{"id":"https://openalex.org/W4375868822","doi":"https://doi.org/10.1109/icassp49357.2023.10095213","title":"Uncertainty Estimation in Deep Speech Enhancement Using Complex Gaussian Mixture Models","display_name":"Uncertainty Estimation in Deep Speech Enhancement Using Complex Gaussian Mixture Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868822","doi":"https://doi.org/10.1109/icassp49357.2023.10095213"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5011728435","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":"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":2,"corresponding_author_ids":["https://openalex.org/A5011728435"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":1.0338,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74950209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"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":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":0.9975000023841858,"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":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.7107661366462708},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.645611047744751},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.5956894159317017},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5460259914398193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5067587494850159},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49312230944633484},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46281421184539795},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.44332408905029297},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.43743062019348145},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4300050139427185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4260501265525818},{"id":"https://openalex.org/keywords/conditional-probability-distribution","display_name":"Conditional probability distribution","score":0.4180501699447632},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3580498695373535},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2074877917766571},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17360031604766846},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13281038403511047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107661366462708},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.645611047744751},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.5956894159317017},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5460259914398193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5067587494850159},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49312230944633484},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46281421184539795},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.44332408905029297},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.43743062019348145},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4300050139427185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4260501265525818},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.4180501699447632},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3580498695373535},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2074877917766571},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17360031604766846},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13281038403511047},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095213","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"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":37,"referenced_works":["https://openalex.org/W1601795611","https://openalex.org/W2067109848","https://openalex.org/W2135284480","https://openalex.org/W2148985659","https://openalex.org/W2289394825","https://openalex.org/W2403891086","https://openalex.org/W2600383743","https://openalex.org/W2673599284","https://openalex.org/W2774707525","https://openalex.org/W2808266363","https://openalex.org/W2885308148","https://openalex.org/W2887922452","https://openalex.org/W2889442120","https://openalex.org/W2948479456","https://openalex.org/W2951266961","https://openalex.org/W2962730596","https://openalex.org/W2962866211","https://openalex.org/W2963914998","https://openalex.org/W2969917057","https://openalex.org/W3014596384","https://openalex.org/W3097906045","https://openalex.org/W3120607380","https://openalex.org/W3134774296","https://openalex.org/W3163464943","https://openalex.org/W3191448984","https://openalex.org/W4221157442","https://openalex.org/W4224920207","https://openalex.org/W4298386155","https://openalex.org/W4301504317","https://openalex.org/W4387757537","https://openalex.org/W6720019270","https://openalex.org/W6735443497","https://openalex.org/W6746914816","https://openalex.org/W6751523092","https://openalex.org/W6764214684","https://openalex.org/W6810059299","https://openalex.org/W6839345390"],"related_works":["https://openalex.org/W1991093342","https://openalex.org/W2078622645","https://openalex.org/W1952261593","https://openalex.org/W2170798819","https://openalex.org/W2990323019","https://openalex.org/W4244110343","https://openalex.org/W3099192420","https://openalex.org/W2778147733","https://openalex.org/W4297730821","https://openalex.org/W2488457351"],"abstract_inverted_index":{"Single-channel":[0],"deep":[1,92,162],"speech":[2,14,34,39,73,93,168],"enhancement":[3,94,169],"approaches":[4],"often":[5],"estimate":[6],"a":[7,16,91,110,116,134,166],"single":[8],"multiplicative":[9],"mask":[10],"to":[11,27,65,82,119,124],"extract":[12],"clean":[13,33,72,130],"without":[15],"measure":[17],"of":[18,109,129,136],"its":[19],"accuracy.":[20],"Instead,":[21],"in":[22,36,59],"this":[23],"work,":[24],"we":[25,80,98],"propose":[26,81],"quantify":[28],"the":[29,56,62,66,100,121,125,148],"uncertainty":[30,42,48,58,78,154],"associated":[31],"with":[32],"estimates":[35],"neural":[37,117],"network-based":[38],"enhancement.":[40],"Predictive":[41],"is":[43],"typically":[44],"categorized":[45],"into":[46,90],"aleatoric":[47],"and":[49,61,75,104,114,155,161],"epistemic":[50],"uncertainty.":[51,68],"The":[52],"former":[53],"accounts":[54],"for":[55,70],"inherent":[57],"data":[60],"latter":[63],"corresponds":[64],"model":[67,99],"Aiming":[69],"robust":[71],"estimation":[74],"efficient":[76],"predictive":[77,153],"quantification,":[79],"integrate":[83],"statistical":[84,159],"complex":[85,138],"Gaussian":[86,139],"mixture":[87,135],"models":[88,160],"(CG-MMs)":[89],"framework.":[95],"More":[96],"specifically,":[97],"dependency":[101],"between":[102],"input":[103,123],"output":[105],"stochastically":[106],"by":[107],"means":[108],"conditional":[111],"probability":[112],"density":[113],"train":[115],"network":[118],"map":[120],"noisy":[122],"full":[126],"posterior":[127],"distribution":[128],"speech,":[131],"modeled":[132],"as":[133],"multiple":[137],"components.":[140],"Experimental":[141],"results":[142],"on":[143],"different":[144],"datasets":[145],"show":[146],"that":[147,156],"proposed":[149],"algorithm":[150],"effectively":[151],"captures":[152],"combining":[157],"powerful":[158],"learning":[163],"also":[164],"delivers":[165],"superior":[167],"performance.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}