{"id":"https://openalex.org/W2002714779","doi":"https://doi.org/10.1109/asru.2009.5373532","title":"Manipulation of consonants in natural speech","display_name":"Manipulation of consonants in natural speech","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2002714779","doi":"https://doi.org/10.1109/asru.2009.5373532","mag":"2002714779"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5086635324","display_name":"Jont B. Allen","orcid":"https://orcid.org/0000-0003-3106-1191"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jont Allen","raw_affiliation_strings":["Beckman Institute, University of Illinois, Urbana-Champaign, USA","Beckman Institute, Univ. of Illinois at Urbana-Champaign (USA)"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, Univ. of Illinois at Urbana-Champaign (USA)","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102722652","display_name":"Feipeng Li","orcid":"https://orcid.org/0000-0002-4172-0608"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feipeng Li","raw_affiliation_strings":["Beckman Institute, University of Illinois, Urbana-Champaign, USA","Beckman Institute, Univ. of Illinois at Urbana-Champaign (USA)"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, Univ. of Illinois at Urbana-Champaign (USA)","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086635324"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.3525,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53950751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.992900013923645,"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":0.992900013923645,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9322999715805054,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10534","display_name":"Structural Health Monitoring Techniques","score":0.9316999912261963,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7093615531921387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6727903485298157},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.6627922058105469},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6113176345825195},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5630483627319336},{"id":"https://openalex.org/keywords/place-of-articulation","display_name":"Place of articulation","score":0.5112226009368896},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.5084601640701294},{"id":"https://openalex.org/keywords/nonsense","display_name":"Nonsense","score":0.5008368492126465},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4754716455936432},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4383169710636139},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42634889483451843},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.418900728225708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27330443263053894},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20610445737838745}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7093615531921387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6727903485298157},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.6627922058105469},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6113176345825195},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5630483627319336},{"id":"https://openalex.org/C36933642","wikidata":"https://www.wikidata.org/wiki/Q214090","display_name":"Place of articulation","level":4,"score":0.5112226009368896},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.5084601640701294},{"id":"https://openalex.org/C62923972","wikidata":"https://www.wikidata.org/wiki/Q600499","display_name":"Nonsense","level":3,"score":0.5008368492126465},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4754716455936432},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4383169710636139},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42634889483451843},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.418900728225708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27330443263053894},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20610445737838745},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1964706935","https://openalex.org/W2020946215","https://openalex.org/W2801025542","https://openalex.org/W1966580183","https://openalex.org/W2002773879","https://openalex.org/W2089522121","https://openalex.org/W2083136263","https://openalex.org/W4213283234","https://openalex.org/W4252296115","https://openalex.org/W2373394249"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2,165],"given":[3],"-":[4],"Starting":[5],"in":[6,32,56,95,188,308,356,371,496],"the":[7,33,46,69,82,117,145,178,197,213,232,270,290,300,320,327,343,388,410,494],"1920s,":[8],"researchers":[9,52],"at":[10,53,66,204,209],"AT&T":[11],"Research":[12],"characterized":[13],"speech":[14,43,84,97,286,357,375,401,446,473,486],"perception.":[15],"Until":[16],"1950,":[17],"this":[18,88,142,261,347],"work":[19,75,89