{"id":"https://openalex.org/W4205483086","doi":"https://doi.org/10.23919/eusipco54536.2021.9616163","title":"Speech Enhancement with Zero-Shot Model Selection","display_name":"Speech Enhancement with Zero-Shot Model Selection","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4205483086","doi":"https://doi.org/10.23919/eusipco54536.2021.9616163"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616163","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616163","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5030281426","display_name":"Ryandhimas E. Zezario","orcid":"https://orcid.org/0000-0001-7319-8263"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ryandhimas E. Zezario","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027130404","display_name":"Chiou\u2010Shann Fuh","orcid":"https://orcid.org/0000-0002-6174-2556"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chiou-Shann Fuh","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["*Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"*Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030281426"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.0322,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82471457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"495"},"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/T11309","display_name":"Music and Audio Processing","score":0.9929999709129333,"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":0.9909999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7478113174438477},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6936249732971191},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6090031266212463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6074034571647644},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5718985199928284},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5428765416145325},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5422632694244385},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5406093597412109},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.47906312346458435},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47132375836372375},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.470601886510849},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42642492055892944},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42045828700065613},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41175681352615356},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16902056336402893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1483844518661499},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0948830246925354},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08281394839286804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7478113174438477},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6936249732971191},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6090031266212463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6074034571647644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5718985199928284},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5428765416145325},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5422632694244385},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5406093597412109},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.47906312346458435},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47132375836372375},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.470601886510849},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42642492055892944},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42045828700065613},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41175681352615356},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16902056336402893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1483844518661499},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0948830246925354},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08281394839286804},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616163","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616163","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1952003395","https://openalex.org/W1992475611","https://openalex.org/W2024490156","https://openalex.org/W2064851185","https://openalex.org/W2078528584","https://openalex.org/W2109933951","https://openalex.org/W2128532956","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2296167893","https://openalex.org/W2326115863","https://openalex.org/W2402901296","https://openalex.org/W2405774341","https://openalex.org/W2441043183","https://openalex.org/W2517760955","https://openalex.org/W2586068394","https://openalex.org/W2594607416","https://openalex.org/W2605589342","https://openalex.org/W2755891984","https://openalex.org/W2809824582","https://openalex.org/W2899406861","https://openalex.org/W2921950349","https://openalex.org/W2943554574","https://openalex.org/W2963045393","https://openalex.org/W2963403924","https://openalex.org/W2963853675","https://openalex.org/W2972425344","https://openalex.org/W2973016613","https://openalex.org/W2973032625","https://openalex.org/W3015337486","https://openalex.org/W3015826515","https://openalex.org/W3080158507","https://openalex.org/W3143107425","https://openalex.org/W6629589734","https://openalex.org/W6633117090","https://openalex.org/W6676368796","https://openalex.org/W6769900187","https://openalex.org/W6781751280","https://openalex.org/W7005873353"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W2413243053","https://openalex.org/W410723623","https://openalex.org/W2015341305","https://openalex.org/W2035068594","https://openalex.org/W4225593417","https://openalex.org/W2573498121","https://openalex.org/W3022298670","https://openalex.org/W2167883292","https://openalex.org/W2164167147"],"abstract_inverted_index":{"Recent":[0],"research":[1],"on":[2,118,126],"speech":[3],"enhancement":[4],"(SE)":[5],"has":[6],"seen":[7,159],"the":[8,21,26,54,65,74,100,108,119,127,149,166,176,179],"emergence":[9],"of":[10,28,56,77,178],"deep-learning-based":[11],"methods.":[12],"It":[13],"is":[14,62],"still":[15],"a":[16,46,85,138,140],"challenging":[17],"task":[18],"to":[19,24,44,52,106,165],"determine":[20],"effective":[22],"ways":[23],"increase":[25,53],"generalizability":[27],"SE":[29,57,87,91,104,185],"under":[30],"diverse":[31],"test":[32],"conditions.":[33],"In":[34],"this":[35],"study,":[36],"we":[37],"combine":[38],"zero-shot":[39,47],"learning":[40,43],"and":[41,67,83,123,133,160,169],"ensemble":[42],"propose":[45],"model":[48,88,105,171],"selection":[49,112,116,124,172],"(ZMOS)":[50],"approach":[51,61,152,181],"generalization":[55],"performance.":[58,186],"The":[59,70,96],"proposed":[60,150,180],"realized":[63],"in":[64,157,182],"offline":[66,71],"online":[68,97],"phases.":[69],"phase":[72,98],"clusters":[73],"entire":[75],"set":[76],"training":[78],"data":[79],"into":[80],"multiple":[81],"subsets":[82],"trains":[84],"specialized":[86],"(termed":[89],"component":[90,103],"model)":[92],"with":[93],"each":[94],"subset.":[95],"selects":[99],"most":[101],"suitable":[102],"perform":[107],"enhancement.":[109],"Furthermore,":[110],"two":[111],"strategies":[113],"were":[114,135],"developed:":[115],"based":[117,125],"quality":[120,128,142],"score":[121],"(QS)":[122],"embedding":[129],"(QE).":[130],"Both":[131],"QS":[132],"QE":[134],"obtained":[136],"using":[137],"Quality-Net,":[139],"non-intrusive":[141],"assessment":[143],"network.":[144],"Experimental":[145],"results":[146],"confirmed":[147],"that":[148],"ZMOS":[151],"can":[153],"achieve":[154],"better":[155],"performance":[156],"both":[158],"unseen":[161],"noise":[162],"types":[163],"compared":[164],"baseline":[167],"systems":[168],"other":[170],"systems,":[173],"which":[174],"indicates":[175],"effectiveness":[177],"providing":[183],"robust":[184]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}