{"id":"https://openalex.org/W1587419491","doi":"https://doi.org/10.1109/icassp.2015.7177994","title":"Cepstral noise subtraction for robust automatic speech recognition","display_name":"Cepstral noise subtraction for robust automatic speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1587419491","doi":"https://doi.org/10.1109/icassp.2015.7177994","mag":"1587419491"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7177994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5041108140","display_name":"Robert Rehr","orcid":"https://orcid.org/0000-0001-7458-2320"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert Rehr","raw_affiliation_strings":["Speech Signal Processing Group, University of Oldenburg, Germany","Speech Signal Processing Group, Department of Medical Physics and Acoustics, Cluster of Excellence Hearing4all, University of Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Signal Processing Group, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Speech Signal Processing Group, Department of Medical Physics and Acoustics, Cluster of Excellence Hearing4all, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Speech Signal Processing Group, University of Oldenburg, Germany","Speech Signal Processing Group, Department of Medical Physics and Acoustics, Cluster of Excellence Hearing4all, University of Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Signal Processing Group, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Speech Signal Processing Group, Department of Medical Physics and Acoustics, Cluster of Excellence Hearing4all, University of Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.03640232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"375","last_page":"378"},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/cepstrum","display_name":"Cepstrum","score":0.7511778473854065},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7394567728042603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7392178773880005},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7072931528091431},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6356810331344604},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5058638453483582},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49526897072792053},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4924338757991791},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49044033885002136},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.48567116260528564},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4741746187210083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42817339301109314},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2861326336860657},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2504851818084717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18227964639663696},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11652126908302307}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7511778473854065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7394567728042603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392178773880005},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7072931528091431},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6356810331344604},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5058638453483582},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49526897072792053},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4924338757991791},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49044033885002136},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.48567116260528564},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4741746187210083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42817339301109314},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2861326336860657},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2504851818084717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18227964639663696},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11652126908302307},{"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/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/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/icassp.2015.7177994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1992475611","https://openalex.org/W1995190897","https://openalex.org/W2050693797","https://openalex.org/W2066561607","https://openalex.org/W2084339293","https://openalex.org/W2109816922","https://openalex.org/W2127825510","https://openalex.org/W2148154194","https://openalex.org/W2151484683","https://openalex.org/W2164715564","https://openalex.org/W2538473075","https://openalex.org/W4256112632","https://openalex.org/W6603616073","https://openalex.org/W6684199065","https://openalex.org/W6729019199"],"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/W334008168"],"abstract_inverted_index":{"The":[0,36,179],"robustness":[1],"of":[2,15,120,177],"speech":[3,89,105],"recognizers":[4],"towards":[5],"noise":[6,58,96,122,160],"can":[7,59,76,155],"be":[8,61,77,156],"increased":[9],"by":[10,23,79,141,158],"normalizing":[11],"the":[12,16,56,72,94,121,127,135,159,174],"statistical":[13],"moments":[14],"Mel-frequency":[17],"cepstral":[18,25,30],"coefficients":[19],"(MFCCs),":[20],"e.":[21],"g.":[22],"using":[24],"mean":[26,31],"normalization":[27,34,110],"(CMN)":[28],"or":[29],"and":[32,46,108],"variance":[33],"(CMVN).":[35],"necessary":[37],"statistics":[38],"are":[39,149],"estimated":[40],"over":[41],"a":[42,48,64,69,142],"long":[43],"time":[44],"window":[45],"often,":[47],"complete":[49],"utterance":[50],"is":[51,139],"chosen.":[52],"Consequently,":[53],"changes":[54],"in":[55,171,185],"background":[57,95,146],"only":[60],"tracked":[62,157],"to":[63,71,92,116,126,168,173],"limited":[65],"extent":[66],"which":[67],"poses":[68],"restriction":[70],"performance":[73,181],"gain":[74,182],"that":[75,148,164],"achieved":[78],"these":[80],"techniques.":[81],"In":[82,98],"contrast,":[83],"algorithms":[84],"recently":[85],"developed":[86],"for":[87,152],"single-channel":[88],"enhancement":[90,106],"allow":[91],"track":[93],"quickly.":[97],"this":[99,165],"paper,":[100],"we":[101,114,131,162],"aim":[102],"at":[103],"combining":[104],"techniques":[107],"feature":[109],"methods.":[111],"For":[112,145],"this,":[113],"propose":[115],"transform":[117],"an":[118,169],"estimate":[119],"power":[123],"spectral":[124],"density":[125],"MFCC":[128],"domain,":[129],"where":[130],"subtract":[132],"it":[133],"from":[134],"noisy":[136],"MFCCs.":[137],"This":[138],"followed":[140],"conventional":[143],"CMVN.":[144,178],"noises":[147],"too":[150],"instationary":[151],"CMVN":[153],"but":[154],"estimator,":[161],"show":[163],"processing":[166],"leads":[167],"improvement":[170],"comparison":[172],"sole":[175],"application":[176],"observed":[180],"emerges":[183],"especially":[184],"low":[186],"signal-to-noise-ratios.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}