{"id":"https://openalex.org/W3131332223","doi":"https://doi.org/10.1109/icassp39728.2021.9414060","title":"Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder","display_name":"Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3131332223","doi":"https://doi.org/10.1109/icassp39728.2021.9414060","mag":"3131332223"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.08706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069061870","display_name":"Huajian Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Huajian Fang","raw_affiliation_strings":["Knowledge Technology (WTM), Universitat Hamburg, Germany","Signal Processing (SP), Universit\u00e4t Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology (WTM), Universitat Hamburg, Germany","institution_ids":["https://openalex.org/I884043246"]},{"raw_affiliation_string":"Signal Processing (SP), Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023952427","display_name":"Guillaume Carbajal","orcid":"https://orcid.org/0000-0003-4077-1742"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guillaume Carbajal","raw_affiliation_strings":["Signal Processing (SP), Universit\u00e4t Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing (SP), Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Knowledge Technology (WTM), Universitat Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Knowledge Technology (WTM), Universitat Hamburg, Germany","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Signal Processing (SP), Universit\u00e4t Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing (SP), Universit\u00e4t Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069061870"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":7.4098,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.97957133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"676","last_page":"680"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9955000281333923,"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/autoencoder","display_name":"Autoencoder","score":0.8807739019393921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7733544111251831},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.728969931602478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6769475936889648},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6445878744125366},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5461313724517822},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5105572938919067},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.49998974800109863},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4880481958389282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48759785294532776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46334773302078247},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41216063499450684}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8807739019393921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7733544111251831},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.728969931602478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6769475936889648},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6445878744125366},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5461313724517822},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5105572938919067},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.49998974800109863},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4880481958389282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48759785294532776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46334773302078247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41216063499450684},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.08706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.08706","pdf_url":"https://arxiv.org/pdf/2102.08706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.08706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.08706","pdf_url":"https://arxiv.org/pdf/2102.08706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1506438021","https://openalex.org/W1522301498","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W1985093013","https://openalex.org/W2039844283","https://openalex.org/W2046869671","https://openalex.org/W2051428568","https://openalex.org/W2072634211","https://openalex.org/W2099471712","https://openalex.org/W2108501770","https://openalex.org/W2135029798","https://openalex.org/W2135284480","https://openalex.org/W2149273154","https://openalex.org/W2161620716","https://openalex.org/W2168273590","https://openalex.org/W2188365844","https://openalex.org/W2766672686","https://openalex.org/W2883322837","https://openalex.org/W2901552243","https://openalex.org/W2938737578","https://openalex.org/W2962866211","https://openalex.org/W2962897886","https://openalex.org/W2963632741","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W3097549261","https://openalex.org/W3100968126","https://openalex.org/W3143596294","https://openalex.org/W4245883374","https://openalex.org/W4292403327","https://openalex.org/W4297791576","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6680012447","https://openalex.org/W6687045409","https://openalex.org/W6752558437"],"related_works":["https://openalex.org/W3037110488","https://openalex.org/W3108403339","https://openalex.org/W2022538999","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W2002243964","https://openalex.org/W3090086172","https://openalex.org/W4287867034","https://openalex.org/W4375869276","https://openalex.org/W1603113134"],"abstract_inverted_index":{"Recently,":[0],"a":[1,60,129,146],"generative":[2],"variational":[3],"autoencoder":[4],"(VAE)":[5],"has":[6],"been":[7],"proposed":[8,91],"for":[9],"speech":[10,14,22,66,151],"enhancement":[11],"to":[12,32,50,123,145],"model":[13,108,118,143],"statistics.":[15],"However,":[16],"this":[17],"approach":[18,71],"only":[19],"uses":[20],"clean":[21],"in":[23,36,54,98],"the":[24,28,43,46,55,95,105,111,139,142,149],"training":[25,56,152],"phase,":[26],"making":[27],"estimation":[29],"particularly":[30],"sensitive":[31],"noise":[33,52,85,125],"presence,":[34],"especially":[35],"low":[37],"signal-to-noise":[38],"ratios":[39],"(SNRs).":[40],"To":[41],"increase":[42],"robustness":[44,140],"of":[45,75,100,107,121,141,148],"VAE,":[47],"we":[48,114,137],"propose":[49],"include":[51],"information":[53],"phase":[57],"by":[58],"using":[59,82],"noise-aware":[61,92],"encoder":[62],"trained":[63],"on":[64,72],"noisy-clean":[65,150],"pairs.":[67],"We":[68,87],"evaluate":[69],"our":[70,90,117],"real":[73],"recordings":[74],"different":[76,84],"noisy":[77],"environments":[78],"and":[79],"acoustic":[80],"conditions":[81,126],"two":[83],"datasets.":[86],"show":[88],"that":[89,116],"VAE":[93,97],"outperforms":[94],"standard":[96],"terms":[99],"overall":[101],"distortion":[102],"without":[103],"increasing":[104],"number":[106],"parameters.":[109],"At":[110],"same":[112],"time,":[113],"demonstrate":[115,138],"is":[119],"capable":[120],"generalizing":[122],"unseen":[124],"better":[127],"than":[128],"supervised":[130],"feedforward":[131],"deep":[132],"neural":[133],"network":[134],"(DNN).":[135],"Furthermore,":[136],"performance":[144],"reduction":[147],"data":[153],"size.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}