{"id":"https://openalex.org/W4221143458","doi":"https://doi.org/10.21437/interspeech.2022-517","title":"CMGAN: Conformer-based Metric GAN for Speech Enhancement","display_name":"CMGAN: Conformer-based Metric GAN for Speech Enhancement","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221143458","doi":"https://doi.org/10.21437/interspeech.2022-517"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-517","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-517","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.15149","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081813456","display_name":"Ruizhe Cao","orcid":null},"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":"Ruizhe Cao","raw_affiliation_strings":["University of Stuttgart, Institute of Signal Processing and System Theory, Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute of Signal Processing and System Theory, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","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":false,"raw_author_name":"Sherif Abdulatif","raw_affiliation_strings":["University of Stuttgart, Institute of Signal Processing and System Theory, Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute of Signal Processing and System Theory, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101717969","display_name":"Bin Yang","orcid":"https://orcid.org/0000-0003-3322-867X"},"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":["University of Stuttgart, Institute of Signal Processing and System Theory, Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Institute of Signal Processing and System Theory, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081813456"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":12.7241,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.99213094,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"936","last_page":"940"},"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":0.9882000088691711,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9595999717712402,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.8659501075744629},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8406181335449219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7184373736381531},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6819785833358765},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6623412370681763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5474194288253784},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5346699357032776},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44806942343711853},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4156855344772339},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.381666898727417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34851133823394775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17418819665908813},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.12698298692703247}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8659501075744629},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8406181335449219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7184373736381531},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6819785833358765},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6623412370681763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5474194288253784},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5346699357032776},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44806942343711853},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4156855344772339},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.381666898727417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34851133823394775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17418819665908813},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.12698298692703247},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-517","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-517","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.15149","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15149","pdf_url":"https://arxiv.org/pdf/2203.15149","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.15149","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15149","pdf_url":"https://arxiv.org/pdf/2203.15149","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W2067295501","https://openalex.org/W2094721231","https://openalex.org/W2144404214","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2502312327","https://openalex.org/W2593414223","https://openalex.org/W2603567530","https://openalex.org/W2808920027","https://openalex.org/W2908510526","https://openalex.org/W2949558265","https://openalex.org/W2962866211","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963902628","https://openalex.org/W2998161426","https://openalex.org/W3009541132","https://openalex.org/W3015197852","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3097945073","https://openalex.org/W3158779859","https://openalex.org/W3161950572","https://openalex.org/W3163842642","https://openalex.org/W3191448984","https://openalex.org/W3197284240","https://openalex.org/W3197729725","https://openalex.org/W3201698955","https://openalex.org/W3213188934","https://openalex.org/W4206537410","https://openalex.org/W4225905067","https://openalex.org/W4232282348","https://openalex.org/W4286905522","https://openalex.org/W4287236406","https://openalex.org/W4289242435","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"Recently,":[0],"convolution-augmented":[1],"transformer":[2],"(Conformer)":[3],"has":[4],"achieved":[5],"promising":[6],"performance":[7],"in":[8,27,45,82,134],"automatic":[9],"speech":[10,15,29,111],"recognition":[11],"(ASR)":[12],"and":[13,24,62,70,77,86,146],"time-domain":[14],"enhancement":[16],"(SE),":[17],"as":[18],"it":[19],"can":[20],"capture":[21],"both":[22,68],"local":[23],"global":[25],"dependencies":[26],"the":[28,46,51,83,92,105,108,114,130],"signal.":[30],"In":[31,50,95],"this":[32],"paper,":[33],"we":[34,53],"propose":[35],"a":[36,97,119,140],"conformer-based":[37],"metric":[38,98],"generative":[39],"adversarial":[40],"network":[41],"(CMGAN)":[42],"for":[43],"SE":[44],"time-frequency":[47],"(TF)":[48],"domain.":[49],"generator,":[52],"utilize":[54],"two-stage":[55],"conformer":[56],"blocks":[57],"to":[58,90,102,118],"aggregate":[59],"all":[60],"magnitude":[61,76],"complex":[63,78],"spectrogram":[64,79],"information":[65],"by":[66,112],"modeling":[67],"time":[69],"frequency":[71],"dependencies.":[72],"The":[73],"estimation":[74],"of":[75,107,132,144,148],"is":[80,100],"decoupled":[81],"decoder":[84],"stage":[85],"then":[87],"jointly":[88],"incorporated":[89],"reconstruct":[91],"enhanced":[93,109],"speech.":[94],"addition,":[96],"discriminator":[99],"employed":[101],"further":[103],"improve":[104],"quality":[106],"estimated":[110],"optimizing":[113],"generator":[115],"with":[116,139],"respect":[117],"corresponding":[120],"evaluation":[121],"score.":[122],"Quantitative":[123],"analysis":[124],"on":[125],"Voice":[126],"Bank+DEMAND":[127],"dataset":[128],"indicates":[129],"capability":[131],"CMGAN":[133],"outperforming":[135],"various":[136],"previous":[137],"models":[138],"margin,":[141],"i.e.,":[142],"PESQ":[143],"3.41":[145],"SSNR":[147],"11.10":[149],"dB.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":5}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}