{"id":"https://openalex.org/W2969917057","doi":"https://doi.org/10.1109/taslp.2019.2935803","title":"Using Generalized Gaussian Distributions to Improve Regression Error Modeling for Deep Learning-Based Speech Enhancement","display_name":"Using Generalized Gaussian Distributions to Improve Regression Error Modeling for Deep Learning-Based Speech Enhancement","publication_year":2019,"publication_date":"2019-08-22","ids":{"openalex":"https://openalex.org/W2969917057","doi":"https://doi.org/10.1109/taslp.2019.2935803","mag":"2969917057"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2935803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2935803","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5100704805","display_name":"Li Chai","orcid":"https://orcid.org/0000-0001-7906-9913"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Chai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7906-9913","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019919993","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0003-1313-9418"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Feng Liu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1892-2551","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7812,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91446501,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"27","issue":"12","first_page":"1919","last_page":"1931"},"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":0.9973999857902527,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9947999715805054,"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/timit","display_name":"TIMIT","score":0.7021971344947815},{"id":"https://openalex.org/keywords/heteroscedasticity","display_name":"Heteroscedasticity","score":0.6446608304977417},{"id":"https://openalex.org/keywords/homoscedasticity","display_name":"Homoscedasticity","score":0.6173409819602966},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5555868744850159},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5073923468589783},{"id":"https://openalex.org/keywords/generalized-normal-distribution","display_name":"Generalized normal distribution","score":0.5000128746032715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.499072790145874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48002853989601135},{"id":"https://openalex.org/keywords/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.4755377769470215},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4690920114517212},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43651461601257324},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4362507462501526},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.43082869052886963},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39464491605758667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3783886730670929},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34913888573646545},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2993899881839752},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.29827356338500977},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19766199588775635},{"id":"https://openalex.org/keywords/normal-distribution","display_name":"Normal distribution","score":0.18697866797447205}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7021971344947815},{"id":"https://openalex.org/C101104100","wikidata":"https://www.wikidata.org/wiki/Q1063540","display_name":"Heteroscedasticity","level":2,"score":0.6446608304977417},{"id":"https://openalex.org/C104409967","wikidata":"https://www.wikidata.org/wiki/Q1054836","display_name":"Homoscedasticity","level":3,"score":0.6173409819602966},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5555868744850159},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5073923468589783},{"id":"https://openalex.org/C171383496","wikidata":"https://www.wikidata.org/wiki/Q2497477","display_name":"Generalized normal distribution","level":3,"score":0.5000128746032715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.499072790145874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48002853989601135},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.4755377769470215},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4690920114517212},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43651461601257324},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4362507462501526},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.43082869052886963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39464491605758667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3783886730670929},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34913888573646545},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2993899881839752},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.29827356338500977},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19766199588775635},{"id":"https://openalex.org/C102094743","wikidata":"https://www.wikidata.org/wiki/Q133871","display_name":"Normal