{"id":"https://openalex.org/W4319862661","doi":"https://doi.org/10.1109/slt54892.2023.10023439","title":"Adaptive-FSN: Integrating Full-Band Extraction and Adaptive Sub-Band Encoding for Monaural Speech Enhancement","display_name":"Adaptive-FSN: Integrating Full-Band Extraction and Adaptive Sub-Band Encoding for Monaural Speech Enhancement","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862661","doi":"https://doi.org/10.1109/slt54892.2023.10023439"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023439","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5079433604","display_name":"Yu-sheng Tsao","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-sheng Tsao","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering","Department of Computer Science and Information Engineering, National Taiwan Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088927394","display_name":"Kuan-Hsun Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Hsun Ho","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering","Department of Computer Science and Information Engineering, National Taiwan Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-weih Hung","raw_affiliation_strings":["National Chi Nan University,Department of Electrical Engineering","Department of Electrical Engineering, National Chi Nan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Department of Electrical Engineering","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053222355","display_name":"Berlin Chen","orcid":"https://orcid.org/0000-0003-0693-8932"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Department of Computer Science and Information Engineering","Department of Computer Science and Information Engineering, National Taiwan Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Department of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan Normal University","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2083,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79486879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"458","last_page":"464"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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/T11309","display_name":"Music and Audio Processing","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7310041785240173},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45202091336250305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43627840280532837},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4124959707260132},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3340991735458374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7310041785240173},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45202091336250305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43627840280532837},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4124959707260132},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3340991735458374}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023439","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W2141411743","https://openalex.org/W2291877678","https://openalex.org/W2603567530","https://openalex.org/W2952218014","https://openalex.org/W2963750251","https://openalex.org/W2990433241","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W3015197852","https://openalex.org/W3096408984","https://openalex.org/W3097777922","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3158779859","https://openalex.org/W3160085755","https://openalex.org/W3198680319","https://openalex.org/W4221149546","https://openalex.org/W4225309689","https://openalex.org/W4233392025","https://openalex.org/W4296069347","https://openalex.org/W4385245566","https://openalex.org/W6770796734","https://openalex.org/W6796651418","https://openalex.org/W6810502683"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871"],"abstract_inverted_index":{"An":[0],"important":[1],"more":[2],"recent":[3],"thread":[4],"of":[5,28,52,70,95,144],"speech":[6,39],"enhancement":[7,40],"work":[8],"is":[9],"to":[10,42,61,103,118],"utilize":[11],"fine-grinded":[12],"local":[13],"spectral":[14,30,106],"patterns":[15],"with":[16,80,99],"sub-band":[17,29,46,53,63,71,78],"processing":[18,64],"that":[19,65,134],"complement":[20],"full-band":[21,90,101],"features":[22],"nicely.":[23],"To":[24],"extend":[25],"the":[26,89,96,114,120,129,142,149],"efficacy":[27],"information,":[31],"we":[32,74,92],"propose":[33],"Adaptive-FSN,":[34],"a":[35,45,49,67,81,109],"fully":[36],"convolutional":[37],"real-time":[38,154],"framework,":[41],"dynamically":[43],"acquire":[44],"embedding":[47,79],"within":[48],"wide":[50,68],"range":[51,69],"frequencies.":[54],"We":[55],"exploit":[56],"an":[57],"adaptive":[58],"subband":[59],"encoder":[60],"portray":[62],"encapsulates":[66],"units.":[72],"Then":[73],"build":[75],"this":[76,135],"effective":[77],"Conformer-based":[82,110],"structure":[83],"and":[84,147],"multi-view":[85],"attention.":[86],"As":[87],"for":[88,152],"features,":[91],"make":[93],"use":[94],"FullSubNet+":[97,139],"architecture":[98],"its":[100],"extractor":[102],"get":[104],"global":[105],"information.":[107],"Finally,":[108],"fusion":[111],"model":[112],"combines":[113],"above":[115],"information":[116],"sources":[117],"predict":[119],"complex":[121],"ideal":[122],"ratio":[123],"mask":[124],"(cIRM).":[125],"Experimental":[126],"results":[127],"on":[128],"VoiceBank-DEMAND":[130],"benchmark":[131],"task":[132],"reveal":[133],"novel":[136],"framework":[137],"outperforms":[138],"by":[140],"promoting":[141],"quality":[143],"processed":[145],"utterances":[146],"reducing":[148],"implementation":[150],"complexity":[151],"faster":[153],"computation.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}