{"id":"https://openalex.org/W4400579243","doi":"https://doi.org/10.1109/taslp.2024.3426996","title":"Unsupervised Face-Masked Speech Enhancement Using Generative Adversarial Networks With Human-in-the-Loop Assessment Metrics","display_name":"Unsupervised Face-Masked Speech Enhancement Using Generative Adversarial Networks With Human-in-the-Loop Assessment Metrics","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400579243","doi":"https://doi.org/10.1109/taslp.2024.3426996"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3426996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426996","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5073046122","display_name":"Syu\u2010Siang Wang","orcid":"https://orcid.org/0000-0002-2652-5521"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Syu-Siang Wang","raw_affiliation_strings":["Department of Electrical Engineering, Yuan Ze University, Taoyuan, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-2652-5521","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Yuan Ze University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742815","display_name":"Jia\u2010Yang Chen","orcid":"https://orcid.org/0000-0003-0743-0663"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Yang Chen","raw_affiliation_strings":["Department of Electrical Engineering, Yuan Ze University, Taoyuan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Yuan Ze University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080005842","display_name":"Bo-Ren Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo-Ren Bai","raw_affiliation_strings":["Software R&D Department, Fortemedia, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0008-6079-0987","affiliations":[{"raw_affiliation_string":"Software R&D Department, Fortemedia, Taipei, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038450527","display_name":"Shih\u2010Hau Fang","orcid":"https://orcid.org/0000-0003-1580-0257"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shih-Hau Fang","raw_affiliation_strings":["Department of Electrical Engineering, Yuan Ze University, Taoyuan, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-1580-0257","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Yuan Ze University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]},{"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"],"raw_orcid":"https://orcid.org/0000-0001-6956-0418","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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5631,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61211383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"32","issue":null,"first_page":"3826","last_page":"3837"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/adversarial-system","display_name":"Adversarial system","score":0.7035102844238281},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6059482097625732},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5862970948219299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.581743597984314},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5587761402130127},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5163158774375916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5124340653419495},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4620698094367981},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3657909035682678},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36362195014953613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18769967555999756},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18588948249816895},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.0904940664768219}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7035102844238281},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6059482097625732},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5862970948219299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.581743597984314},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5587761402130127},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5163158774375916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5124340653419495},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4620698094367981},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3657909035682678},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36362195014953613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18769967555999756},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18588948249816895},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.0904940664768219},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/taslp.2024.3426996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426996","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1968939597","https://openalex.org/W1975301756","https://openalex.org/W1994906459","https://openalex.org/W2013608223","https://openalex.org/W2093231248","https://openalex.org/W2103934944","https://openalex.org/W2128653836","https://openalex