,":[6],"the":[7,18,21,47,54,70,84,93,96,102,155,160],"observed":[8],"speech":[9,23,28,38],"signal":[10],"is":[11,33,107],"smeared":[12],"due":[13],"to":[14,42,76,91],"reverberation.":[15,79],"This":[16],"degrades":[17],"performance":[19,162],"of":[20,53,87,95,109],"automatic":[22],"recognition":[24,29,161],"(ASR).":[25],"Thus,":[26],"hands-free":[27],"for":[30,119],"human-machine":[31],"communication":[32],"a":[34],"difficult":[35],"task.":[36],"Most":[37],"enhancement":[39],"techniques":[40],"used":[41],"address":[43],"this":[44,57,66],"problem":[45],"enhance":[46],"contaminated":[48],"waveform":[49,103],"independent":[50],"from":[51,133],"that":[52,154],"ASR.":[55],"However,":[56],"approach":[58],"does":[59],"not":[60,100],"necessarily":[61],"improve":[62,92],"ASR":[63,123],"performance.":[64],"paper,":[67],"we":[68,138],"expand":[69],"conventional":[71,164],"spectral":[72],"subtraction-based":[73],"(SS)":[74],"technique":[75],"deal":[77],"with":[78,115,141,145],"our":[81],"proposed":[82,156],"approach,":[83],"dereverberation":[85],"parameters":[86,113],"SS":[88],"optimized":[90],"likelihood":[94],"acoustic":[97,116],"model":[98,117],"and":[99,147],"just":[101],"signal.":[104],"The":[105],"system":[106],"capable":[108],"adaptively":[110],"fine-tuning":[111],"these":[112],"jointly":[114],"training":[118],"effective":[120],"use":[121],"in":[122],"application.":[124],"We":[125],"have":[126],"experimented":[127],"using":[128],"real":[129],"reverberant":[130,142],"data":[131,143],"collected":[132],"an":[134],"operational":[135],"robot.":[136],"Moreover,":[137],"also":[139],"evaluated":[140],"corrupted":[144],"environmental":[146],"robot":[148],"internal":[149],"noise.":[150],"Experimental":[151],"results":[152],"show":[153],"method":[157],"significantly":[158],"improves":[159],"over":[163],"approach.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}