{"id":"https://openalex.org/W2157614506","doi":"https://doi.org/10.1109/tasl.2009.2030012","title":"Speech Enhancement Using Gaussian Scale Mixture Models","display_name":"Speech Enhancement Using Gaussian Scale Mixture Models","publication_year":2009,"publication_date":"2009-08-12","ids":{"openalex":"https://openalex.org/W2157614506","doi":"https://doi.org/10.1109/tasl.2009.2030012","mag":"2157614506","pmid":"https://pubmed.ncbi.nlm.nih.gov/21359139"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2030012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2030012","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5109130388","display_name":"Jiucang Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I1307098950","display_name":"Salk Institute for Biological Studies","ror":"https://ror.org/03xez1567","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1307098950"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiucang Hao","raw_affiliation_strings":["Computational Neurobiology Laboratory, Salk Institute, La Jolla, CA 92037 USA, and also with the Institute for Neural Computation, University of California, San Diego, CA 92093 USA","Institute of Neural Computation, University of California, San Diego, CA, USA","Computational Neurobiology Laboratory, Salk Institute, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Neurobiology Laboratory, Salk Institute, La Jolla, CA 92037 USA, and also with the Institute for Neural Computation, University of California, San Diego, CA 92093 USA","institution_ids":["https://openalex.org/I1307098950"]},{"raw_affiliation_string":"Institute of Neural Computation, University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Computational Neurobiology Laboratory, Salk Institute, La Jolla, CA, USA","institution_ids":["https://openalex.org/I1307098950"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022408850","display_name":"Te-Won Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Te-Won Lee","raw_affiliation_strings":["QUALCOMM, Inc.orporated, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"QUALCOMM, Inc.orporated, San Diego, CA, USA","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044141636","display_name":"Terrence J. Sejnowski","orcid":"https://orcid.org/0000-0002-0622-7391"},"institutions":[{"id":"https://openalex.org/I1307098950","display_name":"Salk Institute for Biological Studies","ror":"https://ror.org/03xez1567","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1307098950"]},{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Terrence J Sejnowski","raw_affiliation_strings":["Division of Biological Sciences, University of California, San Diego, CA, USA","Howard Hughes Medical Institute and Computational Neurobiology Laboratory, Salk Institute, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biological Sciences, University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Howard Hughes Medical Institute and Computational Neurobiology Laboratory, Salk Institute, La Jolla, CA, USA","institution_ids":["https://openalex.org/I1307098950","https://openalex.org/I1344073410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0796,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.79559235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":"6","first_page":"1127","last_page":"1136"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9970999956130981,"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/mathematics","display_name":"Mathematics","score":0.5599060654640198},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5559141635894775},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4805634319782257},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.45946502685546875},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.4561660885810852},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.45230698585510254},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44799086451530457},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.44249439239501953},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4243605136871338},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3845893144607544},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3351789116859436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3267565369606018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21877583861351013},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12592661380767822},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.11680382490158081}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5599060654640198},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5559141635894775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4805634319782257},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.45946502685546875},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.4561660885810852},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.45230698585510254},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44799086451530457},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.44249439239501953},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4243605136871338},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3845893144607544},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3351789116859436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3267565369606018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21877583861351013},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12592661380767822},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.11680382490158081},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tasl.2009.2030012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2030012","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:21359139","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21359139","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.8934","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.8934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.cnl.salk.edu/PDFs/Speech