{"id":"https://openalex.org/W2143033549","doi":"https://doi.org/10.1109/sped.2011.5940729","title":"Comparison of feature extraction methods for speech recognition in noise-free and in traffic noise environment","display_name":"Comparison of feature extraction methods for speech recognition in noise-free and in traffic noise environment","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2143033549","doi":"https://doi.org/10.1109/sped.2011.5940729","mag":"2143033549"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2011.5940729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2011.5940729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 6th Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5061652068","display_name":"Gell\u00e9rt S\u00e1rosi","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]},{"id":"https://openalex.org/I3131446353","display_name":"Andr\u00e1ssy University Budapest","ror":"https://ror.org/05xezqk59","country_code":"HU","type":"education","lineage":["https://openalex.org/I3131446353"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Gellert Sarosi","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University\uc2a0of\uc2a0Technology\uc2a0and\uc2a0Economics, Budapest, Hungary","[Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University\uc2a0of\uc2a0Technology\uc2a0and\uc2a0Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I3131446353"]},{"raw_affiliation_string":"[Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary]","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074091838","display_name":"Mihaly Mozsary","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]},{"id":"https://openalex.org/I3131446353","display_name":"Andr\u00e1ssy University Budapest","ror":"https://ror.org/05xezqk59","country_code":"HU","type":"education","lineage":["https://openalex.org/I3131446353"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Mihaly Mozsary","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University\uc2a0of\uc2a0Technology\uc2a0and\uc2a0Economics, Budapest, Hungary","[Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University\uc2a0of\uc2a0Technology\uc2a0and\uc2a0Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I3131446353"]},{"raw_affiliation_string":"[Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary]","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]},{"id":"https://openalex.org/I3131446353","display_name":"Andr\u00e1ssy University Budapest","ror":"https://ror.org/05xezqk59","country_code":"HU","type":"education","lineage":["https://openalex.org/I3131446353"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Peter Mihajlik","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University\uc2a0of\uc2a0Technology\uc2a0and\uc2a0Economics, Budapest, Hungary","[Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University\uc2a0of\uc2a0Technology\uc2a0and\uc2a0Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I3131446353"]},{"raw_affiliation_string":"[Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary]","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075146981","display_name":"Tibor Fegy\u00f3","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]},{"id":"https://openalex.org/I3131446353","display_name":"Andr\u00e1ssy University Budapest","ror":"https://ror.org/05xezqk59","country_code":"HU","type":"education","lineage":["https://openalex.org/I3131446353"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tibor Fegyo","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University\uc2a0of\uc2a0Technology\uc2a0and\uc2a0Economics, Budapest, Hungary","[Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University\uc2a0of\uc2a0Technology\uc2a0and\uc2a0Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I3131446353"]},{"raw_affiliation_string":"[Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary]","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1121,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.78648384,"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":"1","last_page":"8"},"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":0.9993000030517578,"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":0.9973999857902527,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.786988377571106},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7470756769180298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7463688850402832},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5931271910667419},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5519216060638428},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4897940158843994},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4483073949813843},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4182114005088806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40134498476982117}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.786988377571106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470756769180298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7463688850402832},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5931271910667419},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5519216060638428},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4897940158843994},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4483073949813843},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4182114005088806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40134498476982117},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped.2011.5940729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2011.5940729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 6th Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W48997180","https://openalex.org/W1489184006","https://openalex.org/W1543522032","https://openalex.org/W1607274768","https://openalex.org/W2046932483","https://openalex.org/W2090861223","https://openalex.org/W2111880697","https://openalex.org/W2158483598","https://openalex.org/W2158849374","https://openalex.org/W6602003631","https://openalex.org/W6632726156","https://openalex.org/W6683469299"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2736574136","https://openalex.org/W2373675101","https://openalex.org/W2038216521","https://openalex.org/W106160982","https://openalex.org/W894828327","https://openalex.org/W2136559180"],"abstract_inverted_index":{"A":[0],"crucial":[1],"part":[2],"of":[3,112],"a":[4,130],"speech":[5,58],"recognizer":[6],"is":[7,16],"the":[8,14,113,134,143,148],"acoustic":[9],"feature":[10,76],"extraction,":[11],"especially":[12],"when":[13],"application":[15],"intended":[17],"to":[18,36,123],"be":[19],"used":[20,79],"in":[21,63,94,142,147],"noisy":[22],"environment.":[23],"In":[24],"this":[25],"paper":[26],"we":[27],"investigate":[28],"several":[29,81],"novel":[30],"front-end":[31],"techniques":[32,120],"and":[33,71,109,137,151],"compare":[34],"them":[35],"multiple":[37,110],"baselines.":[38],"Recognition":[39],"tests":[40],"were":[41,78,139],"performed":[42],"on":[43,49,54],"studio":[44],"quality":[45],"wide":[46],"band":[47,56],"recordings":[48],"Hungarian":[50],"as":[51,53],"well":[52],"narrow":[55],"telephone":[57],"including":[59],"real-life":[60],"noises":[61],"collected":[62],"six":[64],"languages:":[65],"English,":[66],"German,":[67],"French,":[68],"Italian,":[69],"Spanish":[70],"Hungarian.":[72],"The":[73],"following":[74],"baseline":[75],"types":[77],"with":[80],"settings:":[82],"Mel":[83],"Frequency":[84],"Cepstral":[85,115],"Coefficients":[86,116],"(MFCC),":[87],"Perceptual":[88,103],"Linear":[89],"Prediction":[90],"(PLP)":[91],"features":[92],"implemented":[93],"HTK,":[95],"SPHINX,":[96],"or":[97],"by":[98],"ourselves.":[99],"Novel":[100],"methods":[101],"include":[102],"Minimum":[104],"Variance":[105],"Distortionless":[106],"Response":[107],"(PMVDR)":[108],"variations":[111,145],"Power-Normalized":[114],"(PNCC).":[117],"Also,":[118],"adaptive":[119],"are":[121],"applied":[122],"reduce":[124],"convolutive":[125],"distortions.":[126],"We":[127],"have":[128],"experienced":[129],"significant":[131],"difference":[132],"between":[133],"MFCC":[135],"implementations,":[136],"there":[138],"major":[140],"differences":[141],"PNCC":[144],"useful":[146],"different":[149],"bandwidths":[150],"noise":[152],"conditions.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}