.org/W2130476329","https://openalex.org/W2131030892","https://openalex.org/W2141998673","https://openalex.org/W2160191698","https://openalex.org/W2163101527","https://openalex.org/W2296073425","https://openalex.org/W2400549570","https://openalex.org/W2405774341","https://openalex.org/W2765278963","https://openalex.org/W2793675140","https://openalex.org/W2888858245","https://openalex.org/W2900298217","https://openalex.org/W2937579788","https://openalex.org/W2962793481","https://openalex.org/W2963539064","https://openalex.org/W2963767194","https://openalex.org/W2972394484","https://openalex.org/W2973016613","https://openalex.org/W2979850772","https://openalex.org/W2997418143","https://openalex.org/W3015545615","https://openalex.org/W3015959238","https://openalex.org/W3031135612","https://openalex.org/W3091830790","https://openalex.org/W3096408984","https://openalex.org/W3100604685","https://openalex.org/W3105021688","https://openalex.org/W3120557855","https://openalex.org/W3122264812","https://openalex.org/W3129390785","https://openalex.org/W3147539069","https://openalex.org/W3151133102","https://openalex.org/W3161364427","https://openalex.org/W3161480375","https://openalex.org/W3174264304","https://openalex.org/W3175971180","https://openalex.org/W3196475561","https://openalex.org/W3197042120","https://openalex.org/W3197912330","https://openalex.org/W3200407957","https://openalex.org/W3202278141","https://openalex.org/W3207551191","https://openalex.org/W3212906118","https://openalex.org/W4200258062","https://openalex.org/W4200500028","https://openalex.org/W4206634335","https://openalex.org/W4210436619","https://openalex.org/W4214840799","https://openalex.org/W4220936060","https://openalex.org/W4226198268","https://openalex.org/W4308712522","https://openalex.org/W4309627611","https://openalex.org/W4319585899","https://openalex.org/W4372260337","https://openalex.org/W4372260534","https://openalex.org/W4387010482","https://openalex.org/W4388620484","https://openalex.org/W6675521023","https://openalex.org/W6679390333","https://openalex.org/W6736942654","https://openalex.org/W6748733227","https://openalex.org/W6790691601","https://openalex.org/W6798972960","https://openalex.org/W6801588699","https://openalex.org/W6861531434"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2888032422","https://openalex.org/W4210468674","https://openalex.org/W2996316059","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501"],"abstract_inverted_index":{"The":[0,59,85,152,178],"utilization":[1],"of":[2,13,83,102,110,154,168,180,187],"face":[3],"masks":[4],"is":[5,198],"an":[6,56,92],"essential":[7],"healthcare":[8],"measure,":[9],"particularly":[10],"during":[11,79],"times":[12],"pandemics,":[14],"yet":[15],"it":[16],"can":[17],"present":[18],"challenges":[19],"in":[20,22,70,130,200],"communication":[21],"our":[23],"daily":[24],"lives.":[25],"To":[26,113],"address":[27],"this":[28,150,196],"problem,":[29],"we":[30,116],"propose":[31],"a":[32,76,118,136],"novel":[33],"approach":[34],"known":[35],"as":[36,65,75,159],"the":[37,80,100,103,108,146,155,165,181,185],"human-in-the-loop":[38],"StarGAN":[39,208],"(HL\u2013StarGAN)":[40],"face-masked":[41,119,133,169,191],"speech":[42,106,120,174],"enhancement":[43,197],"method.":[44],"HL\u2013StarGAN":[45,87,148,188],"comprises":[46,125],"discriminator,":[47],"classifier,":[48],"metric":[49,60],"assessment":[50,61,175],"predictor,":[51,62],"and":[52,73,107,135,142,203,209],"generator":[53],"that":[54,96],"leverages":[55],"attention":[57],"mechanism.":[58],"referred":[63],"to":[64,189],"MaskQSS,":[66],"incorporates":[67],"human":[68,111],"participants":[69],"its":[71],"development":[72],"serves":[74],"\u201chuman-in-the-loop\u201d":[77],"module":[78],"learning":[81,94],"process":[82],"HL\u2013StarGAN.":[84],"overall":[86],"model":[88],"was":[89],"trained":[90],"using":[91,149],"unsupervised":[93],"strategy":[95],"simultaneously":[97],"focuses":[98],"on":[99,145],"reconstruction":[101],"original":[104],"clean":[105,137],"optimization":[109],"perception.":[112],"implement":[114],"HL\u2013StarGAN,":[115],"created":[117],"database":[121],"named":[122],"\u201cFMVD,\u201d":[123],"which":[124],"recordings":[126],"from":[127],"34":[128],"speakers":[129],"three":[131],"distinct":[132],"scenarios":[134],"condition.":[138],"We":[139],"conducted":[140],"subjective":[141,204],"objective":[143,202],"tests":[144],"proposed":[147],"database.":[151],"outcomes":[153],"test":[156],"results":[157],"are":[158],"follows:":[160],"(1)":[161],"MaskQSS":[162,182],"successfully":[163],"predicted":[164],"quality":[166],"scores":[167],"voices,":[170],"outperforming":[171,206],"several":[172],"existing":[173],"methods.":[176],"(2)":[177],"integration":[179],"predictor":[183],"enhanced":[184],"ability":[186],"transform":[190],"voices":[192],"into":[193],"high-quality":[194],"speech;":[195],"evident":[199],"both":[201],"tests,":[205],"conventional":[207],"CycleGAN-based":[210],"systems.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}