{"id":"https://openalex.org/W3007185811","doi":"https://doi.org/10.1109/asru46091.2019.9003973","title":"Power-Law Nonlinearity with Maximally Uniform Distribution Criterion for Improved Neural Network Training in Automatic Speech Recognition","display_name":"Power-Law Nonlinearity with Maximally Uniform Distribution Criterion for Improved Neural Network Training in Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007185811","doi":"https://doi.org/10.1109/asru46091.2019.9003973","mag":"3007185811"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003973","is_oa":false,"landing_page_url":"http://doi.org/10.1109/asru46091.2019.9003973","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065995328","display_name":"Mehul Kumar","orcid":"https://orcid.org/0000-0001-7341-2362"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehul Kumar","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052377938","display_name":"Kwangyoun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwangyoun Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113125574","display_name":"Dhananjaya Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhananjaya Gowda","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100684422"],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":1.5402,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87798124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"23","issue":null,"first_page":"988","last_page":"995"},"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":0.9997000098228455,"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":0.9995999932289124,"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/histogram","display_name":"Histogram","score":0.6830675601959229},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5956301689147949},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5917499661445618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5610989928245544},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5238364338874817},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.482555091381073},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.44155895709991455},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.43834513425827026},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.42278552055358887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33597779273986816},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32471537590026855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29033613204956055},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.26389241218566895},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.25548550486564636},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17918860912322998},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15056943893432617},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1389836072921753}],"concepts":[{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.6830675601959229},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5956301689147949},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5917499661445618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5610989928245544},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5238364338874817},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.482555091381073},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.44155895709991455},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.43834513425827026},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42278552055358887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33597779273986816},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32471537590026855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29033613204956055},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.26389241218566895},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25548550486564636},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17918860912322998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15056943893432617},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1389836072921753},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003973","is_oa":false,"landing_page_url":"http://doi.org/10.1109/asru46091.2019.9003973","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W587794757","https://openalex.org/W1494198834","https://openalex.org/W1574170747","https://openalex.org/W1607274768","https://openalex.org/W1815076433","https://openalex.org/W1965635292","https://openalex.org/W1979651826","https://openalex.org/W2062164080","https://openalex.org/W2064675550","https://openalex.org/W2088489891","https://openalex.org/W2091696547","https://openalex.org/W2105806712","https://openalex.org/W2107508685","https://openalex.org/W2114719288","https://openalex.org/W2133564696","https://openalex.org/W2160815625","https://openalex.org/W2191779130","https://openalex.org/W2193413348","https://openalex.org/W2213952365","https://openalex.org/W2326699523","https://openalex.org/W2396889049","https://openalex.org/W2398826216","https://openalex.org/W2402144811","https://openalex.org/W2515737026","https://openalex.org/W2545177271","https://openalex.org/W2589857635","https://openalex.org/W2617258110","https://openalex.org/W2622203030","https://openalex.org/W2750499125","https://openalex.org/W2785572076","https://openalex.org/W2799800213","https://openalex.org/W2803023894","https://openalex.org/W2889282842","https://openalex.org/W2936774411","https://openalex.org/W2942228371","https://openalex.org/W2944255943","https://openalex.org/W2953384591","https://openalex.org/W2962728618","https://openalex.org/W2962824709","https://openalex.org/W2963122170","https://openalex.org/W2963980003","https://openalex.org/W2964138484","https://openalex.org/W2964272710","https://openalex.org/W2964308564","https://openalex.org/W2972389417","https://openalex.org/W2972426539","https://openalex.org/W2972816482","https://openalex.org/W2997454826","https://openalex.org/W3007528493","https://openalex.org/W3008587939","https://openalex.org/W3103005696","https://openalex.org/W4294619417","https://openalex.org/W6617368339","https://openalex.org/W6629717138","https://openalex.org/W6638545294","https://openalex.org/W6679434410","https://openalex.org/W6687152286","https://openalex.org/W6687566353","https://openalex.org/W6688428952","https://openalex.org/W6713134421","https://openalex.org/W6747158283"],"related_works":["https://openalex.org/W2766680336","https://openalex.org/W4289830142","https://openalex.org/W2133320490","https://openalex.org/W2125446021","https://openalex.org/W3150393935","https://openalex.org/W2980055100","https://openalex.org/W2186790562","https://openalex.org/W1497065097","https://openalex.org/W2548564146","https://openalex.org/W2061808167"],"abstract_inverted_index":{"In":[0,16,51,123],"this":[1,17,202],"paper,":[2],"we":[3,19,54,74,126,178,206],"describe":[4],"the":[5,13,57,70,88,95,99,102,109,116,137,140,144,167,175,213,226],"Maximum":[6],"Uniformity":[7],"of":[8,42,139,201],"Distribution":[9],"(MUD)":[10],"algorithm":[11,210],"with":[12],"power-law":[14],"nonlinearity.":[15],"approach,":[18],"hypothesize":[20],"that":[21,91,159,205],"neural":[22],"network":[23],"training":[24,110],"will":[25],"become":[26],"more":[27,223],"stable":[28],"if":[29],"feature":[30],"distribution":[31,118],"is":[32,112,204,221],"not":[33,128],"too":[34],"much":[35,222],"skewed.":[36],"We":[37],"propose":[38],"two":[39],"different":[40],"types":[41],"MUD":[43,47,124,162],"approaches:":[44],"power":[45,71,81],"function-based":[46,72],"and":[48,61,143,186,229],"histogram-based":[49,100],"MUD.":[50],"these":[52],"approaches,":[53],"first":[55],"obtain":[56],"mel":[58],"filterbank":[59,67],"coefficients":[60,83],"apply":[62,75],"nonlinearity":[63,79,92,215],"functions":[64],"for":[65,211],"each":[66],"channel.":[68],"With":[69,98],"MUD,":[73,101],"a":[76,120,148,208,217],"power-function":[77,160],"based":[78,161],"where":[80],"function":[82],"are":[84],"chosen":[85],"to":[86,114,233],"maximize":[87],"likelihood":[89],"assuming":[90],"outputs":[93],"follow":[94],"uniform":[96,121],"distribution.":[97,122],"empirical":[103],"Cumulative":[104],"Density":[105],"Function":[106],"(CDF)":[107],"from":[108],"database":[111],"employed":[113],"transform":[115],"original":[117],"into":[119],"processing,":[125],"do":[127],"use":[129],"any":[130,194],"prior":[131],"knowledge":[132],"(e.g.":[133],"logarithmic":[134],"relation)":[135],"about":[136],"energy":[138],"incoming":[141],"signal":[142],"perceived":[145],"intensity":[146],"by":[147],"human.":[149],"Experimental":[150],"results":[151],"using":[152,193],"an":[153],"end-to-end":[154],"speech":[155],"recognition":[156],"system":[157],"demonstrate":[158],"shows":[163],"better":[164],"result":[165],"than":[166,225],"conventional":[168],"Mel":[169],"Filterbank":[170],"Cepstral":[171],"Coefficients":[172],"(MFCCs).":[173],"On":[174],"LibriSpeech":[176],"database,":[177],"could":[179],"achieve":[180],"4.02":[181],"%":[182,188],"WER":[183,189],"on":[184,190],"test-clean":[185],"13.34":[187],"test-other":[191],"without":[192],"Language":[195],"Models":[196],"(LMs).":[197],"The":[198],"major":[199],"contribution":[200],"work":[203],"developed":[207],"new":[209],"designing":[212],"compressive":[214],"in":[216],"data-driven":[218],"way,":[219],"which":[220],"flexible":[224],"previous":[227],"approaches":[228],"may":[230],"be":[231],"extended":[232],"other":[234],"domains":[235],"as":[236],"well.":[237]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}