{"id":"https://openalex.org/W4416250067","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228906","title":"SMRU-Lite: Efficient Low-Complexity Speech Enhancement Model with Uncertainty Estimation","display_name":"SMRU-Lite: Efficient Low-Complexity Speech Enhancement Model with Uncertainty Estimation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250067","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228906"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100443059","display_name":"Zhiyu Zhang","orcid":"https://orcid.org/0009-0002-4313-1759"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Zhang","raw_affiliation_strings":["Southeast University,National Mobile Communications Research Laboratory,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,National Mobile Communications Research Laboratory,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056414497","display_name":"Tong Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Lei","raw_affiliation_strings":["Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018569990","display_name":"Zhihang Sun","orcid":"https://orcid.org/0000-0002-3787-0144"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihang Sun","raw_affiliation_strings":["Tencent AI Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088185643","display_name":"Feiran Yang","orcid":"https://orcid.org/0000-0002-1734-3785"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiran Yang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Acoustics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073675630","display_name":"Rilin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rilin Chen","raw_affiliation_strings":["Tencent AI Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083864182","display_name":"Chunguo Li","orcid":"https://orcid.org/0000-0002-4689-7226"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunguo Li","raw_affiliation_strings":["Southeast University,National Mobile Communications Research Laboratory,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,National Mobile Communications Research Laboratory,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9929999709129333,"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":0.9929999709129333,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.001500000013038516,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.0010999999940395355,"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/generalization","display_name":"Generalization","score":0.7990000247955322},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.6841999888420105},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6550999879837036},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6265000104904175},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5011000037193298},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4742000102996826},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.46880000829696655}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7990000247955322},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.6841999888420105},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6326000094413757},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6265000104904175},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4706000089645386},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42419999837875366},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3578999936580658},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C94361409","wikidata":"https://www.wikidata.org/wiki/Q7882500","display_name":"Uncertainty reduction theory","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2120847449","https://openalex.org/W2121973264","https://openalex.org/W2153894152","https://openalex.org/W2289394825","https://openalex.org/W2575742305","https://openalex.org/W2603567530","https://openalex.org/W2696967604","https://openalex.org/W2803417661","https://openalex.org/W2883780447","https://openalex.org/W2889890482","https://openalex.org/W2952218014","https://openalex.org/W2991361823","https://openalex.org/W3028019732","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3164605550","https://openalex.org/W4285504888","https://openalex.org/W4306155393","https://openalex.org/W4312678820","https://openalex.org/W4362690115","https://openalex.org/W4375869460","https://openalex.org/W4375928773","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4388805985","https://openalex.org/W4392903568","https://openalex.org/W4392908343","https://openalex.org/W4406462013","https://openalex.org/W4408353997"],"related_works":[],"abstract_inverted_index":{"Although":[0],"neural":[1],"network-based":[2],"speech":[3,147],"enhancement":[4,148],"models":[5,28,122],"perform":[6],"much":[7],"better":[8],"than":[9],"their":[10,13],"traditional":[11],"counterparts,":[12],"substantial":[14],"computational":[15,63,100,125],"demands":[16],"make":[17],"it":[18,141],"challenging":[19],"for":[20,86,145],"real-time":[21,146],"applications":[22],"on":[23,47],"edge":[24],"devices.":[25],"Moreover,":[26,77],"compact":[27],"often":[29],"exhibit":[30],"weak":[31],"generalization":[32,93,135],"in":[33,62,136],"complex":[34],"and":[35,71,94],"out-of-domain":[36],"scenarios.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"an":[43,72],"efficient":[44],"model":[45,57,109,132],"based":[46],"our":[48,108,131],"previous":[49],"work":[50],"Split-and-Merge":[51],"Recurrent-based":[52],"UNet":[53],"(SMRU).":[54],"The":[55],"proposed":[56,120],"achieves":[58],"a":[59,81,142],"significant":[60],"reduction":[61],"load":[64],"through":[65],"the":[66,78,99,113],"incorporation":[67],"of":[68,80],"Skip-RNN":[69],"layers":[70],"attention-based":[73],"sub-band":[74],"compression":[75],"module.":[76],"employment":[79],"two-stage":[82],"uncertainty-driven":[83],"loss":[84],"function":[85],"aleatoric":[87],"uncertainty":[88],"capture":[89],"leads":[90],"to":[91],"enhanced":[92],"denoising":[95],"performance":[96],"without":[97],"increasing":[98],"complexity":[101],"during":[102],"inference.":[103],"Experimental":[104],"results":[105],"demonstrate":[106],"that":[107],"not":[110],"only":[111],"surpasses":[112],"original":[114],"SMRU":[115],"but":[116],"also":[117],"outperforms":[118],"recently":[119],"lightweight":[121],"with":[123],"similar":[124],"cost":[126],"(approximately":[127],"200M":[128],"MACs).":[129],"Furthermore,":[130],"exhibits":[133],"strong":[134],"cross-corpus":[137],"test":[138],"sets,":[139],"making":[140],"promising":[143],"solution":[144],"applications.":[149]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}