{"id":"https://openalex.org/W7076052962","doi":"https://doi.org/10.1109/tce.2025.3598007","title":"Lightweight Adaptive Deep Learning for Efficient Real-Time Speech Enhancement on Edge Devices","display_name":"Lightweight Adaptive Deep Learning for Efficient Real-Time Speech Enhancement on Edge Devices","publication_year":2025,"publication_date":"2025-08-15","ids":{"openalex":"https://openalex.org/W7076052962","doi":"https://doi.org/10.1109/tce.2025.3598007"},"language":"en","primary_location":{"id":"doi:10.1109/tce.2025.3598007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3598007","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Transactions on Consumer Electronics","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":"Fazal E. Wahab","orcid":"https://orcid.org/0000-0003-4827-170X"},"institutions":[{"id":"https://openalex.org/I4210122157","display_name":"Hubei Polytechnic University","ror":"https://ror.org/01z07eq06","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210122157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fazal E. Wahab","raw_affiliation_strings":["School of Electrical Engineering, Hubei Polytechnic University, Huangshi, China"],"raw_orcid":"https://orcid.org/0000-0003-4827-170X","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Hubei Polytechnic University, Huangshi, China","institution_ids":["https://openalex.org/I4210122157"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhongfu Ye","orcid":"https://orcid.org/0000-0002-3207-2258"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfu Ye","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3207-2258","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nasir Saleem","orcid":"https://orcid.org/0000-0003-0010-0629"},"institutions":[{"id":"https://openalex.org/I251738","display_name":"Edinburgh Napier University","ror":"https://ror.org/03zjvnn91","country_code":"GB","type":"education","lineage":["https://openalex.org/I251738"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nasir Saleem","raw_affiliation_strings":["School of Computing, Edinburgh Napier University, Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0003-0010-0629","affiliations":[{"raw_affiliation_string":"School of Computing, Edinburgh Napier University, Edinburgh, U.K","institution_ids":["https://openalex.org/I251738"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sami Bourouis","orcid":"https://orcid.org/0000-0002-6638-7039"},"institutions":[{"id":"https://openalex.org/I179331831","display_name":"Taif University","ror":"https://ror.org/014g1a453","country_code":"SA","type":"education","lineage":["https://openalex.org/I179331831"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sami Bourouis","raw_affiliation_strings":["Department of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-6638-7039","affiliations":[{"raw_affiliation_string":"Department of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia","institution_ids":["https://openalex.org/I179331831"]}]},{"author_position":"last","author":{"id":null,"display_name":"Amir Hussain","orcid":"https://orcid.org/0000-0002-8080-082X"},"institutions":[{"id":"https://openalex.org/I251738","display_name":"Edinburgh Napier University","ror":"https://ror.org/03zjvnn91","country_code":"GB","type":"education","lineage":["https://openalex.org/I251738"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amir Hussain","raw_affiliation_strings":["School of Computing, Edinburgh Napier University, Edinburgh, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8080-082X","affiliations":[{"raw_affiliation_string":"School of Computing, Edinburgh Napier University, Edinburgh, U.K","institution_ids":["https://openalex.org/I251738"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.3225,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.97965358,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"71","issue":"4","first_page":"12086","last_page":"12095"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10290","display_name":"Pregnancy and preeclampsia studies","score":0.13449999690055847,"subfield":{"id":"https://openalex.org/subfields/2729","display_name":"Obstetrics and Gynecology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10290","display_name":"Pregnancy and preeclampsia studies","score":0.13449999690055847,"subfield":{"id":"https://openalex.org/subfields/2729","display_name":"Obstetrics and Gynecology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10978","display_name":"Prenatal Screening and Diagnostics","score":0.12240000069141388,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12587","display_name":"Gestational Trophoblastic Disease Studies","score":0.0794999971985817,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.683899998664856},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6071000099182129},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5778999924659729},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5256999731063843},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5116999745368958},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5073000192642212},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.48669999837875366},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.47609999775886536},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.47110000252723694},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4214000105857849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925000190734863},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.683899998664856},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6071000099182129},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5778999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5443999767303467},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5073000192642212},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4982999861240387},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.48669999837875366},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.47110000252723694},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.40610000491142273},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C30108884","wikidata":"https://www.wikidata.org/wiki/Q1242761","display_name":"Edge