{"id":"https://openalex.org/W4416799501","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249030","title":"Strategic Re-Weighting of U-Net Components in Diffusion Models for Enhanced Speech Enhancement Without Retraining","display_name":"Strategic Re-Weighting of U-Net Components in Diffusion Models for Enhanced Speech Enhancement Without Retraining","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799501","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249030"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249030","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":"https://openalex.org/A5084204020","display_name":"Yuehai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuehai Zhang","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115444854","display_name":"Yang Li","orcid":"https://orcid.org/0000-0001-8132-3984"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuehao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuehao Zhao","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["Waseda University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38706096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"819","last_page":"824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9599000215530396,"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":0.9599000215530396,"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":0.012000000104308128,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.0026000000070780516,"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/speech-enhancement","display_name":"Speech enhancement","score":0.6407999992370605},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.541700005531311},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5084999799728394},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4648999869823456},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45750001072883606},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.43810001015663147},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.430400013923645},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.37470000982284546},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.37470000982284546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476000189781189},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6407999992370605},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503600001335144},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45750001072883606},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37470000982284546},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3287999927997589},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249030","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1983108229","https://openalex.org/W2516001803","https://openalex.org/W2603567530","https://openalex.org/W2606943906","https://openalex.org/W2964058413","https://openalex.org/W4221144097","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385822788","https://openalex.org/W4392903897","https://openalex.org/W4392939451","https://openalex.org/W4401609190","https://openalex.org/W4402112506","https://openalex.org/W4402715897","https://openalex.org/W4409347156"],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"generative":[1],"speech":[2,128],"enhancement":[3,129],"(SE)":[4],"leveraging":[5],"U-Net":[6,26,48],"architectures":[7],"has":[8],"garnered":[9],"significant":[10],"attention":[11],"due":[12],"to":[13,63,82],"its":[14],"outstanding":[15],"performance.":[16],"In":[17],"this":[18,92,96],"paper,":[19],"we":[20,55,94],"explore":[21],"the":[22,40,44,51,58,73,80,88,107],"inherent":[23],"potential":[24],"of":[25,47],"within":[27],"diffusion":[28,41,123],"models":[29,124],"for":[30],"SE":[31,52],"tasks,":[32],"which":[33],"can":[34,78],"substantially":[35],"improve":[36],"generation":[37],"quality":[38],"during":[39],"process.":[42],"Investigating":[43],"distinct":[45],"roles":[46],"components":[49],"in":[50],"denoising":[53],"process,":[54],"identify":[56],"that":[57,98],"main":[59],"backbone":[60,114],"primarily":[61],"contributes":[62],"denoising,":[64],"while":[65],"skip":[66,111],"connections":[67,112],"predominantly":[68],"introduce":[69,95],"high-frequency":[70],"features":[71],"into":[72,121],"decoder.":[74],"This":[75],"latter":[76],"effect":[77],"cause":[79],"network":[81],"de-emphasize":[83],"crucial":[84],"semantic":[85],"information":[86],"from":[87,109],"backbone.":[89],"Building":[90],"on":[91],"insight,":[93],"method":[97],"requires":[99],"no":[100],"retraining":[101],"or":[102],"fine-tuning.":[103],"By":[104],"strategically":[105],"re-weighting":[106],"contributions":[108],"U-Net's":[110],"and":[113,125],"feature":[115],"maps,":[116],"our":[117],"approach":[118],"seamlessly":[119],"integrates":[120],"existing":[122],"demonstrably":[126],"enhances":[127],"performance":[130],"with":[131],"minimal":[132],"code":[133],"modification.":[134]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}