{"id":"https://openalex.org/W3162538144","doi":"https://doi.org/10.1109/waspaa52581.2021.9632771","title":"Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation","display_name":"Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3162538144","doi":"https://doi.org/10.1109/waspaa52581.2021.9632771","mag":"3162538144"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","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/A5100733417","display_name":"Sunwoo Kim","orcid":"https://orcid.org/0000-0002-7055-6587"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sunwoo Kim","raw_affiliation_strings":["Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408"],"affiliations":[{"raw_affiliation_string":"Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408"],"affiliations":[{"raw_affiliation_string":"Indiana University,Department of Intelligent Systems Engineering,Bloomington,IN,USA,47408","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100733417"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":2.4689,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89824163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"180"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8051130771636963},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7735481858253479},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5231698155403137},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5186076164245605},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4752916097640991},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4618571996688843},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.44150039553642273},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4246743321418762},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4128614068031311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4122246503829956},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4117923974990845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35890015959739685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051130771636963},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7735481858253479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5231698155403137},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5186076164245605},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4752916097640991},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4618571996688843},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.44150039553642273},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4246743321418762},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4128614068031311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4122246503829956},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4117923974990845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35890015959739685},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G6046083165","display_name":null,"funder_award_id":"2046963","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W27961112","https://openalex.org/W652269744","https://openalex.org/W1492071093","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1581984155","https://openalex.org/W1821462560","https://openalex.org/W2078528584","https://openalex.org/W2119144962","https://openalex.org/W2124033848","https://openalex.org/W2141411743","https://openalex.org/W2150295085","https://openalex.org/W2157331557","https://openalex.org/W2219249508","https://openalex.org/W2587088898","https://openalex.org/W2604794864","https://openalex.org/W2766966408","https://openalex.org/W2899515918","https://openalex.org/W2910453440","https://openalex.org/W2933708090","https://openalex.org/W2945528222","https://openalex.org/W2950276680","https://openalex.org/W2951574208","https://openalex.org/W2952218014","https://openalex.org/W2954224973","https://openalex.org/W2962866211","https://openalex.org/W2962894366","https://openalex.org/W2963499153","https://openalex.org/W2964058413","https://openalex.org/W2964299589","https://openalex.org/W2970806306","https://openalex.org/W2972541922","https://openalex.org/W2982802130","https://openalex.org/W2990796920","https://openalex.org/W2998284473","https://openalex.org/W3095717210","https://openalex.org/W3097911996","https://openalex.org/W3099330747","https://openalex.org/W3105867580","https://openalex.org/W3142629163","https://openalex.org/W3162424266","https://openalex.org/W4287632494","https://openalex.org/W6601146891","https://openalex.org/W6629404803","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6677580257","https://openalex.org/W6682222085","https://openalex.org/W6688816777","https://openalex.org/W6745689806","https://openalex.org/W6756086276","https://openalex.org/W6760691258","https://openalex.org/W6762840122","https://openalex.org/W6765174816","https://openalex.org/W6792635402"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W3172493050","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W2593798266","https://openalex.org/W2466503045","https://openalex.org/W1868271753","https://openalex.org/W2289004579","https://openalex.org/W67475362"],"abstract_inverted_index":{"In":[0],"realistic":[1],"speech":[2,32,56],"enhancement":[3,33],"settings":[4],"for":[5,66],"end-user":[6],"devices,":[7],"we":[8,76,82,171],"often":[9],"encounter":[10],"only":[11],"a":[12,29,37,120],"few":[13],"speakers":[14],"and":[15,95,132],"noise":[16],"types":[17],"that":[18,122,145,173],"tend":[19],"to":[20,35,41,52,102,126,129],"reoccur":[21],"in":[22,47],"the":[23,42,59,64,71,78,84,99,104,113,146,153,158,163,186,190],"specific":[24],"acoustic":[25],"environment.":[26],"We":[27],"propose":[28],"novel":[30],"personalized":[31,164],"method":[34,149],"adapt":[36],"compact":[38,154],"denoising":[39,87,182],"model":[40,176],"test-time":[43,49,142],"specificity.":[44],"Our":[45],"goal":[46],"this":[48],"adaptation":[50],"is":[51],"utilize":[53],"no":[54,179],"clean":[55,74,118,137],"target":[57,101],"of":[58,73,115,135,181],"test":[60,159],"speaker,":[61],"thus":[62],"fulfilling":[63],"requirement":[65],"zero-shot":[67,109],"learning.":[68],"To":[69],"complement":[70],"lack":[72],"speech,":[75,119],"employ":[77],"knowledge":[79],"distillation":[80],"framework:":[81],"distill":[83],"more":[85],"advanced":[86],"results":[88],"from":[89],"an":[90],"overly":[91],"large":[92],"teacher":[93,192],"model,":[94],"use":[96],"them":[97],"as":[98],"pseudo":[100],"train":[103],"small":[105],"student":[106,187],"model.":[107],"This":[108],"learning":[110],"procedure":[111],"circumvents":[112],"process":[114,121],"collecting":[116],"users'":[117],"users":[123],"are":[124],"reluctant":[125],"comply":[127],"due":[128],"privacy":[130],"concerns":[131],"technical":[133],"difficulty":[134],"recording":[136],"voice.":[138],"Experiments":[139],"on":[140],"various":[141],"conditions":[143],"show":[144],"proposed":[147],"personalization":[148,174],"can":[150],"significantly":[151],"improve":[152],"models'":[155],"performance":[156],"during":[157],"time.":[160],"Furthermore,":[161],"since":[162],"models":[165,188],"outperform":[166],"larger":[167],"non-personalized":[168],"baseline":[169],"models,":[170],"claim":[172],"achieves":[175],"compression":[177],"with":[178],"loss":[180],"performance.":[183],"As":[184],"expected,":[185],"underperform":[189],"state-of-the-art":[191],"models.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}