{"id":"https://openalex.org/W4416798658","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249415","title":"Speech Enhancement Network with Windowed Cross Attention Using Noise-Reference Microphone","display_name":"Speech Enhancement Network with Windowed Cross Attention Using Noise-Reference Microphone","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798658","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249415"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Kota Suzuki","orcid":null},"institutions":[{"id":"https://openalex.org/I72253084","display_name":"Saitama University","ror":"https://ror.org/02evnh647","country_code":"JP","type":"education","lineage":["https://openalex.org/I72253084"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kota Suzuki","raw_affiliation_strings":["Saitama University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saitama University,Japan","institution_ids":["https://openalex.org/I72253084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110654558","display_name":"Yosuke Sugiura","orcid":null},"institutions":[{"id":"https://openalex.org/I72253084","display_name":"Saitama University","ror":"https://ror.org/02evnh647","country_code":"JP","type":"education","lineage":["https://openalex.org/I72253084"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Sugiura","raw_affiliation_strings":["Saitama University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saitama University,Japan","institution_ids":["https://openalex.org/I72253084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036337826","display_name":"Tetsuya Shimamura","orcid":"https://orcid.org/0000-0002-7874-3467"},"institutions":[{"id":"https://openalex.org/I72253084","display_name":"Saitama University","ror":"https://ror.org/02evnh647","country_code":"JP","type":"education","lineage":["https://openalex.org/I72253084"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Shimamura","raw_affiliation_strings":["Saitama University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saitama University,Japan","institution_ids":["https://openalex.org/I72253084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I72253084"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38504239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"891","last_page":"896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9940000176429749,"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":0.9940000176429749,"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":0.002199999988079071,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0010000000474974513,"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/microphone","display_name":"Microphone","score":0.8465999960899353},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8062999844551086},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6654000282287598},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5550000071525574},{"id":"https://openalex.org/keywords/noise-canceling-microphone","display_name":"Noise-canceling microphone","score":0.39329999685287476},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3465999960899353},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8465999960899353},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8062999844551086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6747000217437744},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6654000282287598},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6035000085830688},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4099000096321106},{"id":"https://openalex.org/C36922181","wikidata":"https://www.wikidata.org/wiki/Q7047650","display_name":"Noise-canceling microphone","level":5,"score":0.39329999685287476},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":19,"referenced_works":["https://openalex.org/W2067295501","https://openalex.org/W2144404214","https://openalex.org/W2286130239","https://openalex.org/W2514828952","https://openalex.org/W2889442120","https://openalex.org/W2964058413","https://openalex.org/W3015791598","https://openalex.org/W3032514799","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3160085755","https://openalex.org/W3197627016","https://openalex.org/W3198511309","https://openalex.org/W3205770165","https://openalex.org/W4232282348","https://openalex.org/W4312219134","https://openalex.org/W4312993501","https://openalex.org/W4385486126","https://openalex.org/W4408352009"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"propose":[4],"an":[5],"enhancement":[6,11],"to":[7,31],"a":[8,15,25,37,44,53,65,76,84],"multichannel":[9],"speech":[10,42,95],"network":[12],"that":[13],"leverages":[14],"noisereference":[16],"microphone.":[17],"Our":[18],"primary":[19,38],"contribution":[20],"is":[21],"the":[22],"introduction":[23],"of":[24,56,93],"Windowed":[26],"Cross-Attention":[27],"(WCA)":[28,60],"mechanism,":[29],"designed":[30],"more":[32],"effectively":[33],"fuse":[34],"features":[35],"from":[36],"microphone":[39,46],"capturing":[40,47],"mixed":[41],"and":[43,75,102],"secondary":[45],"environmental":[48],"noise.":[49],"This":[50],"paper":[51],"presents":[52],"comparative":[54],"evaluation":[55],"our":[57,70],"proposed":[58],"method":[59,90],"against":[61],"several":[62],"baseline":[63],"architectures:":[64],"standard":[66],"multi-channel":[67],"DEMUCS":[68],"(DEMUCS-m),":[69],"prior":[71],"noise-fusion":[72],"architecture":[73],"(DEMUCS-prop),":[74],"deep":[77],"non-linear":[78],"filter":[79],"(DNLF).":[80],"Experiments":[81],"conducted":[82],"in":[83,91],"simulated":[85],"acoustic":[86],"space":[87],"assess":[88],"each":[89],"terms":[92],"objective":[94],"quality":[96],"metrics,":[97],"followed":[98],"by":[99],"detailed":[100],"analysis":[101],"discussion.":[103]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}