{"id":"https://openalex.org/W2583851971","doi":"https://doi.org/10.1109/lsp.2017.2661699","title":"Locally Normalized Filter Banks Applied to Deep Neural-Network-Based Robust Speech Recognition","display_name":"Locally Normalized Filter Banks Applied to Deep Neural-Network-Based Robust Speech Recognition","publication_year":2017,"publication_date":"2017-01-31","ids":{"openalex":"https://openalex.org/W2583851971","doi":"https://doi.org/10.1109/lsp.2017.2661699","mag":"2583851971"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2017.2661699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2017.2661699","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://americanae.aecid.es/americanae/es/registros/registro.do?tipoRegistro=MTD&idBib=3237599","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013929728","display_name":"Josu\u00e9 Fredes","orcid":"https://orcid.org/0000-0002-9614-4193"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Josue Fredes","raw_affiliation_strings":["Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103827948","display_name":"Jos\u00e9 N\u00f3voa","orcid":null},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Jose Novoa","raw_affiliation_strings":["Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069424860","display_name":"Richard M. Stern","orcid":"https://orcid.org/0000-0003-0557-7282"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard M. Stern","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029824436","display_name":"N\u00e9stor Becerra Yoma","orcid":"https://orcid.org/0000-0002-3052-4687"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Nestor Becerra Yoma","raw_affiliation_strings":["Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Processing and Transmission Laboratory, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3616,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93203221,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"24","issue":"4","first_page":"377","last_page":"381"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9975000023841858,"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":0.7409754395484924},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7166707515716553},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7161387205123901},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6864014267921448},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6582634449005127},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6152487993240356},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5328711867332458},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5236313343048096},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.52073073387146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4897646903991699},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4539213180541992},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4247708320617676},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42047712206840515}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7409754395484924},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7166707515716553},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7161387205123901},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6864014267921448},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6582634449005127},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6152487993240356},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5328711867332458},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5236313343048096},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.52073073387146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4897646903991699},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4539213180541992},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4247708320617676},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42047712206840515},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lsp.2017.2661699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2017.2661699","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:americanae.aecid.es:3237599","is_oa":true,"landing_page_url":"http://americanae.aecid.es/americanae/es/registros/registro.do?tipoRegistro=MTD&idBib=3237599","pdf_url":null,"source":{"id":"https://openalex.org/S4306400786","display_name":"Americanae (AECID Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ieee Signal Processing Letters","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:localhost:10533/232402","is_oa":true,"landing_page_url":"http://hdl.handle.net/10533/232402","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ieee Signal Processing Letters","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:americanae.aecid.es:3237599","is_oa":true,"landing_page_url":"http://americanae.aecid.es/americanae/es/registros/registro.do?tipoRegistro=MTD&idBib=3237599","pdf_url":null,"source":{"id":"https://openalex.org/S4306400786","display_name":"Americanae (AECID Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ieee Signal Processing Letters","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W48303286","https://openalex.org/W144317751","https://openalex.org/W619799124","https://openalex.org/W1524333225","https://openalex.org/W1550695516","https://openalex.org/W1576555758","https://openalex.org/W1585276604","https://openalex.org/W1586176709","https://openalex.org/W1602122992","https://openalex.org/W1992468098","https://openalex.org/W1994396704","https://openalex.org/W2015337779","https://openalex.org/W2062164080","https://openalex.org/W2066561607","https://openalex.org/W2089920437","https://openalex.org/W2111492050","https://openalex.org/W2112021726","https://openalex.org/W2394952970","https://openalex.org/W2408077871","https://openalex.org/W2514656709","https://openalex.org/W2515753980","https://openalex.org/W2518159493","https://openalex.org/W2914484425","https://openalex.org/W2964138484","https://openalex.org/W4255949318","https://openalex.org/W4384209696","https://openalex.org/W6605859042","https://openalex.org/W6619536949","https://openalex.org/W6631362777","https://openalex.org/W6676587989","https://openalex.org/W6712316285"],"related_works":["https://openalex.org/W2902887112","https://openalex.org/W2606551632","https://openalex.org/W2018086531","https://openalex.org/W2766680336","https://openalex.org/W2387604097","https://openalex.org/W1980297060","https://openalex.org/W2133320490","https://openalex.org/W4289830142","https://openalex.org/W2373675101","https://openalex.org/W3150393935"],"abstract_inverted_index":{"This":[0],"letter":[1],"describes":[2],"modifications":[3],"to":[4,37,148,179],"locally":[5,46],"normalized":[6,47],"filter":[7,154],"banks":[8,155],"(LNFB),":[9],"which":[10,51,74,105],"substantially":[11],"improve":[12],"their":[13],"performance":[14],"on":[15,109],"the":[16,59,65,84,97,164,173],"Aurora-4":[17,165],"robust":[18,178],"speech":[19,30],"recognition":[20,31],"task":[21],"using":[22,77],"a":[23,42,110,113],"Deep":[24],"Neural":[25],"Network-Hidden":[26],"Markov":[27],"Model":[28],"(DNN-HMM)-based":[29],"system.":[32],"The":[33,56,116,167],"modified":[34],"coefficients,":[35],"referred":[36],"as":[38],"LNFB":[39,60,122,125],"features,":[40],"are":[41,75,94,161],"filter-bank":[43],"version":[44],"of":[45,58,67,72,87,99,142],"cepstral":[48],"coefficients":[49],"(LNCC),":[50],"have":[52],"been":[53],"described":[54],"previously.":[55],"ability":[57],"features":[61,129,150,189],"is":[62,106,176,191],"enhanced":[63],"through":[64,96],"use":[66,98],"newly":[68],"proposed":[69,174],"dynamic":[70],"versions":[71],"them,":[73],"developed":[76],"an":[78,134],"approach":[79],"that":[80,172],"differs":[81],"somewhat":[82],"from":[83,152],"traditional":[85],"development":[86],"delta":[88,126],"and":[89,102,112,127,130,144,158,184,190],"delta-delta":[90,128],"features.":[91],"Further":[92],"enhancements":[93],"obtained":[95],"mean":[100],"normalization":[101],"mean-variance":[103,131],"normalization,":[104],"evaluated":[107],"both":[108],"per-speaker":[111],"per-utterance":[114],"basis.":[115],"best":[117],"performing":[118],"feature":[119],"combination":[120],"(typically":[121],"combined":[123],"with":[124,196],"normalization)":[132],"provides":[133],"average":[135],"relative":[136],"reduction":[137],"in":[138,194],"word":[139],"error":[140],"rate":[141],"11.4%":[143],"9.4%,":[145],"respectively,":[146],"compared":[147],"comparable":[149],"derived":[151],"Mel":[153],"when":[156],"clean":[157],"multinoise":[159],"training":[160,183],"used":[162],"for":[163],"evaluation.":[166],"results":[168],"presented":[169],"here":[170],"suggest":[171],"technique":[175],"more":[177,192],"channel":[180,197],"mismatches":[181],"between":[182],"testing":[185],"data":[186],"than":[187],"MFCC-derived":[188],"effective":[193],"dealing":[195],"diversity.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}