{"id":"https://openalex.org/W2155082225","doi":"https://doi.org/10.1109/icassp.2004.1325959","title":"Cepstral gain normalization for noise robust speech recognition","display_name":"Cepstral gain normalization for noise robust speech recognition","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2155082225","doi":"https://doi.org/10.1109/icassp.2004.1325959","mag":"2155082225"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1325959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5000178698","display_name":"Shingo Yoshizawa","orcid":"https://orcid.org/0000-0002-3988-4929"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Yoshizawa","raw_affiliation_strings":["Graduate School of Engineering, Hokkaido University, Sapporo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069938327","display_name":"Naoto Hayasaka","orcid":"https://orcid.org/0000-0003-2844-524X"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"N. Hayasaka","raw_affiliation_strings":["Graduate School of Engineering, Hokkaido University, Sapporo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054467709","display_name":"Naoya Wada","orcid":"https://orcid.org/0000-0002-8519-7599"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"N. Wada","raw_affiliation_strings":["Graduate School of Engineering, Hokkaido University, Sapporo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084006463","display_name":"Yoshikazu Miyanaga","orcid":"https://orcid.org/0000-0002-2795-2234"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Miyanaga","raw_affiliation_strings":["Graduate School of Engineering, Hokkaido University, Sapporo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4626,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.77035994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"209"},"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":0.9991000294685364,"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/normalization","display_name":"Normalization (sociology)","score":0.802056074142456},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7886534929275513},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7867931127548218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230973243713379},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6620011925697327},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6322320103645325},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5328443646430969},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5120468735694885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48261651396751404},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.411052942276001},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3219150900840759}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.802056074142456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7886534929275513},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7867931127548218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230973243713379},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6620011925697327},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6322320103645325},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5328443646430969},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5120468735694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48261651396751404},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.411052942276001},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3219150900840759},{"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1325959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1480055486","https://openalex.org/W1970825018","https://openalex.org/W1974387177","https://openalex.org/W2050693797","https://openalex.org/W2052922189","https://openalex.org/W2113911479","https://openalex.org/W2126597753","https://openalex.org/W2128653836","https://openalex.org/W2137075158","https://openalex.org/W2157702502"],"related_works":["https://openalex.org/W4252379076","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948"],"abstract_inverted_index":{"The":[0,66,110],"paper":[1],"describes":[2],"a":[3,75,104],"robust":[4,72],"speech":[5,64],"recognition":[6,94,115],"technique":[7],"which":[8,32,48],"normalizes":[9,49],"cepstral":[10,44,61],"gains":[11,51],"in":[12,39,63],"order":[13],"to":[14,85],"remove":[15],"effects":[16,24],"of":[17,34,54,60,114,123],"additive":[18],"noise.":[19],"We":[20,91],"assume":[21],"that":[22],"the":[23,50,100],"can":[25,69],"be":[26],"expressed":[27],"by":[28,52],"an":[29],"approximate":[30],"model":[31],"consists":[33],"gain":[35,45],"and":[36,57,78,88,103],"DC":[37],"components":[38],"log-spectrum.":[40],"Accordingly,":[41],"we":[42],"propose":[43],"normalization":[46],"(CGN)":[47],"means":[53],"calculating":[55],"maximum":[56],"minimum":[58],"values":[59],"coefficients":[62],"frames.":[65],"proposed":[67],"method":[68],"extract":[70],"noise":[71],"features":[73],"without":[74],"priori":[76],"knowledge":[77],"environmental":[79],"adaptation":[80],"because":[81],"it":[82],"is":[83],"applied":[84],"both":[86],"training":[87],"testing":[89],"data.":[90],"have":[92],"evaluated":[93],"performance":[95],"under":[96],"noisy":[97],"environments":[98],"using":[99],"Noisex-92":[101],"database":[102],"100":[105],"Japanese":[106],"city":[107],"names":[108],"task.":[109],"CGN":[111],"provides":[112],"improvements":[113],"accuracy":[116],"at":[117],"various":[118],"SNRs":[119],"compared":[120],"with":[121],"combinations":[122],"conventional":[124],"methods.":[125]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}