{"id":"https://openalex.org/W2768175742","doi":"https://doi.org/10.1109/taslp.2017.2778151","title":"On the Importance of Super-Gaussian Speech Priors for Machine-Learning Based Speech Enhancement","display_name":"On the Importance of Super-Gaussian Speech Priors for Machine-Learning Based Speech Enhancement","publication_year":2017,"publication_date":"2017-11-28","ids":{"openalex":"https://openalex.org/W2768175742","doi":"https://doi.org/10.1109/taslp.2017.2778151","mag":"2768175742"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2778151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2778151","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.05003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Robert Rehr","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":"Robert Rehr","raw_affiliation_strings":["Signal Processing Group, Department of Informatics, University of Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":null,"display_name":"Timo Gerkmann","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":false,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Signal Processing Group, Department of Informatics, University of Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Informatics, University of Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":1.4953,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.84225275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"26","issue":"2","first_page":"357","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8766999840736389,"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":0.8766999840736389,"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":0.05829999968409538,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.007699999958276749,"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/prior-probability","display_name":"Prior probability","score":0.742900013923645},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6075999736785889},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5691999793052673},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48750001192092896},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.43720000982284546},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38440001010894775},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.36570000648498535},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3529999852180481},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3513000011444092},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3513000011444092}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.742900013923645},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6075999736785889},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5645999908447266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5314000248908997},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4262000024318695},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.34209999442100525},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.328000009059906},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.25769999623298645}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2017.2778151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2778151","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"},{"id":"pmh:oai:arXiv.org:1703.05003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.05003","pdf_url":"https://arxiv.org/pdf/1703.05003","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:1703.05003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.05003","pdf_url":"https://arxiv.org/pdf/1703.05003","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1984213819","https://openalex.org/W1995190897","https://openalex.org/W2002096058","https://openalex.org/W2004227461","https://openalex.org/W2010757852","https://openalex.org/W2012770786","https://openalex.org/W2013608223","https://openalex.org/W2016254085","https://openalex.org/W2025515167","https://openalex.org/W2039844283","https://openalex.org/W2051428568","https://openalex.org/W2051812123","https://openalex.org/W2062227835","https://openalex.org/W2063157319","https://openalex.org/W2066561607","https://openalex.org/W2103135337","https://openalex.org/W2103747981","https://openalex.org/W2109215269","https://openalex.org/W2109744426","https://openalex.org/W2121973264","https://openalex.org/W2130389898","https://openalex.org/W2130476329","https://openalex.org/W2139500975","https://openalex.org/W2147299274","https://openalex.org/W2150415460","https://openalex.org/W2157614506","https://openalex.org/W2158336491","https://openalex.org/W2161620716","https://openalex.org/W2163195137","https://openalex.org/W2164715564","https://openalex.org/W2165967438","https://openalex.org/W2236045036","https://openalex.org/W2515728195","https://openalex.org/W2560174002","https://openalex.org/W2749721520","https://openalex.org/W3147539069","https://openalex.org/W6605266330","https://openalex.org/W6607486085","https://openalex.org/W6631943919","https://openalex.org/W6789826613"],"related_works":[],"abstract_inverted_index":{"For":[0,95],"enhancing":[1],"noisy":[2],"signals,":[3],"machine-learning":[4,50],"based":[5,104],"single-channel":[6],"speech":[7,15,41,80],"enhancement":[8,136],"schemes":[9],"exploit":[10],"prior":[11],"knowledge":[12],"about":[13],"typical":[14],"spectral":[16,42,51,81],"structures.":[17],"To":[18],"ensure":[19],"a":[20,75,100,108],"good":[21],"generalization":[22],"and":[23,32,64,107,122,148],"to":[24,39,46],"meet":[25],"requirements":[26],"in":[27],"terms":[28],"of":[29,62,77,116],"computational":[30],"complexity":[31],"memory":[33],"consumption,":[34],"certain":[35],"methods":[36],"restrict":[37],"themselves":[38],"learning":[40],"envelopes.":[43],"We":[44],"refer":[45],"these":[47],"approaches":[48,140],"as":[49,91,114],"envelope":[52],"(MLSE)-based":[53],"approaches.":[54,118],"In":[55],"this":[56],"paper,":[57],"we":[58,98],"show":[59],"by":[60],"means":[61],"theoretical":[63],"experimental":[65],"analyses":[66],"that":[67,126],"for":[68,74,134,138],"MLSE-based":[69,117,139],"approaches,":[70],"super-Gaussian":[71,128,141],"priors":[72,129,142],"allow":[73],"reduction":[76],"noise":[78],"between":[79],"harmonics":[82],"which":[83],"is":[84],"not":[85],"achievable":[86],"using":[87],"Gaussian":[88,151],"estimators":[89],"such":[90],"the":[92,96],"Wiener":[93],"filter.":[94],"evaluation,":[97],"use":[99],"deep":[101],"neural":[102],"network":[103],"phoneme":[105],"classifier":[106],"low-rank":[109],"nonnegative":[110],"matrix":[111],"factorization":[112],"framework":[113],"examples":[115],"A":[119],"listening":[120],"experiment":[121],"instrumental":[123],"measures":[124],"confirm":[125],"while":[127],"yield":[130],"only":[131],"moderate":[132],"improvements":[133],"classic":[135],"schemes,":[137],"clearly":[143],"make":[144],"an":[145],"important":[146],"difference":[147],"significantly":[149],"outperform":[150],"priors.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2017-12-04T00:00:00"}