{"id":"https://openalex.org/W4416751162","doi":"https://doi.org/10.1109/sips66314.2025.11261303","title":"Multichannel Speech Enhancement Method Using Dilated Semi-Dense Convolutional Network","display_name":"Multichannel Speech Enhancement Method Using Dilated Semi-Dense Convolutional Network","publication_year":2025,"publication_date":"2025-11-01","ids":{"openalex":"https://openalex.org/W4416751162","doi":"https://doi.org/10.1109/sips66314.2025.11261303"},"language":null,"primary_location":{"id":"doi:10.1109/sips66314.2025.11261303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips66314.2025.11261303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Signal Processing Systems (SiPS)","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/A5079061263","display_name":"Takehiko Ueyama","orcid":"https://orcid.org/0000-0002-5647-3937"},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomohiro Ueyama","raw_affiliation_strings":["Yokohama National University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Yokohama National University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034784131","display_name":"Koichi Ichige","orcid":"https://orcid.org/0000-0001-7663-6919"},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Ichige","raw_affiliation_strings":["Yokohama National University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Yokohama National University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047485312","display_name":"Takahiro Murakami","orcid":"https://orcid.org/0000-0003-0615-9939"},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Murakami","raw_affiliation_strings":["Meiji University,Department of Electronics and Bioinformatics"],"affiliations":[{"raw_affiliation_string":"Meiji University,Department of Electronics and Bioinformatics","institution_ids":["https://openalex.org/I16656306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079061263"],"corresponding_institution_ids":["https://openalex.org/I180203408"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4754107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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":0.9940999746322632,"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":0.0026000000070780516,"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":0.0003000000142492354,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.664900004863739},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.5820000171661377},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5591999888420105},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.5159000158309937},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4745999872684479},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.39419999718666077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3928999900817871}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368000149726868},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.664900004863739},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5591999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5462999939918518},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.5159000158309937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sips66314.2025.11261303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips66314.2025.11261303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Signal Processing Systems (SiPS)","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":10,"referenced_works":["https://openalex.org/W2131968171","https://openalex.org/W2158216966","https://openalex.org/W2568308529","https://openalex.org/W2892163332","https://openalex.org/W2963446712","https://openalex.org/W2998480669","https://openalex.org/W3015191643","https://openalex.org/W3015791598","https://openalex.org/W3097777922","https://openalex.org/W4391621214"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,19,26],"dilated":[4,47,49,55],"semi-dense":[5,56],"convolutional":[6],"network":[7],"for":[8,21],"multichannel":[9],"speech":[10],"enhancement":[11],"using":[12],"machine":[13],"learning.":[14],"The":[15],"baseline,":[16],"SpatialNet,":[17],"employs":[18],"Conformer":[20],"narrowband":[22],"processing":[23],"but":[24],"uses":[25],"simple":[27],"3-layer":[28],"CNN":[29],"block,":[30],"limiting":[31],"local":[32],"information":[33],"extraction.":[34],"To":[35],"improve":[36],"performance,":[37],"we":[38],"replace":[39],"the":[40,53],"Convolutional":[41],"Neural":[42],"Network":[43],"(CNN)":[44],"block":[45],"with":[46],"convolution,":[48,51],"dense":[50],"and":[52],"proposed":[54],"convolution.":[57]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}