{"id":"https://openalex.org/W3162424266","doi":"https://doi.org/10.1109/waspaa52581.2021.9632752","title":"Zero-Shot Personalized Speech Enhancement Through Speaker-Informed Model Selection","display_name":"Zero-Shot Personalized Speech Enhancement Through Speaker-Informed Model Selection","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3162424266","doi":"https://doi.org/10.1109/waspaa52581.2021.9632752","mag":"3162424266"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632752","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/A5085011950","display_name":"Aswin Sivaraman","orcid":"https://orcid.org/0000-0003-2248-4846"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aswin Sivaraman","raw_affiliation_strings":["Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"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/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Indiana University, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085011950"],"corresponding_institution_ids":["https://openalex.org/I592451"],"apc_list":null,"apc_paid":null,"fwci":1.2345,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78799224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"175"},"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":0.9995999932289124,"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":0.996399998664856,"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":0.7448925375938416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6357216835021973},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5406813621520996},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5242619514465332},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5202787518501282},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.511935830116272},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4812012314796448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4674200713634491},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4514533281326294},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.446536660194397},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42730778455734253},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.36534059047698975},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3602716326713562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448925375938416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6357216835021973},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5406813621520996},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5242619514465332},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5202787518501282},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.511935830116272},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4812012314796448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4674200713634491},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4514533281326294},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.446536660194397},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42730778455734253},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.36534059047698975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3602716326713562},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632752","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1790748249","https://openalex.org/W1897240248","https://openalex.org/W2078528584","https://openalex.org/W2109761419","https://openalex.org/W2121973264","https://openalex.org/W2127589108","https://openalex.org/W2128653836","https://openalex.org/W2141411743","https://openalex.org/W2148628165","https://openalex.org/W2150769028","https://openalex.org/W2150884987","https://openalex.org/W2157331557","https://openalex.org/W2187089797","https://openalex.org/W2219249508","https://openalex.org/W2304609584","https://openalex.org/W2550397165","https://openalex.org/W2746710273","https://openalex.org/W2748488820","https://openalex.org/W2775477443","https://openalex.org/W2787692317","https://openalex.org/W2900368655","https://openalex.org/W2962866211","https://openalex.org/W2963853675","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2973016613","https://openalex.org/W2973032625","https://openalex.org/W2973062255","https://openalex.org/W3015219411","https://openalex.org/W3080427797","https://openalex.org/W3097911996","https://openalex.org/W3112462122","https://openalex.org/W3124794156","https://openalex.org/W3161266072","https://openalex.org/W4205483086","https://openalex.org/W6629717138","https://openalex.org/W6688816777","https://openalex.org/W6755462816","https://openalex.org/W6787320306"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W3111219495","https://openalex.org/W1600259599","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2419146053","https://openalex.org/W2914064142"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,16,26,71,125],"novel":[4],"zero-shot":[5],"learning":[6],"approach":[7],"towards":[8,25,214],"personalized":[9],"speech":[10,22,130],"enhancement":[11],"through":[12],"the":[13,48,87,95,102,106,136,145,149,160,165,188],"use":[14],"of":[15,74,89,138,187,200],"sparsely":[17],"active":[18],"ensemble":[19,61,196],"model.":[20],"Optimizing":[21],"denoising":[23,101],"systems":[24],"particular":[27],"test-time":[28,38,49,83,216],"speaker":[29,50,84,151,178],"can":[30,203],"improve":[31],"performance":[32],"and":[33,93,117,180,211],"reduce":[34],"run-time":[35],"complexity.":[36],"However,":[37],"model":[39,62],"adaptation":[40,213],"may":[41],"be":[42],"challenging":[43],"if":[44],"collecting":[45],"data":[46],"from":[47,70,148],"is":[51,115],"not":[52],"possible.":[53],"To":[54,119],"this":[55,174],"end,":[56],"we":[57,122,155,176],"propose":[58],"using":[59,128],"an":[60,90],"wherein":[63],"each":[64],"specialist":[65,98,182],"module":[66,80,99],"denoises":[67],"noisy":[68,129],"utterances":[69,146],"distinct":[72],"partition":[73],"training":[75,107,170,190],"set":[76,108,171],"speakers.":[77,217],"The":[78],"gating":[79],"inexpensively":[81],"estimates":[82],"characteristics":[85],"in":[86],"form":[88],"embedding":[91,167],"vector":[92],"selects":[94],"most":[96],"appropriate":[97],"for":[100],"test":[103],"signal.":[104],"Grouping":[105],"speakers":[109],"into":[110],"non-overlapping":[111],"semantically":[112],"similar":[113],"groups":[114,179],"non-trivial":[116],"ill-defined.":[118],"do":[120],"this,":[121],"first":[123],"train":[124,181],"Siamese":[126],"network":[127],"pairs":[131],"to":[132],"maximize":[133],"or":[134,152],"minimize":[135],"similarity":[137],"its":[139],"output":[140],"vectors":[141,168],"depending":[142],"on":[143,159],"whether":[144],"derive":[147],"same":[150],"not.":[153],"Next,":[154],"perform":[156],"k-means":[157],"clustering":[158],"latent":[161],"space":[162],"formed":[163],"by":[164],"averaged":[166],"per":[169],"speaker.":[172],"In":[173],"way,":[175],"designate":[177],"modules":[183],"optimized":[184],"around":[185],"partitions":[186],"complete":[189],"set.":[191],"Our":[192],"experiments":[193],"show":[194],"that":[195],"models":[197,207],"made":[198],"up":[199],"low-capacity":[201],"specialists":[202],"outperform":[204],"high-capacity":[205],"generalist":[206],"with":[208],"greater":[209],"efficiency":[210],"improved":[212],"unseen":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}