distribution","level":2,"score":0.18697866797447205},{"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},{"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/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","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":1,"locations":[{"id":"doi:10.1109/taslp.2019.2935803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2935803","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G573022218","display_name":null,"funder_award_id":"U1613211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8173470123","display_name":"\u57fa\u4e8e\u56de\u5f52\u795e\u7ecf\u7f51\u7edc\u7684\u8bed\u97f3\u5206\u79bb\u5173\u952e\u95ee\u9898\u7814\u7a76","funder_award_id":"61671422","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W258661521","https://openalex.org/W639708223","https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1562848178","https://openalex.org/W1579853615","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W1790748249","https://openalex.org/W1897240248","https://openalex.org/W1963950237","https://openalex.org/W1966697370","https://openalex.org/W1974387177","https://openalex.org/W1983050180","https://openalex.org/W1989314204","https://openalex.org/W1995536493","https://openalex.org/W1998435329","https://openalex.org/W2006129368","https://openalex.org/W2013756339","https://openalex.org/W2027123933","https://openalex.org/W2031647436","https://openalex.org/W2039708501","https://openalex.org/W2044893557","https://openalex.org/W2045956438","https://openalex.org/W2053165762","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2090681206","https://openalex.org/W2096709536","https://openalex.org/W2100495367","https://openalex.org/W2103636088","https://openalex.org/W2106644119","https://openalex.org/W2114847658","https://openalex.org/W2121973264","https://openalex.org/W2123684326","https://openalex.org/W2126942983","https://openalex.org/W2128653836","https://openalex.org/W2136922672","https://openalex.org/W2139807330","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2150355110","https://openalex.org/W2154195147","https://openalex.org/W2156232940","https://openalex.org/W2168379380","https://openalex.org/W2180748755","https://openalex.org/W2286859569","https://openalex.org/W2291877678","https://openalex.org/W2345067732","https://openalex.org/W2397226255","https://openalex.org/W2404724332","https://openalex.org/W2516342150","https://openalex.org/W2517760955","https://openalex.org/W2524708987","https://openalex.org/W2550397165","https://openalex.org/W2577587650","https://openalex.org/W2613718673","https://openalex.org/W2620812332","https://openalex.org/W2673599284","https://openalex.org/W2765976216","https://openalex.org/W2767832833","https://openalex.org/W2774389566","https://openalex.org/W2774425939","https://openalex.org/W2778338786","https://openalex.org/W2786835328","https://openalex.org/W2805233667","https://openalex.org/W2891607145","https://openalex.org/W2892129657","https://openalex.org/W2914048585","https://openalex.org/W2919115771","https://openalex.org/W2963045393","https://openalex.org/W2963236355","https://openalex.org/W2963351212","https://openalex.org/W2963828919","https://openalex.org/W3103619082","https://openalex.org/W3124794156","https://openalex.org/W4229578634","https://openalex.org/W4230865130","https://openalex.org/W4253928870","https://openalex.org/W6604653223","https://openalex.org/W6609686331","https://openalex.org/W6634817459","https://openalex.org/W6675903431","https://openalex.org/W6712317276"],"related_works":["https://openalex.org/W2361247493","https://openalex.org/W4375869169","https://openalex.org/W2597829360","https://openalex.org/W2157330024","https://openalex.org/W2952979007","https://openalex.org/W1998374630","https://openalex.org/W2921661700","https://openalex.org/W2528250906","https://openalex.org/W2138406058","https://openalex.org/W2131486661"],"abstract_inverted_index":{"From":[0],"a":[1,32],"statistical":[2,33],"perspective,":[3],"the":[4,16,36,42,79,97,101,109,114,131,155,162],"conventional":[5,132,163],"minimum":[6],"mean":[7],"squared":[8],"error":[9,26,81,103],"(MMSE)":[10],"criterion":[11],"can":[12],"be":[13],"considered":[14],"as":[15,83],"maximum":[17],"likelihood":[18],"(ML)":[19],"solution":[20],"under":[21,142],"an":[22],"assumed":[23],"homoscedastic":[24],"Gaussian":[25,93],"model.":[27],"However,":[28],"in":[29,45,68,135],"this":[30],"paper,":[31],"analysis":[34],"reveals":[35],"super-Gaussian":[37],"and":[38,88,148,169],"heteroscedastic":[39],"properties":[40],"of":[41,78,125,137],"prediction":[43,80],"errors":[44],"nonlinear":[46],"regression":[47],"deep":[48],"neural":[49],"network":[50],"(DNN)-based":[51],"speech":[52],"enhancement":[53],"when":[54],"estimating":[55],"clean":[56],"log-power":[57],"spectral":[58],"(LPS)":[59],"components":[60],"at":[61,149],"DNN":[62,69,128,133],"outputs":[63],"with":[64,91,100,159],"noisy":[65],"LPS":[66],"features":[67],"input":[70],"vectors.":[71],"Accordingly,":[72],"we":[73],"propose":[74],"treating":[75],"all":[76],"dimensions":[77],"vector":[82],"statistically":[84],"independent":[85],"random":[86],"variables":[87],"model":[89,104],"them":[90],"generalized":[92],"distributions":[94],"(GGDs).":[95],"Then,":[96],"objective":[98,139,158],"function":[99],"GGD":[102,160],"is":[105],"derived":[106],"according":[107],"to":[108],"ML":[110,156],"criterion.":[111],"Experiments":[112],"on":[113],"TIMIT":[115],"corpus":[116],"corrupted":[117],"by":[118],"simulated":[119],"additive":[120],"noises":[121],"show":[122],"consistent":[123],"improvements":[124],"our":[126],"proposed":[127],"framework":[129,134],"over":[130],"terms":[136],"various":[138,150],"quality":[140],"measures":[141],"14":[143],"unseen":[144],"noise":[145],"types":[146],"evaluated":[147],"signal-to-noise":[151],"ratio":[152],"levels.":[153],"Furthermore,":[154],"optimization":[157],"outperforms":[161],"MMSE":[164],"criterion,":[165],"achieving":[166],"improved":[167],"generalization":[168],"robustness.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}