{"id":"https://openalex.org/W3195941398","doi":"https://doi.org/10.1016/j.specom.2021.07.007","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":2021,"publication_date":"2021-08-11","ids":{"openalex":"https://openalex.org/W3195941398","doi":"https://doi.org/10.1016/j.specom.2021.07.007","mag":"3195941398","pmid":"https://pubmed.ncbi.nlm.nih.gov/35784517","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/9246086"},"language":"en","primary_location":{"id":"doi:10.1016/j.specom.2021.07.007","doi":"https://doi.org/10.1016/j.specom.2021.07.007","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2021.07.007","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"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-2","ki-jl-1","norway-1","poland-140","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.specom.2021.07.007","any_repository_has_fulltext":true},"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":true,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA","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":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA","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":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5057910370"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":2030,"currency":"USD","value_usd":2030},"apc_paid":{"value":2030,"currency":"USD","value_usd":2030},"fwci":1.5154,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83011783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"134","issue":null,"first_page":"20","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7128999829292297,"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":0.7128999829292297,"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":0.27469998598098755,"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":0.006099999882280827,"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":0.593999981880188},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.9100000262260437},{"id":"https://openalex.org/keywords/speech-quality-assessment","display_name":"speech quality assessment","score":0.3720000088214874},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5899999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194429874420166},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.7653483152389526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7366942763328552},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5362083315849304},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5229990482330322},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4460867643356323},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.4401867687702179},{"id":"https://openalex.org/C173413354","wikidata":"https://www.wikidata.org/wiki/Q7049470","display_name":"Nonlinear distortion","level":4,"score":0.4345459043979645},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.42060285806655884},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3849177956581116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3112393617630005},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09283336997032166},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.specom.2021.07.007","doi":"https://doi.org/10.1016/j.specom.2021.07.007","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2021.07.007","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"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-2","ki-jl-1","norway-1","poland-140","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"},{"id":"pmid:35784517","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35784517","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech communication","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9246086","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9246086","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Speech Commun","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1016/j.specom.2021.07.007","doi":"https://doi.org/10.1016/j.specom.2021.07.007","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2021.07.007","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"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-2","ki-jl-1","norway-1","poland-140","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3142037619","display_name":"CCI-Mobile: Signal Processing Advancements for Cochlear Implant Users in Naturalistic Environments","funder_award_id":"R01DC016839","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G5339030464","display_name":null,"funder_award_id":"FA8750-15-1- 0205","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320333766","display_name":"Department of Electrical and Computer Engineering, University of Texas at Dallas","ror":null},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W179777611","https://openalex.org/W914169429","https://openalex.org/W1533124881","https://openalex.org/W1552314771","https://openalex.org/W1573773023","https://openalex.org/W1574170747","https://openalex.org/W1600213168","https://openalex.org/W1635512741","https://openalex.org/W1775699292","https://openalex.org/W1985067545","https://openalex.org/W2025929295","https://openalex.org/W2041823554","https://openalex.org/W2064926064","https://openalex.org/W2065387641","https://openalex.org/W2107638917","https://openalex.org/W2127851351","https://openalex.org/W2152305730","https://openalex.org/W2398865593","https://openalex.org/W2401368656","https://openalex.org/W2404649752","https://openalex.org/W2406107511","https://openalex.org/W2406312423","https://openalex.org/W2593116425","https://openalex.org/W2730845691","https://openalex.org/W2890964092","https://openalex.org/W2988616598","https://openalex.org/W3147165232","https://openalex.org/W4236354120","https://openalex.org/W4254373586","https://openalex.org/W6637879876","https://openalex.org/W6713852211","https://openalex.org/W6930004708"],"related_works":["https://openalex.org/W914169429","https://openalex.org/W2546365877","https://openalex.org/W6930004708","https://openalex.org/W2889278126","https://openalex.org/W2064926064","https://openalex.org/W1985067545","https://openalex.org/W2125775073","https://openalex.org/W1566448264","https://openalex.org/W95889525","https://openalex.org/W1759561377"],"abstract_inverted_index":{"Speech,":[0],"speaker,":[1],"and":[2,39,103,116,125,151,189],"language":[3,190],"systems":[4],"have":[5],"traditionally":[6],"relied":[7],"on":[8,112],"carefully":[9],"collected":[10],"speech":[11,113,145,149,169,188],"material":[12],"for":[13,65,99,153,187],"training":[14],"acoustic":[15,74],"models.":[16],"There":[17,60],"is":[18,31,35,61],"an":[19],"enormous":[20],"amount":[21],"of":[22,46,107,161],"freely":[23],"accessible":[24],"audio":[25,82,101,185,210],"content.":[26],"A":[27],"major":[28],"challenge,":[29],"however,":[30],"that":[32,137],"such":[33,70],"data":[34],"not":[36],"professionally":[37],"recorded,":[38],"therefore":[40],"may":[41],"contain":[42],"a":[43,62,93,140],"wide":[44],"diversity":[45],"background":[47],"noise,":[48],"nonlinear":[49,141],"distortions,":[50],"or":[51,55,58,78],"other":[52],"unknown":[53,71],"environmental":[54],"technology-based":[56],"contamination":[57],"mismatch.":[59],"crucial":[63],"need":[64],"automatic":[66,117],"analysis":[67],"to":[68,79,86,166,182],"screen":[69],"datasets":[72],"before":[73],"model":[75],"development":[76,192],"training,":[77],"perform":[80],"input":[81],"purity":[83],"screening":[84],"prior":[85],"classification.":[87],"In":[88],"this":[89],"study,":[90],"we":[91],"propose":[92],"waveform":[94],"based":[95],"clipping":[96,108,138,162],"detection":[97,174],"algorithm":[98],"naturalistic":[100,209],"streams":[102],"examine":[104],"the":[105,123],"impact":[106],"at":[109],"different":[110],"severities":[111],"quality":[114,150],"measurements":[115],"speaker":[118,154],"recognition":[119],"systems.":[120],"We":[121,156],"use":[122],"TIMIT":[124],"NIST":[126],"SRE08":[127],"corpora":[128],"as":[129,135],"case":[130],"studies.":[131],"The":[132,172],"results":[133],"show,":[134],"expected,":[136],"introduces":[139],"distortion":[142],"into":[143],"clean":[144],"data,":[146],"which":[147,176],"reduces":[148],"performance":[152],"recognition.":[155],"also":[157],"investigate":[158],"what":[159],"degree":[160],"can":[163],"be":[164,178],"present":[165],"sustain":[167],"effective":[168],"system":[170],"performance.":[171],"proposed":[173],"system,":[175],"will":[177],"released,":[179],"could":[180],"contribute":[181],"massive":[183],"new":[184],"collections":[186],"technology":[191],"(e.g.":[193],"Google":[194],"Audioset":[195],"(Gemmeke":[196],"et":[197,204],"al.,":[198,205],"2017),":[199],"CRSS-UTDallas":[200],"Apollo":[201,213],"Fearless-Steps":[202],"(Yu":[203],"2014)":[206],"(19,000":[207],"h":[208],"from":[211],"NASA":[212],"missions)).":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2021-08-30T00:00:00"}