{"id":"https://openalex.org/W4392903307","doi":"https://doi.org/10.1109/icassp48485.2024.10446235","title":"DDD: A Perceptually Superior Low-Response-Time DNN-Based Declipper","display_name":"DDD: A Perceptually Superior Low-Response-Time DNN-Based Declipper","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903307","doi":"https://doi.org/10.1109/icassp48485.2024.10446235"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446235","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113145196","display_name":"Jayeon Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayeon Yi","raw_affiliation_strings":["University of Michigan,Dept. of Electrical Engineering and Computer Science","Dept. of Electrical Engineering and Computer Science, University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Dept. of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Dept. of Electrical Engineering and Computer Science, University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031164776","display_name":"Junghyun Koo","orcid":"https://orcid.org/0009-0004-4468-0367"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":["Seoul National University,Dept. of Intelligence and Information","Dept. of Intelligence and Information, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Dept. of Intelligence and Information","institution_ids":["https://openalex.org/I4210145386"]},{"raw_affiliation_string":"Dept. of Intelligence and Information, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088852010","display_name":"Kyogu Lee","orcid":"https://orcid.org/0000-0002-4210-0312"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["Seoul National University,Dept. of Intelligence and Information","Artificial Intelligence Institute, Seoul National University","Dept. of Intelligence and Information, Seoul National University","Interdisciplinary Program in Artificial Intelligence, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Dept. of Intelligence and Information","institution_ids":["https://openalex.org/I4210145386"]},{"raw_affiliation_string":"Artificial Intelligence Institute, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of Intelligence and Information, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Interdisciplinary Program in Artificial Intelligence, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03107749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"51","issue":null,"first_page":"801","last_page":"805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/computer-science","display_name":"Computer science","score":0.7879159450531006},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7818631529808044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7011542320251465},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.52009117603302},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5091778635978699},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4823024272918701},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.48126906156539917},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.47874754667282104},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.42555463314056396},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4232487380504608},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4152294993400574},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4129772186279297},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4106808304786682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3901338577270508},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25716927647590637},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0895736813545227},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.08317318558692932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879159450531006},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7818631529808044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7011542320251465},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.52009117603302},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5091778635978699},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4823024272918701},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.48126906156539917},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.47874754667282104},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.42555463314056396},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4232487380504608},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4152294993400574},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4129772186279297},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4106808304786682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3901338577270508},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25716927647590637},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0895736813545227},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08317318558692932},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446235","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1594529853","https://openalex.org/W1985067545","https://openalex.org/W2141998673","https://openalex.org/W2222562092","https://openalex.org/W2535255545","https://openalex.org/W2593414223","https://openalex.org/W2791686384","https://openalex.org/W2952218014","https://openalex.org/W2970006822","https://openalex.org/W2997007695","https://openalex.org/W3015199127","https://openalex.org/W3043119899","https://openalex.org/W3092028330","https://openalex.org/W3096831136","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3162420637","https://openalex.org/W3203491020","https://openalex.org/W4200483526","https://openalex.org/W4225331245","https://openalex.org/W4297841868","https://openalex.org/W4372266986","https://openalex.org/W4372341905","https://openalex.org/W6635548400","https://openalex.org/W6731221779","https://openalex.org/W6767111847","https://openalex.org/W6783867762","https://openalex.org/W6802017037","https://openalex.org/W6842856065"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2057775761","https://openalex.org/W2951387371","https://openalex.org/W4289106901"],"abstract_inverted_index":{"Clipping":[0],"is":[1,50,158],"a":[2,40,59,77,85,120,171],"common":[3],"nonlinear":[4],"distortion":[5],"that":[6,66,76,114,156],"occurs":[7],"whenever":[8],"the":[9,18,26,36,97,117,140,148,166],"input":[10],"or":[11],"output":[12,101,141],"of":[13,28,100,125,143,160,173],"an":[14,137],"audio":[15],"system":[16],"exceeds":[17],"supported":[19],"range.":[20],"This":[21],"phenomenon":[22],"undermines":[23],"not":[24],"only":[25],"perception":[27],"speech":[29,47,102,112,126],"quality":[30,99],"but":[31],"also":[32,154],"downstream":[33],"processes":[34],"utilizing":[35],"disrupted":[37],"signal.":[38],"Therefore,":[39],"real-time-capable,":[41],"robust,":[42],"and":[43,132],"low-response-time":[44],"method":[45],"for":[46],"declipping":[48,87],"(SD)":[49],"desired.":[51],"In":[52],"this":[53],"work,":[54],"we":[55,90],"introduce":[56],"DDD":[57,115,144,157],"(Demucs-Discriminator-Declipper),":[58],"real-time-capable":[60,80],"speech-declipping":[61],"deep":[62],"neural":[63],"network":[64],"(DNN)":[65],"requires":[67],"less":[68],"response":[69,163],"time":[70],"by":[71,119,170],"design.":[72],"We":[73,128],"first":[74],"observe":[75],"previously":[78],"untested":[79],"DNN":[81,168],"model,":[82],"Demucs,":[83],"exhibits":[84],"reasonable":[86],"performance.":[88],"Then":[89],"utilize":[91],"adversarial":[92],"learning":[93],"objectives":[94],"to":[95,135,147],"increase":[96],"perceptual":[98],"without":[103],"additional":[104],"inference":[105],"overhead.":[106],"Subjective":[107],"evaluations":[108],"on":[109],"harshly":[110],"clipped":[111],"shows":[113],"outperforms":[116],"baselines":[118],"wide":[121],"margin":[122],"in":[123,145],"terms":[124],"quality.":[127],"perform":[129],"detailed":[130],"waveform":[131],"spectral":[133],"analyses":[134],"gain":[136],"insight":[138],"into":[139],"behavior":[142],"comparison":[146],"baselines.":[149],"Finally,":[150],"our":[151],"streaming":[152],"simulations":[153],"show":[155],"capable":[159],"sub-decisecond":[161],"mean":[162],"times,":[164],"outperforming":[165],"state-of-the-art":[167],"approach":[169],"factor":[172],"six.":[174]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}