{"id":"https://openalex.org/W2963351212","doi":"https://doi.org/10.1109/icassp.2018.8462040","title":"Monaural Speech Enhancement Using Deep Neural Networks by Maximizing a Short-Time Objective Intelligibility Measure","display_name":"Monaural Speech Enhancement Using Deep Neural Networks by Maximizing a Short-Time Objective Intelligibility Measure","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2963351212","doi":"https://doi.org/10.1109/icassp.2018.8462040","mag":"2963351212"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/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 Kolbaek","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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5059","last_page":"5063"},"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":0.9987000226974487,"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":0.9968000054359436,"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":0.8981927633285522},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7126830816268921},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.656592845916748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6370511054992676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5942684412002563},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5710035562515259},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4106958210468292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3816032409667969},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22276023030281067}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8981927633285522},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7126830816268921},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.656592845916748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6370511054992676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5942684412002563},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5710035562515259},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4106958210468292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3816032409667969},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22276023030281067},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1503566218","https://openalex.org/W1707086801","https://openalex.org/W1893876709","https://openalex.org/W1973746598","https://openalex.org/W2030680983","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2071387240","https://openalex.org/W2101042021","https://openalex.org/W2121973264","https://openalex.org/W2135284480","https://openalex.org/W2138406058","https://openalex.org/W2141998673","https://openalex.org/W2146544734","https://openalex.org/W2156488408","https://openalex.org/W2158185319","https://openalex.org/W2159373586","https://openalex.org/W2168379380","https://openalex.org/W2181607856","https://openalex.org/W2364134690","https://openalex.org/W2465704452","https://openalex.org/W2516001803","https://openalex.org/W2517760955","https://openalex.org/W2524708987","https://openalex.org/W2550397165","https://openalex.org/W2586068394","https://openalex.org/W2622055663","https://openalex.org/W2696558042","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W4410693553","https://openalex.org/W6630192472","https://openalex.org/W6637415560","https://openalex.org/W6682123162","https://openalex.org/W6727749278"],"related_works":["https://openalex.org/W2401567014","https://openalex.org/W2538939196","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,94,126],"propose":[4],"a":[5,111,115,137],"Deep":[6],"Neural":[7],"Network":[8],"(D":[9],"NN)":[10],"based":[11,60,140,164],"Speech":[12],"Enhancement":[13],"(SE)":[14],"system":[15,72,112,132,147],"that":[16,49,68,96,128,161],"is":[17],"designed":[18],"to":[19,121],"maximize":[20],"an":[21,32,103],"approximation":[22],"of":[23,150,173],"the":[24,41,69,97,129],"Short-Time":[25],"Objective":[26],"Intelligibility":[27],"(STOI)":[28],"measure.":[29],"We":[30,63],"formalize":[31],"approximate-STOI":[33,104],"cost":[34,105,119],"function":[35,106],"and":[36,47,84],"derive":[37],"analytical":[38],"expressions":[39],"for":[40,44],"gradients":[42,51],"required":[43],"DNN":[45,139,163],"training":[46],"show":[48,64,95,127],"these":[50],"have":[52],"desirable":[53],"properties":[54],"when":[55,80,100],"used":[56],"together":[57],"with":[58,110,114,136],"gradient":[59],"optimization":[61],"techniques.":[62],"through":[65],"simulation":[66],"experiments":[67],"proposed":[70,130],"SE":[71,98,131,146,166],"achieves":[73],"large":[74],"improvements":[75],"in":[76,148,171],"estimated":[77,151,174],"speech":[78,152,175],"intelligibility,":[79],"tested":[81],"on":[82,108,134],"matched":[83],"unmatched":[85],"natural":[86],"noise":[87],"types,":[88],"at":[89],"multiple":[90],"signal-to-noise":[91],"ratios.":[92],"Furthermore,":[93],"system,":[99],"trained":[101,113],"using":[102],"performs":[107,133],"par":[109,135],"mean":[116],"square":[117],"error":[118],"applied":[120],"short-time":[122],"temporal":[123],"envelopes.":[124],"Finally,":[125],"traditional":[138,162],"Short-":[141],"Time":[142],"Spectral":[143],"Amplitude":[144],"(STSA)":[145],"terms":[149,172],"intelligibility.":[153,176],"These":[154],"results":[155],"are":[156],"important":[157],"because":[158],"they":[159],"suggest":[160],"STSA":[165],"systems":[167],"might":[168],"be":[169],"optimal":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
