{"id":"https://openalex.org/W4395447416","doi":"https://doi.org/10.1109/taslp.2024.3393718","title":"CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement","display_name":"CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4395447416","doi":"https://doi.org/10.1109/taslp.2024.3393718"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3393718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3393718","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/A5055793437","display_name":"Sherif Abdulatif","orcid":"https://orcid.org/0000-0001-7498-3773"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sherif Abdulatif","raw_affiliation_strings":["Institute of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7498-3773","affiliations":[{"raw_affiliation_string":"Institute of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruizhe Cao","orcid":"https://orcid.org/0009-0005-6397-2995"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ruizhe Cao","raw_affiliation_strings":["Institute of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0009-0005-6397-2995","affiliations":[{"raw_affiliation_string":"Institute of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101717968","display_name":"Bin Yang","orcid":"https://orcid.org/0000-0002-8322-117X"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bin Yang","raw_affiliation_strings":["Institute of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8322-117X","affiliations":[{"raw_affiliation_string":"Institute of Signal Processing and System Theory, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055793437"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":28.6072,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.99872767,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"2477","last_page":"2493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9961000084877014,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.8212000131607056},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.723922848701477},{"id":"https://openalex.org/keywords/conformational-isomerism","display_name":"Conformational isomerism","score":0.46091228723526},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.4553960859775543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3726976215839386},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.261366605758667},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2474624216556549},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11444255709648132}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.8212000131607056},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.723922848701477},{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.46091228723526},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.4553960859775543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3726976215839386},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.261366605758667},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2474624216556549},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11444255709648132},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3393718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3393718","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":137,"referenced_works":["https://openalex.org/W190004713","https://openalex.org/W1230632900","https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1667249920","https://openalex.org/W1677182931","https://openalex.org/W1838895039","https://openalex.org/W1885185971","https://openalex.org/W1893870629","https://openalex.org/W1897240248","https://openalex.org/W1920160043","https://openalex.org/W1964538581","https://openalex.org/W1975163393","https://openalex.org/W1983108229","https://openalex.org/W1987906574","https://openalex.org/W2000005949","https://openalex.org/W2006129368","https://openalex.org/W2013139519","https://openalex.org/W2018026382","https://openalex.org/W2027804983","https://openalex.org/W2040782121","https://openalex.org/W2048142341","https://openalex.org/W2054747948","https://openalex.org/W2057200980","https://openalex.org/W2066755975","https://openalex.org/W2067295501","https://openalex.org/W2068068201","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2086139506","https://openalex.org/W2098749003","https://openalex.org/W2125114513","https://openalex.org/W2130722890","https://openalex.org/W2141411743","https://openalex.org/W2144404214","https://openalex.org/W2147166770","https://openalex.org/W2168379380","https://openalex.org/W2242685705","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2403555780","https://openalex.org/W2404892923","https://openalex.org/W2476548250","https://openalex.org/W2502312327","https://openalex.org/W2593116425","https://openalex.org/W2593414223","https://openalex.org/W2603567530","https://openalex.org/W2609317876","https://openalex.org/W2696967604","https://openalex.org/W2711335087","https://openalex.org/W2746457594","https://openalex.org/W2746904187","https://openalex.org/W2802034954","https://openalex.org/W2808920027","https://openalex.org/W2889500840","https://openalex.org/W2889540509","https://openalex.org/W2890820256","https