{"id":"https://openalex.org/W4309676772","doi":"https://doi.org/10.1109/smc53654.2022.9945134","title":"Speech Enhancement Generative Adversarial Network Architecture with Gated Linear Units and Dual-Path Transformers","display_name":"Speech Enhancement Generative Adversarial Network Architecture with Gated Linear Units and Dual-Path Transformers","publication_year":2022,"publication_date":"2022-10-09","ids":{"openalex":"https://openalex.org/W4309676772","doi":"https://doi.org/10.1109/smc53654.2022.9945134"},"language":"en","primary_location":{"id":"doi:10.1109/smc53654.2022.9945134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945134","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5110301017","display_name":"Dehui\ufffd Zhang","orcid":"https://orcid.org/0009-0004-9804-696X"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehui Zhang","raw_affiliation_strings":["Qilu University of Technology,(Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","School of Computer Science and Technology, Qilu University of Technology,(Shandong Academy of Sciences), Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology,(Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"School of Computer Science and Technology, Qilu University of Technology,(Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058696702","display_name":"Anming Dong","orcid":"https://orcid.org/0000-0001-7470-5159"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anming Dong","raw_affiliation_strings":["Qilu University of Technology,(Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","School of Computer Science and Technology, Qilu University of Technology,(Shandong Academy of Sciences), Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology,(Shandong Academy of Sciences),School of Computer Science and Technology,Jinan,China","institution_ids":["https://openalex.org/I152269853"]},{"raw_affiliation_string":"School of Computer Science and Technology, Qilu University of Technology,(Shandong Academy of Sciences), Jinan, China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624236","display_name":"Jiguo Yu","orcid":"https://orcid.org/0000-0001-6451-1158"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiguo Yu","raw_affiliation_strings":["Big Data Institute Qilu University of Technology,(Shandong Academy of Sciences),Jinan,China","(Shandong Academy of Sciences), Big Data Institute Qilu University of Technology, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Big Data Institute Qilu University of Technology,(Shandong Academy of Sciences),Jinan,China","institution_ids":["https://openalex.org/I4210142748"]},{"raw_affiliation_string":"(Shandong Academy of Sciences), Big Data Institute Qilu University of Technology, Jinan, China","institution_ids":["https://openalex.org/I4210142748","https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029236521","display_name":"Yi Cao","orcid":"https://orcid.org/0000-0002-1973-5010"},"institutions":[{"id":"https://openalex.org/I34949971","display_name":"University of Jinan","ror":"https://ror.org/02mjz6f26","country_code":"CN","type":"education","lineage":["https://openalex.org/I34949971"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cao","raw_affiliation_strings":["University of Jinan,School of Information Science and Engineering,Jinan,China","School of Information Science and Engineering, University of Jinan, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Jinan,School of Information Science and Engineering,Jinan,China","institution_ids":["https://openalex.org/I34949971"]},{"raw_affiliation_string":"School of Information Science and Engineering, University of Jinan, Jinan, China","institution_ids":["https://openalex.org/I34949971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045797640","display_name":"Chuanting Zhang","orcid":"https://orcid.org/0000-0002-6685-4071"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chuanting Zhang","raw_affiliation_strings":["University of Bristol,Department of Electrical and Electronic Engineering,Bristol,UK","Department of Electrical and Electronic Engineering, University of Bristol, Bristol, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol,Department of Electrical and Electronic Engineering,Bristol,UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080926527","display_name":"You Zhou","orcid":"https://orcid.org/0000-0003-2482-260X"},"institutions":[{"id":"https://openalex.org/I4210160779","display_name":"Institute of New Materials","ror":"https://ror.org/04s8x9847","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210142748","https://openalex.org/I4210160779"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Zhou","raw_affiliation_strings":["Shandong HiCon New Media Institute Co., Ltd.,Jinan,China","Shandong HiCon New Media Institute Co., Ltd., Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong HiCon New Media Institute Co., Ltd.,Jinan,China","institution_ids":["https://openalex.org/I4210160779"]},{"raw_affiliation_string":"Shandong HiCon New Media Institute Co., Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210160779"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.484,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60402896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2563","last_page":"2568"},"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":0.9947999715805054,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748079776763916},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6898916959762573},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5587137937545776},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5383589863777161},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5376077890396118},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47492557764053345},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4747928977012634},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4737982153892517},{"id":"https://openalex.org/keywords/linear-phase","display_name":"Linear