{"id":"https://openalex.org/W2018455158","doi":"https://doi.org/10.1109/icassp.2013.6639232","title":"Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech","display_name":"Adding controlled amount of noise to improve recognition of compressed and spectrally distorted speech","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2018455158","doi":"https://doi.org/10.1109/icassp.2013.6639232","mag":"2018455158"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639232","doi":"https://doi.org/10.1109/icassp.2013.6639232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639232","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"volume":null,"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/A5033391650","display_name":"Jan Nouza","orcid":"https://orcid.org/0000-0003-3960-3194","observed_orcids":["https://orcid.org/0000-0003-3960-3194"]},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Nouza","raw_affiliation_strings":["SpeechLab, Technical University of Liberec, Liberec, Czech Republic","SpeechLab, Tech. Univ. of Liberec, Liberec, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"SpeechLab, Tech. Univ. of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007129369","display_name":"Petr \u010cerva","orcid":"https://orcid.org/0000-0003-0767-0106","observed_orcids":["https://orcid.org/0000-0003-0767-0106"]},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Petr Cerva","raw_affiliation_strings":["SpeechLab, Technical University of Liberec, Liberec, Czech Republic","SpeechLab, Tech. Univ. of Liberec, Liberec, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"SpeechLab, Tech. Univ. of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022347882","display_name":"Jan Silovsk\u00fd","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Silovsky","raw_affiliation_strings":["SpeechLab, Technical University of Liberec, Liberec, Czech Republic","SpeechLab, Tech. Univ. of Liberec, Liberec, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechLab, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]},{"raw_affiliation_string":"SpeechLab, Tech. Univ. of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I147009085"],"apc_list":null,"apc_paid":null,"fwci":0.8612,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.72624231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"91","issue":null,"first_page":"8046","last_page":"8050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9940999746322632,"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":0.9940999746322632,"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":0.005499999970197678,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8050000071525574},{"id":"https://openalex.org/keywords/speech-coding","display_name":"speech coding","score":0.6019999980926514},{"id":"https://openalex.org/keywords/mp3","display_name":"MP3","score":0.8939999938011169},{"id":"https://openalex.org/keywords/spectral-distortion","display_name":"spectral distortion","score":0.9350000023841858},{"id":"https://openalex.org/keywords/noise-injection","display_name":"noise injection","score":0.7210000157356262},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.625}],"concepts":[{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.8284880518913269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797855138778687},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.7614226341247559},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6428919434547424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6281147003173828},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5216820240020752},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.47048452496528625},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.416128933429718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2908317446708679},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1859089732170105},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13966703414916992},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.11394432187080383},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0729374885559082},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639232","doi":"https://doi.org/10.1109/icassp.2013.6639232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639232","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1745839557","https://openalex.org/W1911859126","https://openalex.org/W2100860879","https://openalex.org/W2134749286","https://openalex.org/W2151046578","https://openalex.org/W2238222460","https://openalex.org/W2277967659","https://openalex.org/W2314811536","https://openalex.org/W2407232104","https://openalex.org/W6713616624"],"related_works":["https://openalex.org/W1570867132","https://openalex.org/W1926943011","https://openalex.org/W2551390156","https://openalex.org/W1868281699","https://openalex.org/W2381733013","https://openalex.org/W2599234697","https://openalex.org/W2539793404","https://openalex.org/W1498607327","https://openalex.org/W2402887564","https://openalex.org/W2393244577"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3],"the":[4,40,55,71,76,84,89,109],"recognition":[5,115],"of":[6,22,42,47,57,68,88,106,116,143],"speech":[7,114,134],"whose":[8],"spectrum":[9,36,58],"is":[10],"notably":[11],"distorted":[12,121],"by":[13,19],"lossy":[14],"compression":[15],"(namely":[16],"MP3)":[17],"or":[18,119],"some":[20],"implementations":[21],"`speech":[23],"enhancement'":[24],"techniques.":[25],"We":[26,49,123],"show":[27],"that":[28,37,53],"these":[29],"non-linear":[30],"treatments":[31],"can":[32,111],"introduce":[33],"gaps":[34,77],"in":[35,81,126,136],"significantly":[38,113],"change":[39],"distribution":[41],"MFCCs":[43],"and":[44,60,78,86,94,139],"degrade":[45],"performance":[46],"ASR.":[48],"propose":[50],"a":[51,65,99],"method":[52,110],"measures":[54],"level":[56],"distortion":[59,90],"use":[61,98],"it":[62,125],"for":[63,140],"adding":[64],"controlled":[66],"amount":[67],"noise":[69],"to":[70],"signal.":[72],"It":[73],"effectively":[74],"masks":[75],"helps":[79],"namely":[80],"situations":[82],"where":[83],"source":[85],"parameters":[87],"are":[91],"not":[92],"known":[93],"hence":[95],"we":[96],"cannot":[97],"properly":[100],"matched":[101],"acoustic":[102],"model.":[103],"In":[104],"spite":[105],"its":[107],"simplicity,":[108],"improve":[112],"highly":[117],"compressed":[118],"spectrally":[120],"signals.":[122],"demonstrate":[124],"several":[127],"large":[128],"experiments":[129],"conducted":[130],"on":[131],"publicly":[132],"available":[133],"databases,":[135],"two":[137,141],"languages":[138],"types":[142],"spectral":[144],"distortion.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}