enhancement","level":4,"score":0.32820001244544983},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.27810001373291016},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tce.2025.3598007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2025.3598007","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"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 Transactions on Consumer Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1873316470","display_name":null,"funder_award_id":"EP/T021063/1 (COGMHEAR)","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G1957532387","display_name":null,"funder_award_id":"EP/T024917/1 (NATGEN)","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2325509780","display_name":null,"funder_award_id":"TU-DSPP-2024-60","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2899232937","display_name":"\u57fa\u4e8e\u9ea6\u514b\u98ce\u9635\u5217\u7684\u667a\u80fd\u4f1a\u8bae\u8f6c\u5199\u8bb0\u5f55\u7cfb\u7edf\u4e2d\u7684\u8bed\u97f3\u589e\u5f3a\u95ee\u9898\u7814\u7a76","funder_award_id":"61671418","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"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2024490156","https://openalex.org/W2044893557","https://openalex.org/W2168379380","https://openalex.org/W2364134690","https://openalex.org/W2603567530","https://openalex.org/W2678916739","https://openalex.org/W2889442120","https://openalex.org/W2892009249","https://openalex.org/W2937484199","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2972818416","https://openalex.org/W2991361823","https://openalex.org/W2998445964","https://openalex.org/W3096408984","https://openalex.org/W3097681199","https://openalex.org/W3129077738","https://openalex.org/W3158779859","https://openalex.org/W3160129476","https://openalex.org/W3161950572","https://openalex.org/W3162493033","https://openalex.org/W3163652268","https://openalex.org/W3175083350","https://openalex.org/W3196543311","https://openalex.org/W3198680319","https://openalex.org/W3205770165","https://openalex.org/W3206809722","https://openalex.org/W3211408542","https://openalex.org/W3212231398","https://openalex.org/W3213188934","https://openalex.org/W4210481535","https://openalex.org/W4221143458","https://openalex.org/W4221149441","https://openalex.org/W4221149546","https://openalex.org/W4224917453","https://openalex.org/W4285119904","https://openalex.org/W4312271884","https://openalex.org/W4313174479","https://openalex.org/W4321488355","https://openalex.org/W4324291023","https://openalex.org/W4365420402","https://openalex.org/W4372260250","https://openalex.org/W4379057630","https://openalex.org/W4385245566","https://openalex.org/W4387026472","https://openalex.org/W4387250101","https://openalex.org/W4388805985","https://openalex.org/W4391002282","https://openalex.org/W4391582585","https://openalex.org/W4392523452","https://openalex.org/W4394730920","https://openalex.org/W4396243243","https://openalex.org/W4401720677","https://openalex.org/W4403144036","https://openalex.org/W4404721291","https://openalex.org/W4405310604"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"has":[2],"significantly":[3],"advanced":[4],"speech":[5,15,200],"enhancement":[6,201],"(SE)":[7],"by":[8],"exploiting":[9],"hierarchical":[10],"representations":[11],"to":[12,28,42,50,90,125,136,146,155],"model":[13,95,171],"complex":[14],"patterns.":[16],"However,":[17],"deploying":[18],"these":[19,92],"models":[20,59],"on":[21,87,163,206],"resource-constrained":[22],"edge":[23,75,88,207],"devices":[24,89],"remains":[25],"challenging":[26],"due":[27,41],"computational":[29,115,160],"limitations":[30],"and":[31,70,105,150,159,181,190],"real-time":[32,111,192,204],"processing":[33],"requirements.":[34],"Convolutional":[35],"neural":[36],"networks":[37],"(CNNs)":[38],"face":[39],"challenges":[40],"frequency":[43,121,134],"translation":[44,127],"equivariance,":[45,128],"which":[46],"reduces":[47],"their":[48],"sensitivity":[49],"frequency-specific":[51],"features":[52],"essential":[53],"for":[54,73,85,203],"speech-noise":[55],"separation.":[56],"Transformer-based":[57],"SE":[58,86,174],"are":[60,67],"effective":[61],"at":[62],"capturing":[63],"global":[64],"dependencies":[65],"but":[66],"computationally":[68],"expensive":[69],"less":[71],"suitable":[72,202],"low-latency":[74],"processing.":[76],"This":[77],"study":[78],"proposes":[79],"an":[80,151],"efficient":[81],"encoder-decoder":[82],"architecture":[83],"optimized":[84],"address":[91],"challenges.":[93],"The":[94,117,140],"integrates":[96],"adaptive":[97,120],"frequency-aware":[98],"gated":[99,130],"convolution":[100,131],"(AFAGC)":[101],"in":[102],"the":[103,164,169],"encoder":[104,118],"a":[106,177,191],"Ginformer-based":[107,141],"bottleneck,":[108],"ensuring":[109],"robust":[110],"performance":[112],"with":[113],"minimal":[114],"overhead.":[116],"incorporates":[119],"band":[122],"positional":[123],"encoding":[124],"mitigate":[126],"while":[129],"selectively":[132],"reweights":[133],"components":[135],"emphasize":[137],"speech-relevant":[138],"features.":[139],"bottleneck":[142],"uses":[143],"low-rank":[144],"projections":[145],"reduce":[147],"self-attention":[148],"complexity":[149],"SRU-based":[152],"temporal":[153],"gating":[154],"enhance":[156],"noise":[157],"adaptation":[158],"efficiency.":[161],"Evaluation":[162],"VoiceBank+DEMAND":[165],"dataset":[166],"demonstrates":[167],"that":[168],"proposed":[170],"outperforms":[172],"recent":[173],"models,":[175],"achieving":[176],"PESQ":[178],"of":[179,183,195],"3.25":[180],"STOI":[182],"95.5%.":[184],"With":[185],"only":[186],"1.32":[187],"million":[188],"parameters":[189],"factor":[193],"(RTF)":[194],"0.14,":[196],"it":[197],"delivers":[198],"high-quality":[199],"deployment":[205],"devices.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}