phase","score":0.4272039532661438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4129716753959656},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3758384585380554},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.31507375836372375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30074238777160645},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.2277270257472992},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20947331190109253},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15800276398658752},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1219651997089386},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09641018509864807},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09373444318771362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748079776763916},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6898916959762573},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5587137937545776},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5383589863777161},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5376077890396118},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47492557764053345},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4747928977012634},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4737982153892517},{"id":"https://openalex.org/C20610874","wikidata":"https://www.wikidata.org/wiki/Q512136","display_name":"Linear phase","level":3,"score":0.4272039532661438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4129716753959656},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3758384585380554},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31507375836372375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30074238777160645},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2277270257472992},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20947331190109253},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15800276398658752},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1219651997089386},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09641018509864807},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09373444318771362},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53654.2022.9945134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53654.2022.9945134","pdf_url":null,"source":{"id":"https://openalex.org/S4363607746","display_name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320328720","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1968939597","https://openalex.org/W2048142341","https://openalex.org/W2070126272","https://openalex.org/W2128653836","https://openalex.org/W2802304149","https://openalex.org/W2897371647","https://openalex.org/W2921144622","https://openalex.org/W2940177920","https://openalex.org/W2949558265","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2991361823","https://openalex.org/W2998832642","https://openalex.org/W3015411705","https://openalex.org/W3015910825","https://openalex.org/W3086513098","https://openalex.org/W3096893582","https://openalex.org/W3102190437","https://openalex.org/W3112318417","https://openalex.org/W3161273075","https://openalex.org/W3161950572","https://openalex.org/W3177624059","https://openalex.org/W3186301694","https://openalex.org/W4245919820","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6762114000","https://openalex.org/W6798972960"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2530685530","https://openalex.org/W2057775761","https://openalex.org/W2964074194"],"abstract_inverted_index":{"Generative":[0],"Adversarial":[1],"Networks":[2],"(GANs)":[3],"have":[4],"been":[5],"used":[6],"in":[7,18,23,43,161,168,190,227,275],"the":[8,20,24,40,53,80,86,92,104,110,116,127,140,144,147,150,163,177,186,196,199,202,216,228,231,239,255,266,271],"field":[9],"of":[10,27,49,52,91,109,115,130,133,143,201,230,243,250,257,260,277],"speech":[11,30,64,240,280],"enhancement":[12,31,65,241],"due":[13],"to":[14],"their":[15],"huge":[16],"potentials":[17],"reducing":[19,254],"noise":[21],"mixed":[22],"signals.":[25],"Most":[26],"existing":[28,272],"GAN-based":[29],"approaches":[32],"either":[33],"operate":[34],"on":[35,67,85,247],"time":[36],"domain":[37],"or":[38],"exploit":[39],"magnitude":[41],"spectra":[42],"time-frequency":[44,87,111],"domain,":[45],"but":[46,252],"lack":[47],"consideration":[48],"direct":[50],"optimization":[51],"phase.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,192],"propose":[59],"a":[60,173,234],"GAN":[61,94,244,268],"architecture":[62,95,269],"for":[63,139,149,176],"based":[66],"gated":[68],"linear":[69,174],"units":[70],"(GLUs)":[71],"and":[72,82,106,146,198,209,282],"Dual-Path":[73],"Transformers":[74],"(DPTs),":[75],"which":[76,204],"simultaneously":[77],"deals":[78],"with":[79,222,284],"amplitude":[81],"phase":[83],"information":[84],"domain.":[88],"The":[89,113,153],"generator":[90,117],"proposed":[93,267],"is":[96,118,219],"designed":[97],"following":[98],"an":[99],"autoencoder":[100],"structure":[101,218],"fed":[102],"by":[103,120,171,245],"real":[105,141],"imaginary":[107,151],"parts":[108],"frames.":[112],"encoder":[114,197],"constructed":[119],"multiple":[121,223,248],"cascaded":[122,134],"convolutional":[123,225],"GLUs":[124,136,154],"(ConvGLUs),":[125],"while":[126,179],"decoder":[128,200],"consists":[129],"two":[131],"groups":[132],"deconvolutional":[135],"(DeconvGLUs),":[137],"one":[138],"part":[142],"spectrogram":[145],"other":[148],"part.":[152],"are":[155,159],"adopted":[156],"since":[157],"they":[158],"potential":[160],"avoiding":[162],"gradient":[164],"vanishing":[165],"issue":[166],"dwelling":[167],"deep":[169],"architectures":[170],"providing":[172],"path":[175],"gradients":[178],"retaining":[180],"non-linear":[181],"capabilities.":[182],"Aiming":[183],"at":[184],"capturing":[185],"long-range":[187],"dependent":[188],"features":[189,249],"speech,":[191,251],"place":[193],"DPTs":[194],"between":[195],"generator,":[203],"contains":[205],"multi-head":[206],"attention":[207],"modules":[208],"Bi-directional":[210],"Gated":[211],"Recurrent":[212],"Units":[213],"(BiGRUs).":[214],"Moreover,":[215],"DPT":[217],"also":[220,253],"merged":[221],"one-dimensional":[224],"layers":[226],"discriminator":[229],"GAN.":[232,261],"Such":[233],"design":[235],"not":[236],"only":[237],"improves":[238],"performance":[242],"focusing":[246],"volume":[256],"model":[258],"parameters":[259],"Experimental":[262],"results":[263],"suggest":[264],"that":[265],"outperforms":[270],"benchmark":[273],"GANs":[274],"terms":[276],"both":[278],"objective":[279],"intelligibility":[281],"quality":[283],"less":[285],"computational":[286],"complexity.":[287]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}