Enhancement using Gaussian Scale Mixture Models 2010-4137.pdf","raw_type":"text"},{"id":"pmh:oai:europepmc.org:2304522","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3045111","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306082","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W36799504","https://openalex.org/W45374770","https://openalex.org/W172871796","https://openalex.org/W214562933","https://openalex.org/W569503658","https://openalex.org/W1532581717","https://openalex.org/W1554663460","https://openalex.org/W1782480827","https://openalex.org/W1878437425","https://openalex.org/W1975301756","https://openalex.org/W2016254085","https://openalex.org/W2048142341","https://openalex.org/W2049633694","https://openalex.org/W2050237878","https://openalex.org/W2096779346","https://openalex.org/W2097572849","https://openalex.org/W2099111195","https://openalex.org/W2103135337","https://openalex.org/W2105696145","https://openalex.org/W2105716221","https://openalex.org/W2107420590","https://openalex.org/W2109349638","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2133908567","https://openalex.org/W2143127677","https://openalex.org/W2143600836","https://openalex.org/W2146324387","https://openalex.org/W2147299274","https://openalex.org/W2147665979","https://openalex.org/W2150924398","https://openalex.org/W2158336491","https://openalex.org/W2161182969","https://openalex.org/W2168386179","https://openalex.org/W2169147844","https://openalex.org/W2172085063","https://openalex.org/W3129711340","https://openalex.org/W3147539069","https://openalex.org/W4285719527","https://openalex.org/W4388297464","https://openalex.org/W6601512598","https://openalex.org/W6632030081","https://openalex.org/W6637953461","https://openalex.org/W6680017764"],"related_works":["https://openalex.org/W2604674416","https://openalex.org/W3142326235","https://openalex.org/W1980122758","https://openalex.org/W2089980404","https://openalex.org/W2509835205","https://openalex.org/W2047497780","https://openalex.org/W1549575953","https://openalex.org/W2060891144","https://openalex.org/W2652648847","https://openalex.org/W2044472626"],"abstract_inverted_index":{"This":[0,57],"paper":[1],"presents":[2],"a":[3,12,18,36,45,60,150],"novel":[4],"probabilistic":[5,19,84,133],"approach":[6],"to":[7,51,93,101,112,121,142,158,203,222],"speech":[8,29,68,160],"enhancement.":[9],"Instead":[10],"of":[11,54,130],"deterministic":[13],"logarithmic":[14],"relationship,":[15],"we":[16,138],"assume":[17],"relationship":[20],"between":[21,86],"the":[22,26,32,52,55,67,71,75,105,114,123,144,146,175,188,198,201,204,211],"frequency":[23,42,72,87,177],"coefficients":[24,43,88,178],"and":[25,89,116,149,165,184],"log-spectra.":[27,56],"The":[28,41,83,153],"model":[30,39,64,134],"in":[31,59,70],"log-spectral":[33],"domain":[34],"is":[35,135],"Gaussian":[37,47,61,163],"mixture":[38,63],"(GMM).":[40],"obey":[44],"zero-mean":[46],"whose":[48],"covariance":[49],"equals":[50],"exponential":[53],"results":[58],"scale":[62],"(GSMM)":[65],"for":[66],"signal":[69,125],"domain,":[73],"since":[74],"log-spectra":[76,90,190,199],"can":[77],"be":[78,94,102],"regarded":[79],"as":[80,96],"scaling":[81],"factors.":[82],"relation":[85],"allows":[91],"these":[92],"treated":[95],"two":[97,140],"random":[98],"variables,":[99],"both":[100,170],"estimated":[103,176,189],"from":[104,174,187],"noisy":[106],"signals.":[107],"Expectation-maximization":[108],"(EM)":[109],"was":[110,119],"used":[111,120],"train":[113],"GSMM":[115],"Bayesian":[117],"inference":[118,129],"compute":[122],"posterior":[124],"distribution.":[126],"Because":[127],"exact":[128],"this":[131],"full":[132],"computationally":[136],"intractable,":[137],"developed":[139],"approaches":[141],"enhance":[143,159],"efficiency:":[145],"Laplace":[147],"method":[148],"variational":[151],"approximation.":[152],"proposed":[154],"methods":[155],"were":[156,219],"applied":[157],"corrupted":[161],"by":[162],"noise":[164,167],"speech-shaped":[166],"(SSN).":[168],"For":[169],"approximations,":[171],"signals":[172],"reconstructed":[173,186],"provided":[179],"higher":[180],"signal-to-noise":[181],"ratio":[182],"(SNR)":[183],"those":[185],"produced":[191],"lower":[192],"word":[193],"recognition":[194],"error":[195],"rate":[196],"because":[197],"fit":[200],"inputs":[202],"recognizer":[205],"better.":[206],"Our":[207],"algorithms":[208,214],"effectively":[209],"reduced":[210],"SSN,":[212],"which":[213],"based":[215],"on":[216],"spectral":[217],"analysis":[218],"not":[220],"able":[221],"suppress.":[223]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2022-02-08T00:00:00"}