{"id":"https://openalex.org/W2899638089","doi":"https://doi.org/10.1109/iwaenc.2018.8521382","title":"Improving Statistical Model-Based Speech Enhancement with Deep Neural Networks","display_name":"Improving Statistical Model-Based Speech Enhancement with Deep Neural Networks","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2899638089","doi":"https://doi.org/10.1109/iwaenc.2018.8521382","mag":"2899638089"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5112168875","display_name":"Bengt Borgstr\u00f6m","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bengt J. Borgstrom","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086705866","display_name":"M.S. Brandstein","orcid":"https://orcid.org/0009-0008-7883-3658"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael S. Brandstein","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019766158","display_name":"R.B. Dunn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert B. Dunn","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112168875"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":0.6606,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70005967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"4","issue":null,"first_page":"471","last_page":"475"},"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":0.9977999925613403,"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":0.9955999851226807,"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-enhancement","display_name":"Speech enhancement","score":0.7783200740814209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622208595275879},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6624881625175476},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6024252772331238},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5638926029205322},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5487526059150696},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5347553491592407},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.5149286985397339},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.49406126141548157},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.47853025794029236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4374796450138092},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4363314211368561},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41524291038513184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3342530131340027},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2424880862236023},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1176043450832367},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09783676266670227},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09012767672538757}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7783200740814209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622208595275879},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6624881625175476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6024252772331238},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5638926029205322},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5487526059150696},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5347553491592407},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.5149286985397339},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.49406126141548157},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.47853025794029236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4374796450138092},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4363314211368561},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41524291038513184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3342530131340027},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2424880862236023},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1176043450832367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09783676266670227},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09012767672538757},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc.2018.8521382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1975301756","https://openalex.org/W1999401045","https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2051428568","https://openalex.org/W2058502470","https://openalex.org/W2069681747","https://openalex.org/W2101042021","https://openalex.org/W2109215269","https://openalex.org/W2112099742","https://openalex.org/W2121973264","https://openalex.org/W2128402994","https://openalex.org/W2144561273","https://openalex.org/W2146324387","https://openalex.org/W2149441837","https://openalex.org/W2153485077","https://openalex.org/W2158336491","https://openalex.org/W2219249508","https://openalex.org/W2394498270","https://openalex.org/W2510942155","https://openalex.org/W2542605056","https://openalex.org/W2624871570","https://openalex.org/W2963341071","https://openalex.org/W3127686677","https://openalex.org/W3147539069","https://openalex.org/W4302156456","https://openalex.org/W6677267349","https://openalex.org/W6711896204","https://openalex.org/W6735429107","https://openalex.org/W6739365718"],"related_works":["https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W4375869276","https://openalex.org/W3002068412","https://openalex.org/W1585241115","https://openalex.org/W2120213246","https://openalex.org/W3171883019"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,18,48,133],"framework":[4,65,112],"for":[5,44,69],"improving":[6],"the":[7,32,56,85,94,126],"performance":[8],"of":[9,72,96,105],"statistical":[10],"model-based":[11],"single-channel":[12],"speech":[13,29,92,118],"enhancement":[14],"systems":[15],"by":[16],"using":[17],"deep":[19],"neural":[20],"network":[21],"(DNN).":[22],"A":[23],"DNN":[24,86],"is":[25,38],"trained":[26,89],"to":[27,40,80,90,102,122],"predict":[28],"presence":[30,95],"in":[31,60,93,116,132],"input":[33],"signal,":[34],"and":[35,47,99,108,125],"this":[36],"information":[37],"leveraged":[39],"design":[41,74],"novel":[42],"methods":[43],"noise":[45,98,107],"tracking":[46],"priori":[49],"signal-to-noise":[50],"ratio":[51],"(SNR)":[52],"estimation,":[53,78],"which":[54],"remain":[55],"most":[57],"challenging":[58],"tasks":[59],"conventional":[61],"systems.":[62,83],"The":[63,110],"proposed":[64,111,127],"provides":[66,113],"increased":[67],"flexibility":[68],"various":[70],"aspects":[71],"system":[73,128],"such":[75],"as":[76],"gain":[77],"relative":[79,121],"end-to-end":[81],"DNN-based":[82],"Additionally,":[84],"can":[87],"be":[88],"detect":[91],"both":[97],"reverberation,":[100],"leading":[101],"joint":[103],"suppression":[104],"additive":[106],"reverberation.":[109],"significant":[114],"improvements":[115],"objective":[117],"quality":[119],"metrics":[120],"baseline":[123],"systems,":[124],"was":[129],"heavily":[130],"favored":[131],"subjective":[134],"preference":[135],"test.":[136]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}