://openalex.org/W2905649134","https://openalex.org/W2906724656","https://openalex.org/W2922332774","https://openalex.org/W2931364255","https://openalex.org/W2937484199","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2963045393","https://openalex.org/W2963073614","https://openalex.org/W2963103134","https://openalex.org/W2963317762","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963403924","https://openalex.org/W2963902628","https://openalex.org/W2963941778","https://openalex.org/W2972785266","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W2998572311","https://openalex.org/W2998832642","https://openalex.org/W3009541132","https://openalex.org/W3015197852","https://openalex.org/W3015644200","https://openalex.org/W3043547428","https://openalex.org/W3095913803","https://openalex.org/W3096408984","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3102190437","https://openalex.org/W3113290170","https://openalex.org/W3125868443","https://openalex.org/W3136499730","https://openalex.org/W3138516171","https://openalex.org/W3158779859","https://openalex.org/W3161480375","https://openalex.org/W3161950572","https://openalex.org/W3162493033","https://openalex.org/W3163113319","https://openalex.org/W3163842642","https://openalex.org/W3177067699","https://openalex.org/W3191448984","https://openalex.org/W3197260772","https://openalex.org/W3197284240","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3201698955","https://openalex.org/W3206809722","https://openalex.org/W3213188934","https://openalex.org/W3213952100","https://openalex.org/W4200483526","https://openalex.org/W4206537410","https://openalex.org/W4214921663","https://openalex.org/W4221143458","https://openalex.org/W4221145205","https://openalex.org/W4221155904","https://openalex.org/W4225302959","https://openalex.org/W4225905067","https://openalex.org/W4231225162","https://openalex.org/W4253928870","https://openalex.org/W4281820413","https://openalex.org/W4285119904","https://openalex.org/W4289242435","https://openalex.org/W6673959882","https://openalex.org/W6698034911","https://openalex.org/W6724804524","https://openalex.org/W6739901393","https://openalex.org/W6756251360","https://openalex.org/W6757200458","https://openalex.org/W6757668070","https://openalex.org/W6757817989","https://openalex.org/W6762114000","https://openalex.org/W6767367760","https://openalex.org/W6772349387","https://openalex.org/W6941384618"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W2023036309","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1972863456"],"abstract_inverted_index":{"In":[0],"this":[1,88,116],"work,":[2],"we":[3,86],"further":[4],"develop":[5],"the":[6,22,54,58,82,92,119,137,150,154,161],"conformerbased":[7],"metric":[8,104],"generative":[9],"adversarial":[10],"network":[11],"(CMGAN)":[12],"model":[13,45,59],"<sup":[14,186],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[15,187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[16],"for":[17],"speech":[18,83,140],"enhancement":[19,141],"(SE)":[20],"in":[21,136,149],"time-frequency":[23],"(TF)":[24],"domain.":[25],"This":[26,97],"paper":[27],"builds":[28],"on":[29,44,81],"our":[30,69],"previous":[31],"work":[32,89],"but":[33],"takes":[34],"a":[35,167],"more":[36],"indepth":[37],"look":[38],"by":[39],"conducting":[40],"extensive":[41],"ablation":[42],"studies":[43],"inputs":[46],"and":[47,64,74,94,107,145,172,180],"architectural":[48,101],"design":[49],"choices.":[50],"We":[51,66],"rigorously":[52],"tested":[53],"generalization":[55],"ability":[56],"of":[57,163,170,175],"to":[60,90,113],"unseen":[61],"noise":[62],"types":[63],"distortions.":[65],"have":[67],"fortified":[68],"claims":[70],"through":[71],"DNSMOS":[72],"measurements":[73],"listening":[75],"tests.":[76],"Rather":[77],"than":[78],"focusing":[79],"exclusively":[80],"denoising":[84,151],"task,":[85],"extend":[87],"address":[91],"dereverbration":[93],"super-resolution":[95],"tasks.":[96],"necessitated":[98],"exploring":[99],"various":[100],"changes,":[102],"specifically":[103],"discriminator":[105],"scores":[106],"masking":[108],"techniques.":[109],"It":[110],"is":[111,117],"essential":[112],"highlight":[114],"that":[115,122,130],"among":[118],"earliest":[120],"works":[121],"attempted":[123],"complex":[124],"TF-domain":[125],"super-resolution.":[126,146],"Our":[127],"findings":[128],"show":[129],"CMGAN":[131,158,181],"outperforms":[132],"existing":[133],"state-of-the-art":[134],"methods":[135],"three":[138],"major":[139],"tasks:":[142],"denoising,":[143],"dereverberation,":[144],"For":[147],"example,":[148],"task":[152],"using":[153],"Voice":[155],"Bank+DEMAND":[156],"dataset,":[157],"notably":[159],"exceeded":[160],"performance":[162],"prior":[164],"models,":[165],"attaining":[166],"PESQ":[168],"score":[169],"3.41":[171],"an":[173],"SSNR":[174],"11.10":[176],"dB.":[177],"Audio":[178],"samples":[179],"implementations":[182],"are":[183],"available":[184],"online":[185],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[188],".":[189]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":61},{"year":2024,"cited_by_count":16}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}