{"id":"https://openalex.org/W7076053571","doi":"https://doi.org/10.1109/lsp.2025.3599453","title":"MOS-GAN: Mean Opinion Score GAN for Unsupervised Speech Enhancement","display_name":"MOS-GAN: Mean Opinion Score GAN for Unsupervised Speech Enhancement","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7076053571","doi":"https://doi.org/10.1109/lsp.2025.3599453"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3599453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3599453","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":null,"display_name":"Wenbin Jiang","orcid":"https://orcid.org/0000-0002-4063-8952"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Jiang","raw_affiliation_strings":["School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4063-8952","affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fei Wen","orcid":"https://orcid.org/0000-0002-3083-9611"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wen","raw_affiliation_strings":["School of Information Science and Electronic Engineering/School of lntegrated Circuits, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3083-9611","affiliations":[{"raw_affiliation_string":"School of Information Science and Electronic Engineering/School of lntegrated Circuits, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7102-9826","affiliations":[{"raw_affiliation_string":"X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8436,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87602448,"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":"3465","last_page":"3469"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10591","display_name":"Theoretical and Computational Physics","score":0.043299999088048935,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10591","display_name":"Theoretical and Computational Physics","score":0.043299999088048935,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12613","display_name":"X-ray Diffraction in Crystallography","score":0.020999999716877937,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12579","display_name":"Muon and positron interactions and applications","score":0.0203000009059906,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"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/discriminator","display_name":"Discriminator","score":0.9075999855995178},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.8654000163078308},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7526999711990356},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6392999887466431},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5602999925613403},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.460999995470047},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.3993000090122223},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3978999853134155}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9075999855995178},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.8654000163078308},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7526999711990356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722599983215332},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6392999887466431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237999796867371},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5270000100135803},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.460999995470047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3599453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3599453","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4068114840","display_name":null,"funder_award_id":"62271314","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2051428568","https://openalex.org/W2144404214","https://openalex.org/W2146324387","https://openalex.org/W2160815625","https://openalex.org/W2169147844","https://openalex.org/W2289394825","https://openalex.org/W2516001803","https://openalex.org/W2603567530","https://openalex.org/W2891759647","https://openalex.org/W2919115771","https://openalex.org/W2928165649","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W3015199127","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3122264812","https://openalex.org/W3161480375","https://openalex.org/W3174264304","https://openalex.org/W3197912330","https://openalex.org/W3207551191","https://openalex.org/W4221143458","https://openalex.org/W4221149546","https://openalex.org/W4224925070","https://openalex.org/W4253928870","https://openalex.org/W4292969786","https://openalex.org/W4296069327","https://openalex.org/W4309627611","https://openalex.org/W4367281387","https://openalex.org/W4380715308","https://openalex.org/W4385822709","https://openalex.org/W4392903364","https://openalex.org/W4392903924","https://openalex.org/W4400579243","https://openalex.org/W4403059241"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"speech":[2,21,43,85],"enhancement":[3,44,65],"methods":[4],"are":[5],"predominantly":[6],"trained":[7],"in":[8,22],"a":[9,37,78],"supervised":[10],"manner,":[11],"relying":[12],"on":[13,48,129,145],"synthesized":[14],"paired":[15],"noisy-to-clean":[16],"data.":[17],"However,":[18,94],"acquiring":[19],"clean":[20,98,139],"real-world":[23],"scenarios":[24],"is":[25,67,89,104],"often":[26],"difficult":[27],"or":[28],"even":[29],"impractical.":[30],"To":[31,111],"overcome":[32],"this":[33,113],"limitation,":[34],"we":[35,55,115],"propose":[36],"novel":[38],"unsupervised":[39,119,151],"learning":[40],"framework":[41],"for":[42],"that":[45,132],"relies":[46],"solely":[47],"observed":[49],"noisy":[50],"speech,":[51,99],"called":[52],"MOS-GAN.":[53],"Specifically,":[54],"leverage":[56],"generative":[57],"adversarial":[58],"networks":[59],"(GANs),":[60],"where":[61],"the":[62,71,81,133],"generator":[63],"(the":[64],"model)":[66,88],"optimized":[68,90],"to":[69,91,122],"maximize":[70],"mean":[72],"opinion":[73],"score":[74],"(MOS)":[75],"guided":[76],"by":[77],"discriminator,":[79],"while":[80],"discriminator":[82],"(a":[83],"non-intrusive":[84],"quality":[86],"metric":[87],"predict":[92],"MOS.":[93],"without":[95],"using":[96],"reference":[97],"directly":[100],"training":[101,125],"of":[102],"MOS-GAN":[103],"unstable":[105],"and":[106,150],"cannot":[107],"achieve":[108],"satisfactory":[109],"performance.":[110,126],"address":[112],"issue,":[114],"further":[116],"incorporate":[117],"an":[118],"prior":[120],"loss":[121],"substantially":[123],"enhance":[124],"Experimental":[127],"results":[128],"benchmarks":[130],"demonstrate":[131],"proposed":[134],"method,":[135],"which":[136],"requires":[137],"neither":[138],"data":[140],"nor":[141],"teacher":[142],"models,":[143],"performs":[144],"par":[146],"with":[147],"leading":[148],"self-supervised":[149],"approaches.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}