{"id":"https://openalex.org/W2898446161","doi":"https://doi.org/10.1109/taslp.2018.2877909","title":"On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement","display_name":"On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement","publication_year":2018,"publication_date":"2018-10-25","ids":{"openalex":"https://openalex.org/W2898446161","doi":"https://doi.org/10.1109/taslp.2018.2877909","mag":"2898446161"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2877909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2877909","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/b2fc9b83-75e5-4291-be70-d85bafa758be","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006420917","display_name":"Morten Kolb\u00e6k","orcid":"https://orcid.org/0000-0002-2561-4960"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Morten Kolb\u00e6k","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-2561-4960","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-6856-8928","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark","Oticon A/S, Sm\u00f8rum, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Oticon A/S, Sm\u00f8rum, Denmark","institution_ids":["https://openalex.org/I4210130492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8847,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.86658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"27","issue":"2","first_page":"283","last_page":"295"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.996399998664856,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8780646324157715},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7729583978652954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.689983069896698},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.6374765038490295},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6252106428146362},{"id":"https://openalex.org/keywords/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.5743334293365479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5145260691642761},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.49477189779281616},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.4860244393348694},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.46516114473342896},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42748308181762695},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41651269793510437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.387015700340271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2995762825012207},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24267050623893738},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17764639854431152}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8780646324157715},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7729583978652954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.689983069896698},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.6374765038490295},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6252106428146362},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.5743334293365479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5145260691642761},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.49477189779281616},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4860244393348694},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.46516114473342896},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42748308181762695},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41651269793510437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.387015700340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2995762825012207},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24267050623893738},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17764639854431152},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/taslp.2018.2877909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2877909","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:pure.atira.dk:openaire/b2fc9b83-75e5-4291-be70-d85bafa758be","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/b2fc9b83-75e5-4291-be70-d85bafa758be","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kolb\u00e6k, M, Tan, Z-H & Jensen, J 2019, 'On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement', IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 2, 8509159, pp. 283-295. https://doi.org/10.1109/TASLP.2018.2877909","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:1806.08404","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.08404","pdf_url":"https://arxiv.org/pdf/1806.08404","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"},{"id":"pmh:oai:pure.atira.dk:publications/b2fc9b83-75e5-4291-be70-d85bafa758be","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85055695562&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kolb\u00e6k , M , Tan , Z-H & Jensen , J 2019 , ' On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement ' , IEEE/ACM Transactions on Audio, Speech, and Language Processing , vol. 27 , no. 2 , 8509159 , pp. 283-295 . https://doi.org/10.1109/TASLP.2018.2877909","raw_type":"article"},{"id":"doi:10.48550/arxiv.1806.08404","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.08404","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/b2fc9b83-75e5-4291-be70-d85bafa758be","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/b2fc9b83-75e5-4291-be70-d85bafa758be","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kolb\u00e6k, M, Tan, Z-H & Jensen, J 2019, 'On the Relationship Between Short-Time Objective Intelligibility and Short-Time Spectral-Amplitude Mean-Square Error for Speech Enhancement', IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 2, 8509159, pp. 283-295. https://doi.org/10.1109/TASLP.2018.2877909","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324626","display_name":"Oticon Fonden","ror":"https://ror.org/02x3xhs38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W643591744","https://openalex.org/W1489184006","https://openalex.org/W1495679096","https://openalex.org/W1503566218","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1557189666","https://openalex.org/W1707086801","https://openalex.org/W1893876709","https://openalex.org/W1963970749","https://openalex.org/W1968939597","https://openalex.org/W1973746598","https://openalex.org/W1975301756","https://openalex.org/W1999686891","https://openalex.org/W2014365762","https://openalex.org/W2020997493","https://openalex.org/W2085191029","https://openalex.org/W2101042021","https://openalex.org/W2109215269","https://openalex.org/W2117416982","https://openalex.org/W2120847449","https://openalex.org/W2121973264","https://openalex.org/W2135284480","https://openalex.org/W2137983211","https://openalex.org/W2141998673","https://openalex.org/W2153038597","https://openalex.org/W2159373586","https://openalex.org/W2168274102","https://openalex.org/W2181607856","https://openalex.org/W2289394825","https://openalex.org/W2364134690","https://openalex.org/W2465704452","https://openalex.org/W2516001803","https://openalex.org/W2524708987","https://openalex.org/W2550397165","https://openalex.org/W2594607416","https://openalex.org/W2619516334","https://openalex.org/W2622055663","https://openalex.org/W2696558042","https://openalex.org/W2765425905","https://openalex.org/W2889885720","https://openalex.org/W2891607145","https://openalex.org/W2892129657","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963351212","https://openalex.org/W3147539069","https://openalex.org/W4233159434","https://openalex.org/W4238565852","https://openalex.org/W4250589301","https://openalex.org/W4253928870","https://openalex.org/W4255712431","https://openalex.org/W4294087448","https://openalex.org/W4410693553","https://openalex.org/W6631190155","https://openalex.org/W6637415560","https://openalex.org/W6738491991","https://openalex.org/W6746059548"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2361247493","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2157330024","https://openalex.org/W2542062716","https://openalex.org/W2952979007","https://openalex.org/W1998374630","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"The":[0],"majority":[1],"of":[2,18,52,78],"deep":[3],"neural":[4],"network":[5],"(DNN)":[6],"based":[7,65,86],"speech":[8,32,41,53,75,80,140,152],"enhancement":[9,81],"algorithms":[10,82,85],"rely":[11],"on":[12,44,49,66,87],"the":[13,45,58,88,101,125,134,150],"mean-square":[14],"error":[15],"(MSE)":[16],"criterion":[17,64],"short-time":[19],"spectral":[20],"amplitudes":[21],"(STSA),":[22],"which":[23,144],"has":[24],"no":[25],"apparent":[26],"link":[27],"to":[28,73,84,114,137,149],"human":[29],"perception,":[30],"e.g.,":[31],"intelligibility.":[33],"Short-time":[34],"objective":[35,135],"intelligibility":[36,42,76,153],"(STOI),":[37],"a":[38,61,142],"popular":[39],"state-of-the-art":[40],"estimator,":[43],"other":[46],"hand,":[47],"relies":[48],"linear":[50,68],"correlation":[51,69],"temporal":[54],"envelopes.":[55],"This":[56],"raises":[57],"question":[59],"if":[60,133],"DNN":[62],"training":[63],"envelope":[67],"(ELC)":[70],"can":[71],"lead":[72],"improved":[74],"performance":[77],"DNN-based":[79],"compared":[83],"STSA-MSE":[89,102],"criterion.":[90],"In":[91],"this":[92],"paper,":[93],"we":[94,110],"derive":[95],"that,":[96],"under":[97],"certain":[98],"general":[99],"conditions,":[100],"and":[103,109],"ELC":[104],"criteria":[105],"are":[106],"practically":[107],"equivalent,":[108],"provide":[111],"empirical":[112],"data":[113],"support":[115],"our":[116,120],"theoretical":[117],"results.":[118],"Furthermore,":[119],"experimental":[121],"findings":[122],"suggest":[123],"that":[124],"standard":[126],"STSA":[127],"minimum-MSE":[128],"estimator":[129],"is":[130,136,145],"near":[131],"optimal,":[132],"enhance":[138],"noisy":[139],"in":[141],"manner,":[143],"optimal":[146],"with":[147],"respect":[148],"STOI":[151],"estimator.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2018-11-02T00:00:00"}