{"id":"https://openalex.org/W1995190897","doi":"https://doi.org/10.1109/aspaa.2011.6082266","title":"Noise power estimation based on the probability of speech presence","display_name":"Noise power estimation based on the probability of speech presence","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W1995190897","doi":"https://doi.org/10.1109/aspaa.2011.6082266","mag":"1995190897"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2011.6082266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Sound and Image Processing Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden","Sound and Image Processing Lab., KTH Royal Institute of Technology, 100 44 Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Sound and Image Processing Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Sound and Image Processing Lab., KTH Royal Institute of Technology, 100 44 Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011148355","display_name":"Richard C. Hendriks","orcid":"https://orcid.org/0000-0001-8297-0251"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Richard C. Hendriks","raw_affiliation_strings":["Signal and Information Processing Laboratory, Delft University of Technology, Delft, Netherlands","Signal and Information Processing Lab, Delft University of Technology, 2628 CD, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Signal and Information Processing Laboratory, Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Signal and Information Processing Lab, Delft University of Technology, 2628 CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087022569"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":8.4186,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.98347753,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"145","last_page":"148"},"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":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.7802860140800476},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7778626084327698},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.670526921749115},{"id":"https://openalex.org/keywords/noise-power","display_name":"Noise power","score":0.6335537433624268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6298128366470337},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.5456259250640869},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5000860691070557},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4842474162578583},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.48146310448646545},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4696072041988373},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4641144871711731},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45367640256881714},{"id":"https://openalex.org/keywords/noise-floor","display_name":"Noise floor","score":0.43408408761024475},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.42478200793266296},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.397601455450058},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3508402407169342},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.339325487613678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22116434574127197},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2134634554386139},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.20540887117385864},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11981809139251709},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10134148597717285}],"concepts":[{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.7802860140800476},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7778626084327698},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.670526921749115},{"id":"https://openalex.org/C203234222","wikidata":"https://www.wikidata.org/wiki/Q2133519","display_name":"Noise power","level":3,"score":0.6335537433624268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6298128366470337},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.5456259250640869},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5000860691070557},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4842474162578583},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.48146310448646545},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4696072041988373},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4641144871711731},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45367640256881714},{"id":"https://openalex.org/C187612029","wikidata":"https://www.wikidata.org/wiki/Q17083130","display_name":"Noise floor","level":4,"score":0.43408408761024475},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.42478200793266296},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.397601455450058},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3508402407169342},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.339325487613678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22116434574127197},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2134634554386139},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.20540887117385864},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11981809139251709},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10134148597717285},{"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":2,"locations":[{"id":"doi:10.1109/aspaa.2011.6082266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.8635","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.8635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ens.ewi.tudelft.nl/pubs/gerkmann2011waspaa.pdf","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":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W145422376","https://openalex.org/W1975301756","https://openalex.org/W2111462246","https://openalex.org/W2118354544","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2131753991","https://openalex.org/W2134260279","https://openalex.org/W2146324387","https://openalex.org/W2150026426","https://openalex.org/W2158336491","https://openalex.org/W3147539069","https://openalex.org/W6605967130","https://openalex.org/W6676582144"],"related_works":["https://openalex.org/W2361247493","https://openalex.org/W2157330024","https://openalex.org/W2952979007","https://openalex.org/W1998374630","https://openalex.org/W2528250906","https://openalex.org/W2360887461","https://openalex.org/W1493471768","https://openalex.org/W1973038148","https://openalex.org/W2027761136","https://openalex.org/W3183728684"],"abstract_inverted_index":{"In":[0],"this":[1,65],"paper,":[2],"we":[3],"analyze":[4],"the":[5,25,36,49,69,73,88,103,110,113,117,126],"minimum":[6],"mean":[7],"square":[8],"error":[9],"(MMSE)":[10],"based":[11,27],"spectral":[12,28],"noise":[13,29,119,128,133],"power":[14,30,134],"estimator":[15,90,105,115],"[1]":[16],"and":[17,97,136],"present":[18],"an":[19],"improvement.":[20],"We":[21,62,82],"will":[22],"show":[23,83],"that":[24,84],"MMSE":[26,104,127],"estimate":[31],"is":[32,42,100,123,137],"only":[33],"updated":[34],"when":[35],"a":[37,50,57,76,94],"posteriori":[38,51],"signal-to-noise":[39],"ratio":[40],"(SNR)":[41],"lower":[43],"than":[44],"one.":[45],"This":[46],"threshold":[47],"on":[48],"SNR":[52],"can":[53],"be":[54],"interpreted":[55],"as":[56,99],"voice":[58],"activity":[59],"detector":[60],"(VAD).":[61],"propose":[63],"in":[64,107,131],"work":[66],"to":[67],"replace":[68],"hard":[70],"decision":[71],"of":[72],"VAD":[74],"by":[75,85,102],"soft":[77],"speech":[78],"presence":[79],"probability":[80],"(SPP).":[81],"doing":[86],"so,":[87],"proposed":[89,114],"does":[91],"not":[92],"require":[93],"bias":[95],"correction":[96],"safety-net":[98],"required":[101],"presented":[106],"[1].":[108],"At":[109],"same":[111],"time,":[112],"maintains":[116],"quick":[118],"tracking":[120],"capability":[121],"which":[122],"characteristic":[124],"for":[125],"tracker,":[129],"results":[130],"less":[132,139],"overestimation":[135],"computationally":[138],"expensive.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}