{"id":"https://openalex.org/W3134064908","doi":"https://doi.org/10.23919/eusipco54536.2021.9616114","title":"Towards speech enhancement using a variational U-Net architecture","display_name":"Towards speech enhancement using a variational U-Net architecture","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3134064908","doi":"https://doi.org/10.23919/eusipco54536.2021.9616114","mag":"3134064908"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616114","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616114","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5062468278","display_name":"Eike J. Nustede","orcid":"https://orcid.org/0000-0003-2475-4125"},"institutions":[{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Eike J. Nustede","raw_affiliation_strings":["Dept. med. Physics & Acoustics and Cluster of Excellence Hearing4all, Carl von Ossietzky University Oldenburg, Computational Audition Group, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Dept. med. Physics & Acoustics and Cluster of Excellence Hearing4all, Carl von Ossietzky University Oldenburg, Computational Audition Group, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009092572","display_name":"J\u00f6rn Anem\u00fcller","orcid":"https://orcid.org/0000-0001-5564-5795"},"institutions":[{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorn Anemuller","raw_affiliation_strings":["Dept. med. Physics & Acoustics and Cluster of Excellence Hearing4all, Carl von Ossietzky University Oldenburg, Computational Audition Group, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Dept. med. Physics & Acoustics and Cluster of Excellence Hearing4all, Carl von Ossietzky University Oldenburg, Computational Audition Group, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210144375"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062468278"],"corresponding_institution_ids":["https://openalex.org/I4210144375"],"apc_list":null,"apc_paid":null,"fwci":0.8608,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76819407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"485"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7020516991615295},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6577486395835876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6518995761871338},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.518784761428833},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4412727952003479},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41545969247817993},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41067802906036377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3902961015701294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37166768312454224},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1509608030319214}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7020516991615295},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6577486395835876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6518995761871338},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.518784761428833},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4412727952003479},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41545969247817993},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41067802906036377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3902961015701294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37166768312454224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1509608030319214},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616114","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616114","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G315342548","display_name":null,"funder_award_id":"352015383,SFB 1330/B3","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W1992475611","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2121061347","https://openalex.org/W2290548146","https://openalex.org/W2405774341","https://openalex.org/W2531409750","https://openalex.org/W2928988674","https://openalex.org/W2947592434","https://openalex.org/W2952218014","https://openalex.org/W2962946126","https://openalex.org/W2962963674","https://openalex.org/W2963452667","https://openalex.org/W2963632741","https://openalex.org/W2964058413","https://openalex.org/W2973133192","https://openalex.org/W3016120385","https://openalex.org/W3091830790","https://openalex.org/W3099330747","https://openalex.org/W3115341864","https://openalex.org/W4288346058","https://openalex.org/W4288374759","https://openalex.org/W4297791576","https://openalex.org/W6640963894","https://openalex.org/W6751512325","https://openalex.org/W6752558437","https://openalex.org/W6760867498"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"We":[0,42],"investigate":[1],"the":[2,31,44,52,93,98,120,158,163],"viability":[3],"of":[4,11,46,61,119,137,153],"a":[5,47,102],"variational":[6,122,159],"U-Net":[7,54,123,160],"architecture":[8,55,124],"for":[9,56,104],"denoising":[10],"single-channel":[12],"audio":[13,76],"data.":[14],"Deep":[15],"network":[16,64,167],"speech":[17],"enhancement":[18,132],"systems":[19],"commonly":[20],"aim":[21],"to":[22,28,150,162],"estimate":[23],"filter":[24,110],"masks,":[25],"or":[26],"opt":[27],"work":[29],"on":[30,75,115],"waveform":[32],"signal,":[33],"potentially":[34],"neglecting":[35],"relationships":[36],"across":[37],"higher":[38],"dimensional":[39],"spectro-temporal":[40],"features.":[41],"study":[43],"adoption":[45],"probabilistic":[48],"(variational)":[49],"bottleneck":[50],"into":[51],"classic":[53],"direct":[57],"spectral":[58,106],"reconstruction.":[59],"Evaluation":[60],"several":[62],"ablation":[63],"variants":[65],"is":[66],"carried":[67],"out":[68],"using":[69],"signal-to-distortion":[70],"ratio":[71],"and":[72,81,139,143],"perceptual":[73],"measures,":[74],"data":[77],"that":[78,92],"includes":[79],"known":[80],"unknown":[82],"noise":[83,155],"types":[84],"as":[85,87],"well":[86],"reverberation.":[88],"Our":[89],"experiments":[90],"show":[91],"residual":[94],"(skip)":[95],"connections":[96],"in":[97,130,141],"proposed":[99,121],"system":[100],"are":[101],"prerequisite":[103],"successful":[105],"reconstruction,":[107],"i.e.,":[108],"without":[109],"mask":[111,165],"estimation.":[112],"Results":[113],"show,":[114],"average,":[116],"an":[117],"advantage":[118],"over":[125],"its":[126],"classic,":[127],"non-variational":[128],"version":[129],"signal":[131],"performance":[133],"under":[134],"reverberant":[135],"conditions":[136],"0.31":[138],"6.98":[140],"PESQ":[142],"STOI":[144],"scores,":[145],"respectively.":[146],"Anecdotal":[147],"evidence":[148],"points":[149],"improved":[151],"suppression":[152],"impulsive":[154],"sources":[156],"with":[157],"compared":[161],"recurrent":[164],"estimation":[166],"baseline.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}