{"id":"https://openalex.org/W2550397165","doi":"https://doi.org/10.1109/taslp.2016.2628641","title":"Speech Intelligibility Potential of General and Specialized Deep Neural Network Based Speech Enhancement Systems","display_name":"Speech Intelligibility Potential of General and Specialized Deep Neural Network Based Speech Enhancement Systems","publication_year":2016,"publication_date":"2016-11-16","ids":{"openalex":"https://openalex.org/W2550397165","doi":"https://doi.org/10.1109/taslp.2016.2628641","mag":"2550397165"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2628641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2628641","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/A5110456236","display_name":"Morten Kolbk","orcid":null},"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":null,"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":null,"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":["Oticon A/S, Smørum, Denmark","Department of Electronic Systems, Aalborg University, Aalborg, Denmark","Oticon A/S, Sm\u00f8rum, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oticon A/S, Smørum, Denmark","institution_ids":["https://openalex.org/I4210130492"]},{"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":21.7566,"has_fulltext":false,"cited_by_count":215,"citation_normalized_percentile":{"value":0.99679874,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"25","issue":"1","first_page":"153","last_page":"167"},"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":0.998199999332428,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7267903089523315},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7256277203559875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6696593761444092},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6592190265655518},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5627639293670654},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5212646126747131},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5210561156272888},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5132460594177246},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4967663884162903},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4773421585559845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32270190119743347},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18843072652816772},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10174709558486938},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08089908957481384}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7267903089523315},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7256277203559875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6696593761444092},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6592190265655518},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5627639293670654},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5212646126747131},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5210561156272888},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5132460594177246},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4967663884162903},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4773421585559845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32270190119743347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18843072652816772},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10174709558486938},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08089908957481384},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2016.2628641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2628641","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:publications/6848bcd9-66ef-4298-af10-93941189ea47","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/6848bcd9-66ef-4298-af10-93941189ea47","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kolb\u00e6k , M , Tan , Z-H & Jensen , J 2017 , ' Speech Intelligibility Potential of General and Specialized Deep Neural Network Based Speech Enhancement Systems ' , I E E E Transactions on Audio, Speech and Language Processing , vol. 25 , no. 1 , pp. 153 - 167 . https://doi.org/10.1109/TASLP.2016.2628641","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320324626","display_name":"Oticon Fonden","ror":"https://ror.org/02x3xhs38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W189850294","https://openalex.org/W190004713","https://openalex.org/W1495679096","https://openalex.org/W1506806321","https://openalex.org/W1516630152","https://openalex.org/W1533861849","https://openalex.org/W1552314771","https://openalex.org/W1569068623","https://openalex.org/W1665214252","https://openalex.org/W1790748249","https://openalex.org/W1794826295","https://openalex.org/W1893876709","https://openalex.org/W1904365287","https://openalex.org/W1922655562","https://openalex.org/W1963970749","https://openalex.org/W1971281497","https://openalex.org/W1976951404","https://openalex.org/W1989364685","https://openalex.org/W1993882792","https://openalex.org/W2007790905