{"id":"https://openalex.org/W4415971108","doi":"https://doi.org/10.1109/lsp.2025.3630096","title":"MBTU-SE: A Speech Enhancement Network Integrates Enhanced Taylor Multi-Branch Linear Transformer With U-Net Architecture","display_name":"MBTU-SE: A Speech Enhancement Network Integrates Enhanced Taylor Multi-Branch Linear Transformer With U-Net Architecture","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415971108","doi":"https://doi.org/10.1109/lsp.2025.3630096"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3630096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3630096","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5100453977","display_name":"Heng Wang","orcid":"https://orcid.org/0000-0003-0678-817X"},"institutions":[{"id":"https://openalex.org/I14116566","display_name":"Wuhan Polytechnic University","ror":"https://ror.org/05w0e5j23","country_code":"CN","type":"education","lineage":["https://openalex.org/I14116566"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Wang","raw_affiliation_strings":["School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0678-817X","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China","institution_ids":["https://openalex.org/I14116566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367816","display_name":"Chenglong Wang","orcid":"https://orcid.org/0009-0001-8397-3881"},"institutions":[{"id":"https://openalex.org/I14116566","display_name":"Wuhan Polytechnic University","ror":"https://ror.org/05w0e5j23","country_code":"CN","type":"education","lineage":["https://openalex.org/I14116566"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Wang","raw_affiliation_strings":["School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0001-8397-3881","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China","institution_ids":["https://openalex.org/I14116566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634478","display_name":"Xueting Wang","orcid":"https://orcid.org/0009-0008-3510-7031"},"institutions":[{"id":"https://openalex.org/I14116566","display_name":"Wuhan Polytechnic University","ror":"https://ror.org/05w0e5j23","country_code":"CN","type":"education","lineage":["https://openalex.org/I14116566"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueting Wang","raw_affiliation_strings":["School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0008-3510-7031","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China","institution_ids":["https://openalex.org/I14116566"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Yu","orcid":"https://orcid.org/0009-0002-6668-6474"},"institutions":[{"id":"https://openalex.org/I14116566","display_name":"Wuhan Polytechnic University","ror":"https://ror.org/05w0e5j23","country_code":"CN","type":"education","lineage":["https://openalex.org/I14116566"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yu","raw_affiliation_strings":["School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0002-6668-6474","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China","institution_ids":["https://openalex.org/I14116566"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yimin Jiang","orcid":"https://orcid.org/0009-0004-6704-4603"},"institutions":[{"id":"https://openalex.org/I14116566","display_name":"Wuhan Polytechnic University","ror":"https://ror.org/05w0e5j23","country_code":"CN","type":"education","lineage":["https://openalex.org/I14116566"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimin Jiang","raw_affiliation_strings":["School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0004-6704-4603","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer, Wuhan Polytechnic University, Wuhan, China","institution_ids":["https://openalex.org/I14116566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35800536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"4309","last_page":"4313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919000267982483,"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":0.9919000267982483,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.0010000000474974513,"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/softmax-function","display_name":"Softmax function","score":0.6783000230789185},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6330000162124634},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5802000164985657},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5666000247001648},{"id":"https://openalex.org/keywords/taylor-series","display_name":"Taylor series","score":0.5295000076293945},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5242999792098999},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.45249998569488525},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38370001316070557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283999919891357},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6783000230789185},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6330000162124634},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5802000164985657},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5666000247001648},{"id":"https://openalex.org/C158946198","wikidata":"https://www.wikidata.org/wiki/Q131187","display_name":"Taylor series","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5242999792098999},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41519999504089355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32600000500679016},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.304500013589859},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C160824197","wikidata":"https://www.wikidata.org/wiki/Q2071054","display_name":"Linear approximation","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3630096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3630096","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":30,"referenced_works":["https://openalex.org/W2094721231","https://openalex.org/W2937484199","https://openalex.org/W2940275453","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W3015278429","https://openalex.org/W3158779859","https://openalex.org/W3161950572","https://openalex.org/W3162493033","https://openalex.org/W3194523157","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3211438798","https://openalex.org/W3213188934","https://openalex.org/W4221143458","https://openalex.org/W4221162870","https://openalex.org/W4225288502","https://openalex.org/W4225309689","https://openalex.org/W4245919820","https://openalex.org/W4296068985","https://openalex.org/W4296069272","https://openalex.org/W4312642508","https://openalex.org/W4324092848","https://openalex.org/W4385807442","https://openalex.org/W4387042228","https://openalex.org/W4390872931","https://openalex.org/W4395447416","https://openalex.org/W4398138244","https://openalex.org/W4402112274","https://openalex.org/W4409326045"],"related_works":[],"abstract_inverted_index":{"Achieving":[0],"high-performance":[1],"speech":[2,17,74],"enhancement":[3,18],"with":[4,60,105],"low":[5],"computational":[6],"cost":[7],"remains":[8],"challenging.":[9],"This":[10],"paper":[11],"proposes":[12],"MBTU-SE,":[13],"a":[14,55,101],"lightweight":[15,110],"novel":[16],"network":[19],"based":[20],"on":[21],"the":[22],"U-Net":[23],"architecture.":[24],"It":[25],"approximates":[26],"Softmax":[27],"attention":[28,84],"via":[29],"Taylor":[30,58,80,90],"expansion,":[31],"employs":[32],"norm-preserving":[33],"mapping":[34],"for":[35],"first-order":[36],"residuals,":[37],"and":[38,64,93,112],"adopts":[39],"multi-branch":[40,56,78],"parallelism":[41],"to":[42,45,69,73,85],"reduce":[43],"complexity":[44],"linear":[46,57,79],"levels":[47],"while":[48],"maintaining":[49],"high":[50,113],"performance.":[51,114],"Key":[52],"innovations":[53],"include":[54],"Transformer":[59,81],"multi-scale":[61,65,94],"patch":[62],"embedding":[63,67],"deformable":[66],"(MDE)":[68],"adapt":[70],"receptive":[71],"fields":[72],"features.":[75],"The":[76],"improved":[77],"(IMLT)":[82],"enhances":[83],"key":[86],"regions":[87],"through":[88],"refined":[89],"residual":[91],"approximation":[92],"group":[95],"convolution.":[96],"On":[97],"VoiceBank+DEMAND,":[98],"MBTU-SE":[99],"achieves":[100],"PESQ":[102],"of":[103],"3.39":[104],"only":[106],"0.40M":[107],"parameters,":[108],"balancing":[109],"design":[111]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-06T00:00:00"}