{"id":"https://openalex.org/W4224920207","doi":"https://doi.org/10.1109/icassp43922.2022.9747642","title":"Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement","display_name":"Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920207","doi":"https://doi.org/10.1109/icassp43922.2022.9747642"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747642","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/2203.02288","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"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Huajian Fang","raw_affiliation_strings":["Universität Hamburg,Signal Processing (SP),Germany"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg,Signal Processing (SP),Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077110886","display_name":"Tal Peer","orcid":"https://orcid.org/0000-0002-8974-9127"},"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":"Tal Peer","raw_affiliation_strings":["Universität Hamburg,Signal Processing (SP),Germany"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg,Signal Processing (SP),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":["Universität Hamburg,Knowledge Technology (WTM),Germany"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg,Knowledge Technology (WTM),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":["Universität Hamburg,Signal Processing (SP),Germany"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg,Signal Processing (SP),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"],"apc_list":null,"apc_paid":null,"fwci":1.0991,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78746851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"386","last_page":"390"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9945999979972839,"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":0.7328189611434937},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6797909736633301},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.6416258811950684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6379516124725342},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6116766929626465},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6086210608482361},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.557153582572937},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4814416766166687},{"id":"https://openalex.org/keywords/point-estimation","display_name":"Point estimation","score":0.4661732017993927},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4521028995513916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4083749055862427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4027620851993561},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3901025354862213},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33012986183166504},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1963854432106018},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16725599765777588},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.1359042227268219}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7328189611434937},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6797909736633301},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.6416258811950684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6379516124725342},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6116766929626465},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6086210608482361},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.557153582572937},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4814416766166687},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.4661732017993927},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4521028995513916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4083749055862427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4027620851993561},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3901025354862213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33012986183166504},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1963854432106018},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16725599765777588},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.1359042227268219},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747642","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.02288","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.02288","pdf_url":"https://arxiv.org/pdf/2203.02288","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:2203.02288","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.02288","pdf_url":"https://arxiv.org/pdf/2203.02288","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":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W306230967","https://openalex.org/W1522301498","https://openalex.org/W1995190897","https://openalex.org/W2051428568","https://openalex.org/W2135284480","https://openalex.org/W2169399159","https://openalex.org/W2289394825","https://openalex.org/W2403891086","https://openalex.org/W2516001803","https://openalex.org/W2600383743","https://openalex.org/W2766672686","https://openalex.org/W2883322837","https://openalex.org/W2885308148","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W3015969340","https://openalex.org/W3097549261","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3130335839","https://openalex.org/W3131332223","https://openalex.org/W3147539069","https://openalex.org/W3191448984","https://openalex.org/W6631190155","https://openalex.org/W6735443497","https://openalex.org/W6790869478"],"related_works":["https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W2028846388","https://openalex.org/W4295210860","https://openalex.org/W2072015625","https://openalex.org/W2117955483","https://openalex.org/W2161534637","https://openalex.org/W2010870899","https://openalex.org/W3168171120","https://openalex.org/W4251820777"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,172],"in":[2,44,124],"the":[3,39,62,74,85,89,95,106,129,144,153,160,164],"time-frequency":[4],"domain":[5],"is":[6,54,126],"often":[7],"performed":[8],"by":[9],"estimating":[10,84],"a":[11,31,58,76,137,170],"multiplicative":[12],"mask":[13],"to":[14,56,61,104,113,135,141],"extract":[15],"clean":[16],"speech.":[17],"However,":[18],"most":[19],"neural":[20,45,52],"network-based":[21,46],"methods":[22],"perform":[23],"point":[24,90],"estimation,":[25],"i.e.,":[26],"their":[27],"output":[28],"consists":[29],"of":[30,41,80,88,120,132],"single":[32],"mask.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"study":[38],"benefits":[40],"modeling":[42],"uncertainty":[43,96,112,161,181],"speech":[47],"enhancement.":[48],"For":[49],"this,":[50],"our":[51],"network":[53],"trained":[55],"map":[57],"noisy":[59],"spectrogram":[60],"Wiener":[63,108],"filter":[64,109],"and":[65,110],"its":[66,111],"associated":[67,97,162],"variance,":[68],"which":[69,123],"quantifies":[70],"uncertainty,":[71],"based":[72],"on":[73,148],"maximum":[75],"posteriori":[77],"(MAP)":[78],"inference":[79,131],"spectral":[81,121,133],"coefficients.":[82],"By":[83],"distribution":[86],"instead":[87],"estimate,":[91],"one":[92],"can":[93,156],"model":[94],"with":[98,128,163],"each":[99],"estimate.":[100],"We":[101],"further":[102],"propose":[103],"use":[105],"estimated":[107,165],"build":[114],"an":[115],"approximate":[116],"MAP":[117,130],"(A-MAP)":[118],"estimator":[119],"magnitudes,":[122],"turn":[125],"combined":[127],"coefficients":[134],"form":[136],"hybrid":[138],"loss":[139],"function":[140],"jointly":[142],"reinforce":[143],"estimation.":[145],"Experimental":[146],"results":[147],"different":[149],"datasets":[150],"show":[151],"that":[152,177],"proposed":[154],"method":[155],"not":[157,179],"only":[158],"capture":[159],"filters,":[166],"but":[167],"also":[168],"yield":[169],"higher":[171],"performance":[173],"over":[174],"comparable":[175],"models":[176],"do":[178],"take":[180],"into":[182],"account.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-04-28T00:00:00"}