{"id":"https://openalex.org/W2149527779","doi":"https://doi.org/10.1109/iros.2009.5354201","title":"Missing-feature-theory-based robust simultaneous speech recognition system with non-clean speech acoustic model","display_name":"Missing-feature-theory-based robust simultaneous speech recognition system with non-clean speech acoustic model","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2149527779","doi":"https://doi.org/10.1109/iros.2009.5354201","mag":"2149527779"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2009.5354201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2009.5354201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5065967819","display_name":"T\u00f4ru Takahashi","orcid":"https://orcid.org/0000-0002-8476-9751"},"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":"Toru Takahashi","raw_affiliation_strings":["Department of Intelligence and Science and Technology. Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Science and Technology. Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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":"Kazuhiro 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/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"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":"Kazunori Komatani","raw_affiliation_strings":["Department of Intelligence and Science and Technology. Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Science and Technology. Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Department of Intelligence and Science and Technology. Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Science and Technology. Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Department of Intelligence and Science and Technology. Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Intelligence and Science and Technology. Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8119,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88238161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"4","issue":null,"first_page":"2730","last_page":"2735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.993399977684021,"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/speech-recognition","display_name":"Speech recognition","score":0.8063449859619141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7301840782165527},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6006507277488708},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5898255109786987},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5629667043685913},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5421060919761658},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5381245613098145},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5237616896629333},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5185680985450745},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5143007636070251},{"id":"https://openalex.org/keywords/white-noise","display_name":"White noise","score":0.4112570285797119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3657721281051636}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8063449859619141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301840782165527},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6006507277488708},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5898255109786987},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5629667043685913},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5421060919761658},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5381245613098145},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5237616896629333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5185680985450745},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5143007636070251},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.4112570285797119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3657721281051636},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2009.5354201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2009.5354201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.178.7178","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.7178","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/IROS2009-Takahashi.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W75154987","https://openalex.org/W1487711593","https://openalex.org/W1498433797","https://openalex.org/W2016882596","https://openalex.org/W2049737414","https://openalex.org/W2121715942","https://openalex.org/W2134910060","https://openalex.org/W2146083413","https://openalex.org/W2148719987","https://openalex.org/W2150866759","https://openalex.org/W2160569100","https://openalex.org/W6678185079"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"A":[0],"humanoid":[1],"robot":[2,13,25],"must":[3],"recognize":[4,20,38],"a":[5],"target":[6,22,30],"speech":[7,23,31,35,41,49,65,80,99,126,132],"signal":[8,32,45,73,81],"while":[9],"people":[10],"around":[11],"the":[12,21,29,39,56,97,110,149,164,171],"chat":[14],"with":[15,142,163,168,170],"them":[16],"in":[17],"real-world.":[18],"To":[19,54,90,103],"signal,":[24],"has":[26],"to":[27,67,78,95,108,124],"separate":[28],"among":[33],"other":[34],"signals":[36,66],"and":[37,74,101,130],"separated":[40,44,79,111],"signal.":[42,112],"As":[43],"includes":[46],"distortion,":[47],"automatic":[48],"recognition":[50,133],"(ASR)":[51],"performance":[52,134,151],"degrades.":[53],"avoid":[55],"degradation,":[57],"we":[58,116],"trained":[59],"an":[60],"acoustic":[61,69,84,165,173],"model":[62,166,174],"from":[63],"non-clean":[64],"adapt":[68],"feature":[70],"of":[71,139,158],"distorted":[72],"adding":[75,155],"white":[76,156],"noise":[77,93,106],"before":[82],"extracting":[83],"feature.":[85],"The":[86,161],"issues":[87],"are":[88],"(1)":[89],"determine":[91,104],"optimal":[92,105],"level":[94,107],"add":[96,109],"training":[98,129],"signals,":[100],"(2)":[102],"In":[113],"this":[114],"paper,":[115],"investigate":[117],"how":[118,131],"much":[119],"noises":[120,157],"should":[121],"be":[122],"added":[123],"clean":[125,172],"data":[127],"for":[128,136],"improves":[135],"different":[137],"positions":[138],"three":[140],"talkers":[141],"soft":[143],"masking.":[144],"Experimental":[145],"results":[146],"show":[147],"that":[148],"best":[150],"is":[152],"obtained":[153],"by":[154,175],"30":[159],"dB.":[160],"ASR":[162,169],"outperforms":[167],"4":[176],"points.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
