{"id":"https://openalex.org/W4416251071","doi":"https://doi.org/10.1109/waspaa66052.2025.11230950","title":"Adaptive Slimming for Scalable and Efficient Speech Enhancement","display_name":"Adaptive Slimming for Scalable and Efficient Speech Enhancement","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251071","doi":"https://doi.org/10.1109/waspaa66052.2025.11230950"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5087077768","display_name":"Riccardo Miccini","orcid":"https://orcid.org/0000-0002-0421-6170"},"institutions":[{"id":"https://openalex.org/I4210155671","display_name":"GN Store Nord (Denmark)","ror":"https://ror.org/04ck29617","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210155671"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Riccardo Miccini","raw_affiliation_strings":["GN Audio,Denmark"],"affiliations":[{"raw_affiliation_string":"GN Audio,Denmark","institution_ids":["https://openalex.org/I4210155671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"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":"Minje Kim","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102957401","display_name":"Cl\u00e9ment Laroche","orcid":"https://orcid.org/0000-0003-1753-1898"},"institutions":[{"id":"https://openalex.org/I4210155671","display_name":"GN Store Nord (Denmark)","ror":"https://ror.org/04ck29617","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210155671"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Cl\u00e9ment Laroche","raw_affiliation_strings":["GN Audio,Denmark"],"affiliations":[{"raw_affiliation_string":"GN Audio,Denmark","institution_ids":["https://openalex.org/I4210155671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033388505","display_name":"Luca Pezzarossa","orcid":"https://orcid.org/0000-0002-0863-2526"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Luca Pezzarossa","raw_affiliation_strings":["Technical University of Denmark,Denmark"],"affiliations":[{"raw_affiliation_string":"Technical University of Denmark,Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"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":"Paris Smaragdis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087077768"],"corresponding_institution_ids":["https://openalex.org/I4210155671"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84971335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9835000038146973,"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":0.9835000038146973,"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":0.00570000009611249,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.0017999999690800905,"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/scalability","display_name":"Scalability","score":0.7584999799728394},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7569000124931335},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5641000270843506},{"id":"https://openalex.org/keywords/router","display_name":"Router","score":0.46320000290870667},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.42800000309944153},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4142000079154968},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4097999930381775}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7584999799728394},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7569000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372999787330627},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5641000270843506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5509999990463257},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C2986800882","wikidata":"https://www.wikidata.org/wiki/Q7168187","display_name":"Performance enhancement","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.2766000032424927},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W2067295501","https://openalex.org/W2603567530","https://openalex.org/W2963513932","https://openalex.org/W2964058413","https://openalex.org/W2979816491","https://openalex.org/W3019321633","https://openalex.org/W3028019732","https://openalex.org/W3092864146","https://openalex.org/W3095248373","https://openalex.org/W3095568513","https://openalex.org/W3097911996","https://openalex.org/W3097945073","https://openalex.org/W3100148727","https://openalex.org/W3160129476","https://openalex.org/W3160936850","https://openalex.org/W3161480375","https://openalex.org/W3173563887","https://openalex.org/W3177295825","https://openalex.org/W3204647170","https://openalex.org/W3213528868","https://openalex.org/W4205483086","https://openalex.org/W4313174479","https://openalex.org/W4318464963","https://openalex.org/W4372263565","https://openalex.org/W4385822888","https://openalex.org/W4386764026","https://openalex.org/W4387870004","https://openalex.org/W4392903568","https://openalex.org/W4392904220","https://openalex.org/W4401633910","https://openalex.org/W4408354764"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"(SE)":[2],"enables":[3],"robust":[4],"speech":[5,15,151],"recognition,":[6],"real-time":[7],"communication,":[8],"hearing":[9],"aids,":[10],"and":[11,33,52],"other":[12],"applications":[13],"where":[14],"quality":[16,152],"is":[17,112,119],"crucial.":[18],"However,":[19],"deploying":[20],"such":[21],"systems":[22],"on":[23,143],"resource-constrained":[24],"devices":[25],"involves":[26],"choosing":[27],"a":[28,45,67,83],"static":[29,156],"trade-off":[30],"between":[31],"performance":[32],"computational":[34],"efficiency.":[35],"In":[36,81],"this":[37],"paper,":[38],"we":[39,145],"introduce":[40],"dynamic":[41,128],"slimming":[42],"to":[43,66,136],"DEMUCS,":[44],"popular":[46],"SE":[47],"architecture,":[48],"making":[49],"it":[50],"scalable":[51],"input-adaptive.":[53],"Slimming":[54],"lets":[55],"the":[56,77,89,92,96,100,125,132,147,154],"model":[57,74,135],"operate":[58],"at":[59],"different":[60,68],"utilization":[61,159],"factors":[62],"(UF),":[63],"each":[64],"corresponding":[65],"performance/efficiency":[69],"trade-off,":[70],"effectively":[71],"mimicking":[72],"multiple":[73],"sizes":[75],"without":[76],"extra":[78],"storage":[79],"costs.":[80],"addition,":[82],"router":[84],"subnet,":[85],"trained":[86],"end-to-end":[87],"with":[88],"backbone,":[90],"determines":[91],"optimal":[93],"UF":[94],"for":[95],"current":[97],"input.":[98],"Thus,":[99],"system":[101],"saves":[102],"resources":[103],"by":[104,163],"adaptively":[105],"selecting":[106],"smaller":[107],"UFs":[108],"when":[109],"additional":[110],"complexity":[111],"unnecessary.":[113],"We":[114],"show":[115],"that":[116],"our":[117],"solution":[118],"Pareto-optimal":[120],"against":[121],"individual":[122],"UFs,":[123],"confirming":[124],"benefits":[126],"of":[127,140],"routing.":[129],"When":[130],"training":[131],"proposed":[133],"dynamically-slimmable":[134],"use":[137],"10":[138],"%":[139,158],"its":[141],"capacity":[142],"average,":[144],"obtain":[146],"same":[148],"or":[149],"better":[150],"as":[153],"equivalent":[155],"25":[157],"while":[160],"reducing":[161],"MACs":[162],"29":[164],"%.<sup":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-11-14T00:00:00"}
