{"id":"https://openalex.org/W4383750092","doi":"https://doi.org/10.1109/lsp.2023.3293758","title":"GAN-in-GAN for Monaural Speech Enhancement","display_name":"GAN-in-GAN for Monaural Speech Enhancement","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4383750092","doi":"https://doi.org/10.1109/lsp.2023.3293758"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3293758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3293758","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":"https://openalex.org/A5075576975","display_name":"Yicun Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yicun Duan","raw_affiliation_strings":["University of Nottingham Ningbo China, Ningbo, China","University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033219457","display_name":"Jianfeng Ren","orcid":"https://orcid.org/0000-0003-4619-6590"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Ren","raw_affiliation_strings":["University of Nottingham Ningbo China, Ningbo, China","University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009559278","display_name":"Heng Yu","orcid":"https://orcid.org/0000-0002-0305-2135"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Yu","raw_affiliation_strings":["University of Nottingham Ningbo China, Ningbo, China","University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, China"],"affiliations":[{"raw_affiliation_string":"University of Nottingham Ningbo China, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085533260","display_name":"Xudong Jiang","orcid":"https://orcid.org/0000-0002-9104-2315"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xudong Jiang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075576975"],"corresponding_institution_ids":["https://openalex.org/I13591777"],"apc_list":null,"apc_paid":null,"fwci":2.2459,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88838811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"853","last_page":"857"},"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":0.9987000226974487,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9959999918937683,"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/spectrogram","display_name":"Spectrogram","score":0.8560864329338074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7664449214935303},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5847712159156799},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5801820158958435},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5763647556304932},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.49225297570228577},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.45949792861938477},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4392582178115845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32998037338256836},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0764380395412445}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8560864329338074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664449214935303},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5847712159156799},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5801820158958435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5763647556304932},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.49225297570228577},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.45949792861938477},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4392582178115845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32998037338256836},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0764380395412445}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3293758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3293758","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":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G4624659691","display_name":null,"funder_award_id":"2022Z173","funder_id":"https://openalex.org/F4320324778","funder_display_name":"Ningbo Municipal Bureau of Science and Technology"},{"id":"https://openalex.org/G946517907","display_name":null,"funder_award_id":"2019B10026","funder_id":"https://openalex.org/F4320324778","funder_display_name":"Ningbo Municipal Bureau of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320324778","display_name":"Ningbo Municipal Bureau of Science and Technology","ror":"https://ror.org/00gskyj95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2094721231","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2534681680","https://openalex.org/W2757519008","https://openalex.org/W2892356933","https://openalex.org/W2949558265","https://openalex.org/W2949756029","https://openalex.org/W2963189033","https://openalex.org/W2963341071","https://openalex.org/W2981022124","https://openalex.org/W2998161426","https://openalex.org/W3015411705","https://openalex.org/W3092028330","https://openalex.org/W3096159803","https://openalex.org/W3097945073","https://openalex.org/W3120607380","https://openalex.org/W3129958428","https://openalex.org/W3158779859","https://openalex.org/W3161950572","https://openalex.org/W3175083350","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3198234802","https://openalex.org/W3198968036","https://openalex.org/W3201306501","https://openalex.org/W3206809722","https://openalex.org/W3212231398","https://openalex.org/W3215619467","https://openalex.org/W4221143458","https://openalex.org/W4224916670","https://openalex.org/W4224932134","https://openalex.org/W4225672218","https://openalex.org/W4232282348","https://openalex.org/W4253928870","https://openalex.org/W4283069119","https://openalex.org/W4312642508","https://openalex.org/W4312959668","https://openalex.org/W4313174479","https://openalex.org/W4319295650","https://openalex.org/W4320013936","https://openalex.org/W4385822340","https://openalex.org/W6631190155","https://openalex.org/W6738884980","https://openalex.org/W6757632829","https://openalex.org/W6762114000","https://openalex.org/W6783867762","https://openalex.org/W6790935598","https://openalex.org/W6846517224"],"related_works":["https://openalex.org/W2100772705","https://openalex.org/W3137014862","https://openalex.org/W4391028812","https://openalex.org/W4287867034","https://openalex.org/W3108403339","https://openalex.org/W2162712524","https://openalex.org/W2142924612","https://openalex.org/W3005783148","https://openalex.org/W4312518509","https://openalex.org/W383418545"],"abstract_inverted_index":{"Some":[0],"generative":[1],"adversarial":[2,121],"networks":[3],"(GANs)":[4],"have":[5],"been":[6],"developed":[7],"to":[8,88,108,136],"remove":[9],"background":[10],"noise":[11],"in":[12,60],"real-world":[13],"audio":[14,33,46,64,92,112,154],"recordings.":[15],"MetricGAN":[16],"and":[17,39,62,94],"its":[18,40],"variants":[19,41],"focus":[20],"on":[21,149],"generating":[22],"a":[23,27,48,69,129,138],"clean":[24,90],"spectrogram":[25],"from":[26,47],"noisy":[28,49],"one,":[29,50],"but":[30,51],"the":[31,76,83,91,95,103,110,116,125,150,159],"final":[32,111],"quality":[34],"can't":[35],"be":[36],"guaranteed.":[37],"SEGAN":[38],"directly":[42],"generate":[43],"an":[44,99],"enhanced":[45],"their":[52],"over-long":[53],"input":[54],"representations":[55],"make":[56],"it":[57],"less":[58],"effective":[59],"identifying":[61],"removing":[63],"noise.":[65],"In":[66],"this":[67],"paper,":[68],"novel":[70,130],"GAN-in-GAN":[71,127],"framework":[72],"is":[73,134,144],"proposed,":[74],"where":[75],"inner":[77],"GAN":[78,97],"conducts":[79,98],"spectrogram-to-spectrogram":[80],"recovery":[81,101],"under":[82,102],"supervision":[84,104],"of":[85,105,118],"metric":[86],"discriminators":[87,107],"effectively":[89],"noise,":[93],"outer":[96],"audio-to-audio":[100],"multi-resolution":[106],"optimize":[109],"quality.":[113],"To":[114],"tackle":[115],"challenges":[117],"utilizing":[119],"multiple":[120],"losses":[122],"for":[123,153],"training":[124],"proposed":[126,135,142],"simultaneously,":[128],"gradient":[131],"balancing":[132],"scheme":[133],"facilitate":[137],"coherent":[139],"training.":[140],"The":[141],"method":[143],"compared":[145,160],"with":[146],"state-of-the-art":[147],"methods":[148],"VoiceBank+DEMAND":[151],"dataset":[152],"denoising.":[155],"It":[156],"outperforms":[157],"all":[158],"methods.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}