{"id":"https://openalex.org/W2148719987","doi":"https://doi.org/10.1109/robot.2005.1570323","title":"Enhanced Robot Speech Recognition Based on Microphone Array Source Separation and Missing Feature Theory","display_name":"Enhanced Robot Speech Recognition Based on Microphone Array Source Separation and Missing Feature Theory","publication_year":2006,"publication_date":"2006-01-18","ids":{"openalex":"https://openalex.org/W2148719987","doi":"https://doi.org/10.1109/robot.2005.1570323","mag":"2148719987"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2005.1570323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2005.1570323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},"type":"article","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/A5111946499","display_name":"S. Yamamoto","orcid":null},"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":"S. Yamamoto","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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]},{"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":["CA","JP"],"is_corresponding":false,"raw_author_name":"J.-M. Valin","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan","LABORIUS, Department of Electrical Engineering and Computer Engineering, Universit\u00e9 de Sherbrook, Sherbrooke, QUE, Canada"],"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"]},{"raw_affiliation_string":"LABORIUS, Department of Electrical Engineering and Computer Engineering, Universit\u00e9 de Sherbrook, Sherbrooke, QUE, Canada","institution_ids":["https://openalex.org/I135117807"]}]},{"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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Wako, Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026332327","display_name":"Jean Rouat","orcid":"https://orcid.org/0000-0002-9306-426X"},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J. Rouat","raw_affiliation_strings":["LABORIUS, Department of Electrical Engineering and Computer Engineering, Universit\u00e9 de Sherbrook, Sherbrooke, QUE, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LABORIUS, Department of Electrical Engineering and Computer Engineering, Universit\u00e9 de Sherbrook, Sherbrooke, QUE, Canada","institution_ids":["https://openalex.org/I135117807"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039171860","display_name":"Fran\u00e7ois Michaud","orcid":"https://orcid.org/0000-0002-3639-7770"},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"F. Michaud","raw_affiliation_strings":["LABORIUS, Department of Electrical Engineering and Computer Engineering, Universit\u00e9 de Sherbrook, Sherbrooke, QUE, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LABORIUS, Department of Electrical Engineering and Computer Engineering, Universit\u00e9 de Sherbrook, Sherbrooke, QUE, Canada","institution_ids":["https://openalex.org/I135117807"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"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":"T. Ogata","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"]}]},{"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":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.7605,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.97967805,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"1477","last_page":"1482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7072479128837585},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6846598982810974},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.656966507434845},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6474055647850037},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6026057004928589},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5958483219146729},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5932836532592773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5709694623947144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.551771879196167},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5048897862434387},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.48457372188568115},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.451452374458313},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42947423458099365},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41422784328460693},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4101871848106384},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.25233203172683716},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23595425486564636},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.1685958206653595},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.07189753651618958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072479128837585},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6846598982810974},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.656966507434845},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6474055647850037},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6026057004928589},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5958483219146729},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5932836532592773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5709694623947144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551771879196167},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5048897862434387},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.48457372188568115},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.451452374458313},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42947423458099365},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41422784328460693},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4101871848106384},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.25233203172683716},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23595425486564636},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.1685958206653595},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.07189753651618958},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robot.2005.1570323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2005.1570323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1261381236","display_name":"Study on Computational Auditory Scene Analysis for Humanoids by Active Audition","funder_award_id":"15200015","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3374456554","display_name":"\u5b9f\u6642\u9593\u8996\u8074\u899a\u60c5\u5831\u7d71\u5408\u306b\u3088\u308b\u8907\u6570\u306e\u4eba\u3068\u306e\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30fb\u30a4\u30f3\u30bf\u30e9\u30af\u30b7\u30e7\u30f3\u306e\u7814\u7a76","funder_award_id":"16016251","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W70999531","https://openalex.org/W75153181","https://openalex.org/W76407144","https://openalex.org/W289804034","https://openalex.org/W1888374534","https://openalex.org/W1994407899","https://openalex.org/W1996255164","https://openalex.org/W1998746641","https://openalex.org/W2099655464","https://openalex.org/W2100820878","https://openalex.org/W2115839677","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2126969072","https://openalex.org/W2134910060","https://openalex.org/W2136439176","https://openalex.org/W2139129402","https://openalex.org/W2149429583","https://openalex.org/W2153981835","https://openalex.org/W3103998211","https://openalex.org/W3141118935","https://openalex.org/W3146426688","https://openalex.org/W3147539069","https://openalex.org/W6603045223","https://openalex.org/W6603155865","https://openalex.org/W6610316520"],"related_works":["https://openalex.org/W185063079","https://openalex.org/W3131269989","https://openalex.org/W2035981174","https://openalex.org/W2126980866","https://openalex.org/W2120264472","https://openalex.org/W3080770005","https://openalex.org/W2377537305","https://openalex.org/W4386900535","https://openalex.org/W2271701291","https://openalex.org/W2129566906"],"abstract_inverted_index":{"A":[0,64],"humanoid":[1,52,129],"robot":[2,18,53],"under":[3],"real-world":[4],"environments":[5],"usually":[6],"hears":[7],"mixtures":[8],"of":[9,26,75,90,125,147,171,188],"sounds,":[10],"and":[11,24,59,80,175],"thus":[12],"three":[13,161],"capabilities":[14],"are":[15,33,158],"essential":[16],"for":[17,128,160],"audition;":[19],"sound":[20,62,149],"source":[21],"localization,":[22],"separation,":[23],"recognition":[25],"separated":[27,108,148],"sounds.":[28],"While":[29],"the":[30,36,54,102,119,133,136,145,152,168,173,176],"first":[31],"two":[32],"frequently":[34],"addressed,":[35],"last":[37],"one":[38],"has":[39],"not":[40],"been":[41],"studied":[42],"so":[43],"much.":[44],"We":[45],"present":[46],"a":[47,51,71,81,87,139],"system":[48],"that":[49,84,135],"gives":[50,85],"ability":[55],"to":[56],"localize,":[57],"separate":[58],"recognize":[60],"simultaneous":[61,162],"sources.":[63,94],"microphone":[65],"array":[66],"is":[67],"used":[68],"along":[69],"with":[70,138],"real-time":[72,111],"dedicated":[73],"implementation":[74],"Geometric":[76],"Source":[77],"Separation":[78],"(GSS)":[79],"multi-channel":[82],"post-filter":[83,153,174],"us":[86],"further":[88],"reduction":[89,184],"interferences":[91],"from":[92,118,167],"other":[93],"An":[95],"automatic":[96],"speech":[97],"recognizer":[98],"(ASR)":[99],"based":[100],"on":[101],"Missing":[103],"Feature":[104],"Theory":[105],"(MFT)":[106],"recognizes":[107],"sounds":[109],"in":[110,132,181,185],"by":[112,150],"generating":[113],"missing":[114,177],"feature":[115,154,178],"masks":[116],"automatically":[117],"post-filtering":[120],"step.":[121],"The":[122],"main":[123],"advantage":[124],"this":[126],"approach":[127],"robots":[130],"resides":[131],"fact":[134],"ASR":[137],"clean":[140],"acoustic":[141],"model":[142],"can":[143],"adapt":[144],"distortion":[146],"consulting":[151],"masks.":[155],"Recognition":[156],"rates":[157],"presented":[159],"speakers":[163],"located":[164],"at":[165],"2m":[166],"robot.":[169],"Use":[170],"both":[172],"mask":[179],"results":[180],"an":[182],"average":[183],"error":[186],"rate":[187],"42%":[189],"(relative).":[190]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
