{"id":"https://openalex.org/W2171675276","doi":"https://doi.org/10.1109/icmi.2002.1166972","title":"Robust noisy speech recognition with adaptive frequency bank selection","display_name":"Robust noisy speech recognition with adaptive frequency bank selection","publication_year":2003,"publication_date":"2003-06-26","ids":{"openalex":"https://openalex.org/W2171675276","doi":"https://doi.org/10.1109/icmi.2002.1166972","mag":"2171675276"},"language":"en","primary_location":{"id":"doi:10.1109/icmi.2002.1166972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmi.2002.1166972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Fourth IEEE International Conference on Multimodal Interfaces","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/A5115529152","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0002-5432-9325"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Tian","raw_affiliation_strings":["Department of Electronics Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053201857","display_name":"Ji Wu","orcid":"https://orcid.org/0000-0002-3937-2368"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Wu","raw_affiliation_strings":["Department of Electronics Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024726193","display_name":"Zuoying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuoying Wang","raw_affiliation_strings":["Department of Electronics Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030125708","display_name":"Dajin Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dajin Lu","raw_affiliation_strings":["Department of Electronics Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3179,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.56819953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"97","issue":null,"first_page":"75","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9979000091552734,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9919000267982483,"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":0.8264111280441284},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7674002647399902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7222650051116943},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5780665278434753},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5448522567749023},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4733198583126068},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4436016082763672},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4344950318336487},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.41608840227127075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4109700322151184},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4040650725364685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36660635471343994},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07283991575241089}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8264111280441284},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7674002647399902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222650051116943},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5780665278434753},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5448522567749023},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4733198583126068},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4436016082763672},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4344950318336487},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.41608840227127075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4109700322151184},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4040650725364685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36660635471343994},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07283991575241089},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmi.2002.1166972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmi.2002.1166972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. Fourth IEEE International Conference on Multimodal Interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W202024829","https://openalex.org/W1631909651","https://openalex.org/W1974387177","https://openalex.org/W2036099872","https://openalex.org/W2051970538","https://openalex.org/W2069976350","https://openalex.org/W2104499707","https://openalex.org/W2133941891","https://openalex.org/W2141063921","https://openalex.org/W2141493634","https://openalex.org/W2146064606","https://openalex.org/W2158483598","https://openalex.org/W2170912900"],"related_works":["https://openalex.org/W4252379076","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2069517613"],"abstract_inverted_index":{"With":[0],"the":[1,8,24,36,49,83,114,128,137,147,160,163,174],"development":[2],"of":[3,11,26,39,42,51,162],"automatic":[4],"speech":[5,12,27,76,111,170],"recognition":[6,13,28,171],"technology,":[7],"robustness":[9],"problem":[10,25],"systems":[14],"is":[15,107,155],"becoming":[16],"more":[17,19],"and":[18,71,79,97,135,184],"important.":[20],"This":[21],"paper":[22],"addresses":[23],"in":[29,93],"an":[30,152],"additive":[31,52],"background":[32],"noise":[33,43,53],"environment.":[34],"Since":[35],"frequency":[37,47,56,63,84,120,129,149],"energy":[38],"different":[40,46],"types":[41],"focuses":[44],"on":[45,54,146,167],"banks,":[48],"effects":[50],"each":[55],"bank":[57,85],"are":[58,72,132,143],"different.":[59],"The":[60],"seriously":[61,138],"obscured":[62,139],"banks":[64,121,130],"have":[65],"little":[66],"word":[67,90],"signal":[68],"information":[69],"left,":[70],"harmful":[73],"for":[74,122],"subsequence":[75],"processing.":[77],"Wu":[78],"Lin":[80],"(2000)":[81],"applied":[82],"selection":[86],"theory":[87,106],"to":[88,109,158,178],"robust":[89],"boundary":[91],"detection":[92,100],"a":[94],"noisy":[95,110],"environment,":[96],"obtained":[98],"good":[99],"results.":[101],"In":[102],"this":[103,105],"paper,":[104],"extended":[108],"recognition.":[112],"Unlike":[113],"standard":[115],"MFCC":[116],"which":[117],"uses":[118],"all":[119],"cepstral":[123,185],"coefficients,":[124],"we":[125],"only":[126,145],"use":[127],"that":[131,173],"slightly":[133],"corrupted":[134],"discard":[136],"ones.":[140],"Cepstral":[141],"coefficients":[142],"calculated":[144],"selected":[148],"banks.":[150],"Moreover,":[151],"acoustic":[153,164],"model":[154],"also":[156],"adapted":[157],"match":[159],"modification":[161],"feature.":[165],"Experiments":[166],"continuous":[168],"digital":[169],"show":[172],"proposed":[175],"algorithm":[176],"leads":[177],"better":[179],"performance":[180],"than":[181],"spectral":[182],"subtraction":[183],"mean":[186],"normalization":[187],"at":[188],"low":[189],"SNRs.":[190]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}