{"id":"https://openalex.org/W2950348246","doi":"https://doi.org/10.1109/ncc.2019.8732232","title":"On the Role of Linear, Mel and Inverse-Mel Filterbank in the Context of Automatic Speech Recognition","display_name":"On the Role of Linear, Mel and Inverse-Mel Filterbank in the Context of Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W2950348246","doi":"https://doi.org/10.1109/ncc.2019.8732232","mag":"2950348246"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2019.8732232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2019.8732232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 National Conference on Communications (NCC)","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/A5003438160","display_name":"Hemant Kumar Kathania","orcid":"https://orcid.org/0000-0002-6367-5203"},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Hemant K. Kathania","raw_affiliation_strings":["Dept. of ECE, NIT, Sikkim, India"],"affiliations":[{"raw_affiliation_string":"Dept. of ECE, NIT, Sikkim, India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063682063","display_name":"S. Shahnawazuddin","orcid":"https://orcid.org/0000-0002-3916-9693"},"institutions":[{"id":"https://openalex.org/I11793825","display_name":"National Institute of Technology Patna","ror":"https://ror.org/056wyhh33","country_code":"IN","type":"education","lineage":["https://openalex.org/I11793825","https://openalex.org/I4210152752"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Syed Shahnawazuddin","raw_affiliation_strings":["Dept. of ECE, NIT, Patna, India"],"affiliations":[{"raw_affiliation_string":"Dept. of ECE, NIT, Patna, India","institution_ids":["https://openalex.org/I11793825"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070407855","display_name":"Waquar Ahmad","orcid":"https://orcid.org/0000-0001-7817-3313"},"institutions":[{"id":"https://openalex.org/I114845381","display_name":"National Institute of Technology Calicut","ror":"https://ror.org/03yyd7552","country_code":"IN","type":"education","lineage":["https://openalex.org/I114845381"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Waquar Ahmad","raw_affiliation_strings":["Dept. of ECE, NIT, Calicut, India"],"affiliations":[{"raw_affiliation_string":"Dept. of ECE, NIT, Calicut, India","institution_ids":["https://openalex.org/I114845381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015353805","display_name":"Nagaraj Adiga","orcid":"https://orcid.org/0000-0002-3438-567X"},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nagaraj Adiga","raw_affiliation_strings":["Dept. of CS, University of Crete, Greece"],"affiliations":[{"raw_affiliation_string":"Dept. of CS, University of Crete, Greece","institution_ids":["https://openalex.org/I142617266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003438160"],"corresponding_institution_ids":["https://openalex.org/I101326570"],"apc_list":null,"apc_paid":null,"fwci":0.4334,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71296083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9994999766349792,"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":0.9980000257492065,"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/filter-bank","display_name":"Filter bank","score":0.7647825479507446},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6862462162971497},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6036607623100281},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5466436147689819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5438698530197144},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22182658314704895},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.19187882542610168},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11624756455421448},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.09813162684440613},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06473177671432495}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7647825479507446},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6862462162971497},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6036607623100281},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5466436147689819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5438698530197144},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22182658314704895},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.19187882542610168},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11624756455421448},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.09813162684440613},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06473177671432495},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc.2019.8732232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2019.8732232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W48203715","https://openalex.org/W104463061","https://openalex.org/W141885233","https://openalex.org/W1524333225","https://openalex.org/W1532531043","https://openalex.org/W1540779870","https://openalex.org/W1974736851","https://openalex.org/W1994888226","https://openalex.org/W2066159843","https://openalex.org/W2094954292","https://openalex.org/W2100118853","https://openalex.org/W2101662502","https://openalex.org/W2130722890","https://openalex.org/W2141493634","https://openalex.org/W2147768505","https://openalex.org/W2148154194","https://openalex.org/W2160815625","https://openalex.org/W2164931619","https://openalex.org/W2184045248","https://openalex.org/W2295119550","https://openalex.org/W2338914793","https://openalex.org/W2402172738","https://openalex.org/W2507923760","https://openalex.org/W2587488139","https://openalex.org/W2747399100","https://openalex.org/W2755431812","https://openalex.org/W2766853512","https://openalex.org/W6601939760","https://openalex.org/W6605828447","https://openalex.org/W6631362777","https://openalex.org/W6631949791","https://openalex.org/W6679230416","https://openalex.org/W6703681455","https://openalex.org/W6744394073","https://openalex.org/W6745661829"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2021595906","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"In":[0],"the":[1,8,15,25,50,62,71,99,104,112,116,196],"context":[2,72],"of":[3,30,46,64,73,95,185,193],"automatic":[4],"speech":[5,19,74,82,151,175],"recognition":[6,113,165],"(ASR),":[7],"power":[9],"spectrum":[10],"is":[11,22,32,77,84,91,147,181],"generally":[12],"warped":[13],"to":[14,125],"Mel-scale":[16],"during":[17],"front-end":[18],"parameterization.":[20],"This":[21],"motivated":[23],"by":[24],"fact":[26],"that,":[27,80],"human":[28],"perception":[29],"sound":[31],"nonlinear.":[33],"The":[34,53,132,183],"Mel-filterbank":[35,110],"provide":[36],"better":[37],"resolution":[38],"for":[39,169],"low-frequency":[40],"contents":[41],"while":[42],"a":[43,92,190],"greater":[44],"degree":[45],"averaging":[47],"happens":[48],"in":[49,56,70,98,106,129,138,189],"high-frequency":[51,100],"range.":[52],"work":[54],"presented":[55],"this":[57,139],"paper":[58],"aims":[59],"at":[60],"studying":[61],"role":[63],"linear,":[65],"Mel":[66],"and":[67,152],"inverse-Mel":[68,120,179],"filterbanks":[69],"recognition.":[75],"It":[76],"well":[78,159,172],"known":[79],"when":[81,176],"data":[83,155],"from":[85,156],"high-pitched":[86],"speakers":[87],"like":[88],"children,":[89],"there":[90],"significant":[93],"amount":[94],"relevant":[96],"information":[97,105],"region.":[101],"Hence,":[102],"down-sampling":[103],"that":[107],"range":[108],"through":[109],"reduces":[111],"performance.":[114],"On":[115],"other":[117],"hand,":[118],"employing":[119],"or":[121,178],"linear-filterbanks":[122],"are":[123,167],"expected":[124],"be":[126],"more":[127],"effective":[128],"such":[130],"cases.":[131],"same":[133],"has":[134],"been":[135],"experimentally":[136],"validated":[137],"work.":[140],"To":[141],"do":[142],"so,":[143],"an":[144],"ASR":[145],"system":[146],"developed":[148],"on":[149],"adults'":[150],"tested":[153],"using":[154],"adult":[157,173],"as":[158,160,171],"child":[161],"speakers.":[162],"Significantly":[163],"improved":[164],"rates":[166],"noted":[168],"children's":[170],"females'":[174],"linear":[177,186],"filterbank":[180],"used.":[182],"use":[184],"filters":[187],"results":[188],"relative":[191],"improvement":[192],"21%":[194],"over":[195],"baseline.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}