{"id":"https://openalex.org/W4411635572","doi":"https://doi.org/10.1145/3731715.3733391","title":"MixSENet: A Lightweight Model for Speech Enhancement with Multi-Scale Features and Contextual Modeling","display_name":"MixSENet: A Lightweight Model for Speech Enhancement with Multi-Scale Features and Contextual Modeling","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635572","doi":"https://doi.org/10.1145/3731715.3733391"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5114537211","display_name":"Chuike Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ChuiKe Kong","raw_affiliation_strings":["College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0002-1926-5116","affiliations":[{"raw_affiliation_string":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078942180","display_name":"Guangcun Wei","orcid":"https://orcid.org/0000-0002-5461-8901"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangcun Wei","raw_affiliation_strings":["College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0002-5461-8901","affiliations":[{"raw_affiliation_string":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuo Li","orcid":"https://orcid.org/0009-0007-8684-2450"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Li","raw_affiliation_strings":["College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0007-8684-2450","affiliations":[{"raw_affiliation_string":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Penghao Ma","orcid":"https://orcid.org/0009-0004-5267-5111"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Penghao Ma","raw_affiliation_strings":["College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0004-5267-5111","affiliations":[{"raw_affiliation_string":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"last","author":{"id":null,"display_name":"Changhao Li","orcid":"https://orcid.org/0000-0003-3774-2262"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhao Li","raw_affiliation_strings":["College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0003-3774-2262","affiliations":[{"raw_affiliation_string":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I80143920"],"apc_list":null,"apc_paid":null,"fwci":1.5078,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78923673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"625","last_page":"633"},"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":0.9976999759674072,"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":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.744050920009613},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5763547420501709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5451582670211792},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49136725068092346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3275200128555298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744050920009613},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5763547420501709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5451582670211792},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49136725068092346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3275200128555298},{"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":1,"locations":[{"id":"doi:10.1145/3731715.3733391","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2603567530","https://openalex.org/W2921144622","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2971458685","https://openalex.org/W3015197852","https://openalex.org/W3097945073","https://openalex.org/W3134695619","https://openalex.org/W3141443761","https://openalex.org/W3158779859","https://openalex.org/W3161950572","https://openalex.org/W3175083350","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3206809722","https://openalex.org/W3212231398","https://openalex.org/W4221145205","https://openalex.org/W4225298533","https://openalex.org/W4225309689","https://openalex.org/W4288391450","https://openalex.org/W4292946916","https://openalex.org/W4296068416","https://openalex.org/W4312271884","https://openalex.org/W4385486090","https://openalex.org/W4385822368","https://openalex.org/W4385822478","https://openalex.org/W4390872931","https://openalex.org/W4402112274","https://openalex.org/W4402351638"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,47,54,119],"novel":[6],"lightweight":[7],"speech":[8,28],"enhancement":[9],"network,":[10],"MixSENet":[11,106],"(Mixed":[12],"Structure":[13],"Speech":[14],"Enhancement":[15],"Network),":[16],"designed":[17],"to":[18],"address":[19],"the":[20,41,84,112],"challenges":[21],"associated":[22],"with":[23,32,98,118],"multi-scale":[24,55,76],"feature":[25,77],"processing":[26],"of":[27,53,122],"signals":[29],"and":[30,44,62,75,92,128,146],"coping":[31,97],"complex":[33],"noise":[34,100],"environments.":[35],"The":[36,69,131],"network":[37],"is":[38],"based":[39],"on":[40,111],"U-Net":[42],"architecture":[43],"innovatively":[45],"introduces":[46],"hybrid":[48],"structural":[49],"block,":[50],"which":[51],"consists":[52],"parallel":[56,65,80],"large":[57,72],"convolutional":[58],"kernel":[59],"module":[60,67],"(MSPLCK)":[61],"an":[63],"enhanced":[64],"attention":[66],"(EPAM).":[68],"MSPLCK":[70],"achieves":[71],"sensory":[73],"fields":[74],"extraction":[78],"through":[79],"dilated":[81],"convolution,":[82],"whereas":[83],"EPAM":[85],"can":[86],"simultaneously":[87],"process":[88],"global":[89],"shared":[90],"information":[91],"local":[93],"time-frequency":[94],"features":[95],"effectively":[96],"uneven":[99],"distributions.":[101],"Extensive":[102],"experiments":[103],"demonstrate":[104],"that":[105],"shows":[107],"significant":[108],"performance":[109],"advantages":[110],"Voice":[113],"Bank":[114],"+":[115],"DEMAND":[116],"dataset,":[117],"parameter":[120],"count":[121],"only":[123],"0.43M,":[124],"significantly":[125],"reducing":[126],"training":[127],"deployment":[129],"costs.":[130],"method":[132],"has":[133],"substantial":[134],"practical":[135],"value":[136],"in":[137],"real":[138],"application":[139],"scenarios,":[140],"especially":[141],"for":[142],"resource-constrained":[143],"mobile":[144],"devices":[145],"embedded":[147],"systems.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}