{"id":"https://openalex.org/W2896033767","doi":"https://doi.org/10.1121/1.5068230","title":"Nonlinear waveform distortion: Assessment and detection of clipping on speech data and systems","display_name":"Nonlinear waveform distortion: Assessment and detection of clipping on speech data and systems","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2896033767","doi":"https://doi.org/10.1121/1.5068230","mag":"2896033767"},"language":"en","primary_location":{"id":"doi:10.1121/1.5068230","doi":"https://doi.org/10.1121/1.5068230","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5068230","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"conference-abstract","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/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Univ. of Texas at Dallas, 800 W Campbell Rd., Richardson, TX 75080-3021, john.hansen@utdallas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Texas at Dallas, 800 W Campbell Rd., Richardson, TX 75080-3021, john.hansen@utdallas.edu","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043103292","display_name":"Allen Stauffer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allen Stauffer","raw_affiliation_strings":["Univ. of Texas at Dallas, 800 W Campbell Rd., Richardson, TX 75080-3021, john.hansen@utdallas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Texas at Dallas, 800 W Campbell Rd., Richardson, TX 75080-3021, john.hansen@utdallas.edu","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101861591","display_name":"Wei Xia","orcid":"https://orcid.org/0009-0009-4734-6256","observed_orcids":["https://orcid.org/0009-0009-4734-6256"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":["Univ. of Texas at Dallas, 800 W Campbell Rd., Richardson, TX 75080-3021, john.hansen@utdallas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Texas at Dallas, 800 W Campbell Rd., Richardson, TX 75080-3021, john.hansen@utdallas.edu","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"144","issue":"3_Supplement","first_page":"1871","last_page":"1871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7074999809265137,"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":0.7074999809265137,"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":0.2809999883174896,"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":0.00570000009611249,"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/speech-quality","display_name":"speech quality","score":0.6150000095367432},{"id":"https://openalex.org/keywords/automatic-speaker-identification","display_name":"automatic speaker identification","score":0.7749999761581421},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6359999775886536},{"id":"https://openalex.org/keywords/speech-quality-measures","display_name":"speech quality measures","score":0.4869999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377528786659241},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.7997114658355713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6957855224609375},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5942804217338562},{"id":"https://openalex.org/C173413354","wikidata":"https://www.wikidata.org/wiki/Q7049470","display_name":"Nonlinear distortion","level":4,"score":0.5100134611129761},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4810597896575928},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4777107238769531},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.458225816488266},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4492015242576599},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.4299033284187317},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.41254934668540955},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.37983790040016174},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3520042598247528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2916112542152405},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15960192680358887},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10224774479866028},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08089902997016907},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","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/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1121/1.5068230","doi":"https://doi.org/10.1121/1.5068230","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5068230","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W914169429","https://openalex.org/W2546365877","https://openalex.org/W6930004708","https://openalex.org/W2064926064","https://openalex.org/W2889278126","https://openalex.org/W2125775073","https://openalex.org/W2347210599","https://openalex.org/W1985067545","https://openalex.org/W1566448264","https://openalex.org/W2930013255"],"abstract_inverted_index":{"Speech,":[0],"speaker,":[1],"and":[2,43,108,121,130,156,194],"language":[3,195],"systems":[4],"have":[5],"traditionally":[6],"relied":[7],"on":[8,117],"carefully":[9],"collected":[10],"speech":[11,118,132,150,154,174,193],"material":[12,26],"for":[13,28,69,104,158,192],"training":[14],"acoustic":[15,79],"models.":[16],"There":[17,64],"is":[18,34,39,65],"an":[19],"overwhelming":[20],"abundance":[21],"of":[22,50,112,166],"publicly":[23],"accessible":[24],"audio":[25,87,106,190],"available":[27],"training.":[29],"A":[30],"major":[31],"challenge,":[32],"however,":[33],"that":[35,142],"such":[36,74],"found":[37],"data":[38,76],"not":[40],"professionally":[41],"recorded,":[42],"therefore":[44],"may":[45],"contain":[46],"a":[47,66,98,145],"wide":[48],"diversity":[49],"background":[51],"noise,":[52],"nonlinear":[53,146],"distortions,":[54],"or":[55,59,62,83],"other":[56],"unknown":[57,75],"environmental":[58],"technology-based":[60],"contamination":[61],"mismatch.":[63],"critical":[67],"need":[68],"automatic":[70,122],"analysis":[71],"to":[72,84,91,171,188],"screen":[73],"sets":[77],"before":[78],"model":[80],"development":[81],"training,":[82],"perform":[85],"input":[86],"purity":[88],"screening":[89],"prior":[90],"classification.":[92],"In":[93],"this":[94],"study,":[95],"we":[96],"propose":[97],"waveform":[99],"based":[100],"clipping":[101,113,143,167],"detection":[102,179],"algorithm":[103],"naturalistic":[105],"streams":[107],"analyze":[109],"the":[110,128],"impact":[111],"at":[114],"different":[115],"severities":[116],"quality":[119,155],"measures":[120],"speaker":[123,159],"identification":[124],"systems.":[125],"We":[126,161],"use":[127],"TIMIT":[129],"NIST-SRE08":[131],"corpora":[133],"as":[134,140],"case":[135],"studies.":[136],"The":[137,177],"results":[138],"show,":[139],"expected,":[141],"introduces":[144],"distortion":[147],"into":[148],"clean":[149],"data,":[151],"which":[152,181],"reduces":[153],"performance":[157],"recognition.":[160],"also":[162],"investigate":[163],"what":[164],"degree":[165],"can":[168],"be":[169,183],"present":[170],"sustain":[172],"effective":[173],"system":[175],"performance.":[176],"proposed":[178],"system,":[180],"will":[182],"released,":[184],"could":[185],"potentially":[186],"contribute":[187],"new":[189],"collections":[191],"technology":[196],"development.":[197]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2018-10-26T00:00:00"}