","https://openalex.org/W2015469795","https://openalex.org/W2017608047","https://openalex.org/W2030680983","https://openalex.org/W2044893557","https://openalex.org/W2057200980","https://openalex.org/W2062164080","https://openalex.org/W2069681747","https://openalex.org/W2070154210","https://openalex.org/W2071387240","https://openalex.org/W2075616650","https://openalex.org/W2078528584","https://openalex.org/W2085191029","https://openalex.org/W2103018059","https://openalex.org/W2109215269","https://openalex.org/W2109306957","https://openalex.org/W2110798204","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2131753991","https://openalex.org/W2135029798","https://openalex.org/W2135284480","https://openalex.org/W2135823751","https://openalex.org/W2141892084","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2146502635","https://openalex.org/W2147299274","https://openalex.org/W2156488408","https://openalex.org/W2162052745","https://openalex.org/W2168379380","https://openalex.org/W2193413348","https://openalex.org/W2227273290","https://openalex.org/W2259731387","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2294792059","https://openalex.org/W2304609584","https://openalex.org/W2364134690","https://openalex.org/W2402901296","https://openalex.org/W2509674098","https://openalex.org/W2515930231","https://openalex.org/W2561557072","https://openalex.org/W2586068394","https://openalex.org/W2626775259","https://openalex.org/W2914048585","https://openalex.org/W2919115771","https://openalex.org/W2949640717","https://openalex.org/W2962946126","https://openalex.org/W3124794156","https://openalex.org/W3147539069","https://openalex.org/W4212863985","https://openalex.org/W4233392025","https://openalex.org/W4253928870","https://openalex.org/W6631943919","https://openalex.org/W6637242042","https://openalex.org/W6640036494","https://openalex.org/W6640090968","https://openalex.org/W6676481782","https://openalex.org/W6680012447","https://openalex.org/W6681435938","https://openalex.org/W6687566353","https://openalex.org/W6692000528","https://openalex.org/W6713117669","https://openalex.org/W6739898779"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2135485548","https://openalex.org/W3042618827","https://openalex.org/W2373767407","https://openalex.org/W2187949121"],"abstract_inverted_index":{"In":[0,208],"this":[1],"paper,":[2],"we":[3,19,48,92,164,210],"study":[4],"aspects":[5],"of":[6,24,38,145,194,205,225,231,246],"single":[7],"microphone":[8],"speech":[9,151,155],"enhancement":[10],"(SE)":[11],"based":[12,74,123,238],"on":[13],"deep":[14],"neural":[15],"networks":[16],"(DNNs).":[17],"Specifically,":[18],"explore":[20],"the":[21,32,36,39,43,203,206],"generalizability":[22],"capabilities":[23],"state-of-the-art":[25,114,236],"DNN-based":[26,52,96,129,178,214,258],"SE":[27,53,75,97,124,130,179,215,239,259],"systems":[28,76,260,269],"with":[29],"respect":[30],"to":[31,59,72,81,100,112,135,183],"background":[33],"noise":[34,62,83,102,139,188,197,232,250,277],"type,":[35],"gender":[37],"target":[40],"speaker,":[41],"and":[42,88,107,141,154,171,187,196,227,249,276],"signal-to-noise":[44],"ratio":[45],"(SNR).":[46],"Furthermore,":[47,163],"investigate":[49],"how":[50,94],"specialized":[51],"systems,":[54,131],"which":[55],"have":[56,78,199],"been":[57,79,200,219],"trained":[58,80,99,133,220],"be":[60,82,101,174],"either":[61],"type":[63,84,103,278],"specific,":[64,69],"speaker":[65,86,105,264],"specific":[66],"or":[67],"SNR":[68,89,108,275],"perform":[70],"relative":[71,111],"DNN":[73],"that":[77,128,166,212,217,267],"general,":[85,87,104,106],"general.":[90],"Finally,":[91,252],"compare":[93],"a":[95,113,177,191,213,222,228,235,244,253],"system":[98,180,216],"general":[109],"performs":[110],"short-time":[115],"spectral":[116],"amplitude":[117],"minimum":[118],"mean":[119],"square":[120],"error":[121],"(STSA-MMSE)":[122],"algorithm.":[125],"We":[126],"show":[127,165,211,266],"when":[132,158,181,241],"specifically":[134],"handle":[136],"certain":[137],"speakers,":[138,185],"types":[140,198,233],"SNRs,":[142],"are":[143],"capable":[144],"achieving":[146],"large":[147,192,223],"improvements":[148,167],"in":[149,160,168,202,262],"estimated":[150,169],"quality":[152],"(SQ)":[153],"intelligibility":[156],"(SI),":[157],"tested":[159,242,261],"matched":[161],"conditions.":[162],"SQ":[170],"SI":[172,272,282],"can":[173,270],"achieved":[175],"by":[176],"exposed":[182],"unseen":[184,247,263],"genders":[186],"types,":[189],"given":[190],"number":[193,224],"speakers":[195,226,248],"used":[201],"training":[204],"system.":[207],"addition,":[209],"has":[218],"using":[221,243,256],"wide":[229],"range":[230,245],"outperforms":[234],"STSA-MMSE":[237],"method,":[240],"types.":[251],"listening":[254],"test":[255],"several":[257],"conditions":[265],"these":[268],"improve":[271],"for":[273,283],"some":[274],"configurations":[279],"but":[280],"degrade":[281],"others.":[284]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":33},{"year":2017,"cited_by_count":20}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}