{"id":"https://openalex.org/W2130108834","doi":"https://doi.org/10.1109/icassp.2006.1660076","title":"Model-Basedwiener Filter for Noise Robust Speech Recognition","display_name":"Model-Basedwiener Filter for Noise Robust Speech Recognition","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2130108834","doi":"https://doi.org/10.1109/icassp.2006.1660076","mag":"2130108834"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5088808388","display_name":"Takayuki Arakawa","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Arakawa","raw_affiliation_strings":["Media and Information Research Laboratories, NEC Corporation Limited, Japan","[NEC Corp.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media and Information Research Laboratories, NEC Corporation Limited, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"[NEC Corp.]","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050358434","display_name":"Masanori Tsujikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Tsujikawa","raw_affiliation_strings":["Media and Information Research Laboratories, NEC Corporation Limited, Japan","[NEC Corp.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media and Information Research Laboratories, NEC Corporation Limited, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"[NEC Corp.]","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084065446","display_name":"Ryosuke Isotani","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"R. Isotani","raw_affiliation_strings":["Media and Information Research Laboratories, NEC Corporation Limited, Japan","[NEC Corp.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media and Information Research Laboratories, NEC Corporation Limited, Japan","institution_ids":["https://openalex.org/I118347220"]},{"raw_affiliation_string":"[NEC Corp.]","institution_ids":["https://openalex.org/I118347220"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118347220"],"apc_list":null,"apc_paid":null,"fwci":0.9473,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7209271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"537"},"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":0.9990000128746033,"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":0.9986000061035156,"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/speech-recognition","display_name":"Speech recognition","score":0.7981454133987427},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.7262259721755981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7001178860664368},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6790999174118042},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6587702035903931},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.522788941860199},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49749377369880676},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.48263460397720337},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.46447837352752686},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4488442838191986},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.447273313999176},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4360272288322449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3988211750984192},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.12973973155021667},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07378745079040527}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7981454133987427},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.7262259721755981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001178860664368},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6790999174118042},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6587702035903931},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.522788941860199},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49749377369880676},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.48263460397720337},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.46447837352752686},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4488442838191986},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.447273313999176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4360272288322449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3988211750984192},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.12973973155021667},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07378745079040527},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1660076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W35070573","https://openalex.org/W2045036776","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2161078696","https://openalex.org/W2161924393","https://openalex.org/W3147539069"],"related_works":["https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W2028846388","https://openalex.org/W4295210860","https://openalex.org/W4251820777","https://openalex.org/W2438843077","https://openalex.org/W3168171120","https://openalex.org/W2161534637","https://openalex.org/W2098233558","https://openalex.org/W4312751558"],"abstract_inverted_index":{"In":[0,73,101],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,92],"new":[6],"approach":[7],"for":[8,91],"noise":[9,64,154],"robust":[10],"speech":[11,34,38,68],"recognition,":[12],"which":[13,40,159],"integrates":[14],"signal-processing-based":[15],"spectral":[16,56],"enhancement":[17],"and":[18,141],"statistical-model-based":[19],"compensation.":[20],"The":[21,50,124],"proposed":[22,129,165],"method,":[23],"model-based":[24],"Wiener":[25,106],"filter":[26],"(MBW),":[27],"takes":[28],"three":[29],"steps":[30],"to":[31,150],"estimate":[32],"clean":[33],"signals":[35,69],"from":[36],"noisy":[37],"signals,":[39],"are":[41,115],"corrupted":[42],"by":[43,80],"various":[44],"kinds":[45],"of":[46,99,145,153,163],"additive":[47],"background":[48],"noise.":[49],"first":[51],"step":[52],"is":[53,82,108,155],"the":[54,60,66,74,77,85,102,105,111,118,128,135,142,146,151,161,164],"well-known":[55],"subtraction":[57],"(SS).":[58],"Since":[59],"SS":[61,81],"averagely":[62],"subtracts":[63],"components,":[65],"estimated":[67],"often":[70],"include":[71],"distortion.":[72],"second":[75],"step,":[76,104],"distortion":[78],"caused":[79],"reduced":[83],"using":[84,117],"minimum":[86],"mean":[87],"square":[88],"error":[89],"estimation":[90],"Gaussian":[93],"mixture":[94],"model":[95],"representing":[96],"pre-trained":[97],"knowledge":[98],"speech.":[100],"final":[103],"filtering":[107],"performed":[109],"with":[110],"decision-directed":[112],"method.":[113],"Experiments":[114],"conducted":[116],"Aurora2-J":[119],"(Japanese":[120],"digit":[121],"string)":[122],"database.":[123],"results":[125],"show":[126],"that":[127],"method":[130,166],"performs":[131],"as":[132,134],"well":[133],"ETSI":[136],"advanced":[137],"front-end":[138],"in":[139],"average":[140],"variation":[143],"range":[144],"recognition":[147],"accuracy":[148],"according":[149],"kind":[152],"about":[156],"one":[157],"third,":[158],"demonstrates":[160],"robustness":[162]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}