{"id":"https://openalex.org/W4408345858","doi":"https://doi.org/10.1109/icassp49660.2025.10888248","title":"Causal Speech Enhancement Based on a Two-Branch Nested U-Net Architecture Using Self-Supervised Speech Embeddings","display_name":"Causal Speech Enhancement Based on a Two-Branch Nested U-Net Architecture Using Self-Supervised Speech Embeddings","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345858","doi":"https://doi.org/10.1109/icassp49660.2025.10888248"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5109678218","display_name":"Seorim Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seorim Hwang","raw_affiliation_strings":["Yonsei Univ.,ISP Lab.,Wonju,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei Univ.,ISP Lab.,Wonju,Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703900","display_name":"Sung Wook Park","orcid":"https://orcid.org/0000-0001-8151-6663"},"institutions":[{"id":"https://openalex.org/I133533813","display_name":"Gangneung\u2013Wonju National University","ror":"https://ror.org/0461cvh40","country_code":"KR","type":"education","lineage":["https://openalex.org/I133533813"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung Wook Park","raw_affiliation_strings":["Gangneung-Wonju National Univ.,Gangneung,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gangneung-Wonju National Univ.,Gangneung,Korea","institution_ids":["https://openalex.org/I133533813"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070511148","display_name":"Young-Cheol Park","orcid":"https://orcid.org/0000-0001-6275-4957"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngcheol Park","raw_affiliation_strings":["Yonsei Univ.,ISP Lab.,Wonju,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei Univ.,ISP Lab.,Wonju,Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72126509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9923999905586243,"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":0.9923999905586243,"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":0.9715999960899353,"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":0.6949267387390137},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6069937944412231},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5333312153816223},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4404022693634033},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4326234757900238},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.41447755694389343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38341787457466125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.340131938457489},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18286871910095215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949267387390137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6069937944412231},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5333312153816223},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4404022693634033},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4326234757900238},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.41447755694389343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38341787457466125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.340131938457489},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18286871910095215},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":35,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1860981223","https://openalex.org/W1952824372","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2398042854","https://openalex.org/W2550397165","https://openalex.org/W2603567530","https://openalex.org/W2940275453","https://openalex.org/W3025800305","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3120336970","https://openalex.org/W3161480375","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213188934","https://openalex.org/W4210484003","https://openalex.org/W4221143458","https://openalex.org/W4224917453","https://openalex.org/W4225905067","https://openalex.org/W4281659178","https://openalex.org/W4296068996","https://openalex.org/W4297841357","https://openalex.org/W4372270323","https://openalex.org/W4375868880","https://openalex.org/W4375869009","https://openalex.org/W4385823072","https://openalex.org/W4385823298","https://openalex.org/W4387587611","https://openalex.org/W4392903057","https://openalex.org/W4392903736","https://openalex.org/W6757632829","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2981428355","https://openalex.org/W1834994814"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,11,20,30],"causal":[4,139],"speech":[5,27,33,50,55,67],"enhancement":[6],"(SE)":[7],"model":[8,59,90,113],"based":[9],"on":[10,100],"complex":[12,46,54],"two-branch":[13],"nested":[14],"U-Net":[15],"architecture":[16,40],"(CNUNet-TB)":[17],"combined":[18],"with":[19,69,129],"two-stage":[21],"(TS)":[22],"training":[23],"method":[24],"that":[25,119],"leverages":[26],"embeddings":[28,68],"from":[29],"large":[31],"self-supervised":[32,66],"representation":[34],"learning":[35],"(SRL)":[36],"model.":[37],"The":[38,57,142],"proposed":[39,121],"improves":[41],"performance":[42,135],"by":[43,63],"simultaneously":[44],"estimating":[45],"masks":[47],"and":[48,106,144],"the":[49,65,70,79,85,88,101,108,111,120,125],"spectrum,":[51],"effectively":[52,123],"handling":[53],"data.":[56],"SE":[58,89,140],"is":[60,91],"initially":[61],"trained":[62,92],"fusing":[64],"model\u2019s":[71],"latent":[72,96,127],"vectors,":[73],"which":[74],"are":[75,147],"then":[76],"stored":[77,126],"for":[78,110],"second":[80,86],"stage":[81],"of":[82],"training.":[83],"In":[84],"stage,":[87],"to":[93,137],"replicate":[94],"these":[95],"vectors":[97,128],"without":[98],"relying":[99],"SRL":[102,112],"model,":[103],"ensuring":[104],"causality":[105],"eliminating":[107],"need":[109],"during":[114],"inference.":[115],"Experimental":[116],"results":[117],"demonstrate":[118],"CNUNet-TB-TS":[122],"replicates":[124],"strong":[130],"speaker":[131],"representation,":[132],"achieving":[133],"superior":[134],"compared":[136],"recent":[138],"models.":[141],"codes":[143],"demo":[145],"samples":[146],"available":[148],"at":[149],"https://github.com/seorim0/SEusing-SRL-model.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}