,150,251],"was":[20,76,92,156],"done":[21],"by":[22,462],"a":[23,48,157,171,253,280,297,313,335,380,436,439,457,468],"large":[24,281,314,336,381],"group":[25,50],"working":[26,278],"under":[27,68],"Harvey":[28],"Fletcher,":[29],"which":[30],"resulted":[31],"articulation":[34,367],"index,":[35],"an":[36],"important":[37],"tool":[38],"able":[39],"to":[40,59,80,120,135,217,244,303,318,455],"predict":[41,305],"average":[42,166,373],"scores.":[44],"In":[45,140],"1950s":[47],"dedicated":[49],"of":[51,71,87,191,256,284,299,316,338,346,353,379,383,406,412,472,485],"Haskins":[54],"Labs":[55],"NYC":[57],"attempted":[58],"extend":[60],"these":[61,162,257,413],"ideas,":[62],"and":[63,122,208,267,333,479,490,501],"then":[64],"again":[65,170],"MIT":[67],"direction":[70],"Ken":[72],"Stevens,":[73],"further":[74],"done,":[77],"on":[78,476],"trying":[79],"identify":[81,137],"reliable":[83],"cues.":[85],"Most":[86],"after":[90],"1950":[91,149,258],"not":[93,144],"successful":[94,266,370],"finding":[96],"cues,":[98,415],"therefore":[99],"today":[100],"many":[101,107,195],"consider":[102],"it":[103,127],"impossible.":[104],"That":[105],"is,":[106],"believe":[108],"that":[109,131,294,392,403,482],"there":[110],"is":[111,133,143,200,215,243,252,369,423,447],"no":[112],"direct":[113],"unique":[114],"mapping":[115],"from":[116,231,387],"time-frequency":[118],"plane":[119],"consonant":[121,179,354,419],"vowel":[123,421],"recognition.":[124],"For":[125,194],"example":[126],"has":[128],"been":[129,265],"claimed":[130],"context":[132],"necessary":[134],"successfully":[136],"nonsense":[138,384],"consonantvowels.":[139],"fact":[141],"case.":[146],"The":[147,222,240,249,443,504],"post":[148],"mostly":[151],"used":[152],"synthetic":[153],"speech.":[154,450],"This":[155,340],"major":[158,172],"flaw":[159],"with":[160,279,288,312,438],"all":[161,310],"studies.":[163],"Also":[164],"results":[167],"were":[168],"studied,":[169],"flaw.In":[173],"2007":[174],"we":[175,263,323],"carefully":[176,245],"measured":[177],"error":[180,223],"for":[181,219,225,330,334,498,506],"20":[182],"talkers":[183],"speaking":[184],"16":[185],"different":[186,230,441],"consonants,":[187,196,397],"two":[189],"types":[190],"variable":[192],"noise.":[193],"human":[198,449],"performance":[199],"well":[201],"above":[202],"chance":[203],"-20":[205],"dB":[206,211],"SNR,":[207,212],"0":[210],"score":[214,495],"close":[216],"100%":[218],"most":[220],"sounds.":[221,408],"patterns":[224],"individual":[226,331],"sounds":[227,355],"are":[228,404,453],"quite":[229],"average.":[233],"Vowels":[234],"preform":[235],"very":[236,440],"differently":[237],"than":[238],"consonants.":[239,339],"lesson":[241],"learned":[242],"study":[246],"token":[247],"inhomogeneity.":[248],"present":[250],"natural":[254,393],"extension":[255],"studies,":[259],"but":[260],"time":[262],"have":[264,268,324],"determined":[269],"mapping.":[271],"Using":[272],"(1)":[273],"extensive":[274],"psychoacoustic":[275],"methods,":[276],"(2)":[277],"data-base":[282],"(3)":[283],"recorded":[285],"sounds,":[287],"(4)":[289],"newly":[291],"developed":[292],"techniques":[293,452],"(5)":[295],"use":[296,345],"model":[298],"auditory":[301],"system":[302],"(6)":[304],"audible":[306],"cues":[307,329,352,360,402,487],"noise,":[309,463,497],"(7)":[311],"number":[315,337,382],"listeners":[317],"evaluate":[319],"induced":[321],"confusions,":[322],"precisely":[325],"identified":[326],"acoustic":[328,414],"utterances":[332],"paper":[341],"explores":[342],"potential":[344],"new":[348],"knowledge":[349],"about":[350],"perceptual":[351],"processing.":[358],"These":[359,451],"provide":[361],"deep":[362],"insight":[363],"into":[364,426,433,467],"why":[365],"Fletcher's":[366],"index":[368],"predicting":[372],"\"nonsense\"":[374],"syllables.":[376],"Our":[377],"analysis":[378],"Consonant-Vowel":[385],"syllables":[386],"LDC":[389],"database":[390],"reveals":[391],"speech,":[394],"especially":[395],"stop":[396],"often":[398],"contain":[399],"conflicting":[400],"characteristic":[405],"confusable":[407],"Through":[409],"manipulation":[411],"one":[416],"phone":[417],"(a":[418],"or":[420,435],"sound)":[422],"be":[424,431,465,509],"morphed":[425,432,445],"another.":[427],"Meaningful":[428],"sentences":[429],"can":[430,464,491],"nonsense,":[434],"sentence":[437],"meaning.":[442],"resulting":[444],"naturalsounding":[448],"robust":[454],"noise:":[456],"weak":[458],"sound,":[459],"easily":[460],"masked":[461],"converted":[466],"strong":[469],"one.":[470],"Results":[471],"perception":[474],"experiments":[475],"feature-enhanced":[477],"/ka/":[478],"/ga/":[480],"show":[481],"any":[483],"modification":[484],"significantly":[488],"changes,":[489],"even":[492],"improve":[493],"both":[499],"normal":[500],"hearing-impaired":[502],"listeners.":[503],"implications":[505],"ASR":[507],"will":[508],"discussed.":[510]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}