{"id":"https://openalex.org/W2404892923","doi":"https://doi.org/10.1109/icassp.2016.7472934","title":"DNN-based enhancement of noisy and reverberant speech","display_name":"DNN-based enhancement of noisy and reverberant speech","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2404892923","doi":"https://doi.org/10.1109/icassp.2016.7472934","mag":"2404892923"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5076372893","display_name":"Yan Zhao","orcid":"https://orcid.org/0000-0001-8595-3297"},"institutions":[{"id":"https://openalex.org/I4210137835","display_name":"Starkey Hearing Technologies (United States)","ror":"https://ror.org/02yhzgr66","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137835"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yan Zhao","raw_affiliation_strings":["Department of Computer Science & Engineering, Starkey Hearing Technologies, Eden Prairie, MN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Starkey Hearing Technologies, Eden Prairie, MN, USA","institution_ids":["https://openalex.org/I4210137835"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]},{"id":"https://openalex.org/I4210137835","display_name":"Starkey Hearing Technologies (United States)","ror":"https://ror.org/02yhzgr66","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137835"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","Department of Computer Science & Engineering, Starkey Hearing Technologies, Eden Prairie, MN, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science & Engineering, Starkey Hearing Technologies, Eden Prairie, MN, USA","institution_ids":["https://openalex.org/I4210137835"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066184905","display_name":"Ivo Merks","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137835","display_name":"Starkey Hearing Technologies (United States)","ror":"https://ror.org/02yhzgr66","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137835"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivo Merks","raw_affiliation_strings":["Department of Computer Science & Engineering, Starkey Hearing Technologies, Eden Prairie, MN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Starkey Hearing Technologies, Eden Prairie, MN, USA","institution_ids":["https://openalex.org/I4210137835"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100375823","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-6272-4069"},"institutions":[{"id":"https://openalex.org/I4210137835","display_name":"Starkey Hearing Technologies (United States)","ror":"https://ror.org/02yhzgr66","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137835"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Department of Computer Science & Engineering, Starkey Hearing Technologies, Eden Prairie, MN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, Starkey Hearing Technologies, Eden Prairie, MN, USA","institution_ids":["https://openalex.org/I4210137835"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076372893"],"corresponding_institution_ids":["https://openalex.org/I4210137835"],"apc_list":null,"apc_paid":null,"fwci":6.3045,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.97207336,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6525","last_page":"6529"},"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":0.9990000128746033,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-recognition","display_name":"Speech recognition","score":0.7939470410346985},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7910008430480957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7520318031311035},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.681317925453186},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6523095369338989},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5280300378799438},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5157713890075684},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.4727374315261841},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4277772009372711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38562387228012085},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.36294692754745483},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19785520434379578},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0632530152797699}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7939470410346985},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7910008430480957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7520318031311035},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.681317925453186},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6523095369338989},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5280300378799438},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5157713890075684},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.4727374315261841},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4277772009372711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38562387228012085},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.36294692754745483},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19785520434379578},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0632530152797699},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1973669708","https://openalex.org/W1973681148","https://openalex.org/W1989364685","https://openalex.org/W2006129368","https://openalex.org/W2007673756","https://openalex.org/W2010275911","https://openalex.org/W2040782121","https://openalex.org/W2054480978","https://openalex.org/W2055611715","https://openalex.org/W2057200980","https://openalex.org/W2063669828","https://openalex.org/W2066755975","https://openalex.org/W2069681747","https://openalex.org/W2112748425","https://openalex.org/W2117678320","https://openalex.org/W2122982914","https://openalex.org/W2133908567","https://openalex.org/W2141998673","https://openalex.org/W2144786298","https://openalex.org/W2146502635","https://openalex.org/W2156387975","https://openalex.org/W2167314872","https://openalex.org/W2168610508","https://openalex.org/W4231807801","https://openalex.org/W6680017764","https://openalex.org/W6681435938","https://openalex.org/W6682889407"],"related_works":["https://openalex.org/W2732511158","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/W4256175191","https://openalex.org/W2770624987","https://openalex.org/W2135485548"],"abstract_inverted_index":{"In":[0,14,81],"the":[1,37,88,113,117,144,152,156],"real":[2],"world,":[3],"speech":[4,17,35,67,78,92,100,124],"is":[5,19,31,120],"usually":[6],"distorted":[7],"by":[8,93],"both":[9],"reverberation":[10],"and":[11,39,58,65,90,112,140],"background":[12],"noise.":[13],"such":[15],"conditions,":[16],"intelligibility":[18,79,125],"degraded":[20],"substantially,":[21],"especially":[22],"for":[23,138],"hearing-impaired":[24],"(HI)":[25],"listeners.":[26],"As":[27],"a":[28,51,95,135],"consequence,":[29],"it":[30,142],"essential":[32],"to":[33,49,54,86,97,122],"enhance":[34,55,87],"in":[36,62,129],"noisy":[38,89],"reverberant":[40,91,98],"environment.":[41],"Recently,":[42],"deep":[43],"neural":[44],"networks":[45],"have":[46,73],"been":[47],"introduced":[48],"learn":[50],"spectral":[52,145],"mapping":[53,96,146],"corrupted":[56],"speech,":[57],"shown":[59,76],"significant":[60],"improvements":[61],"objective":[63],"metrics":[64],"automatic":[66],"recognition":[68],"score.":[69],"However,":[70],"listening":[71,108],"tests":[72],"not":[74],"yet":[75],"any":[77],"benefit.":[80],"this":[82],"paper,":[83],"we":[84,133],"propose":[85],"learning":[94],"target":[99,104],"rather":[101],"than":[102],"anechoic":[103],"speech.":[105],"A":[106],"preliminary":[107],"test":[109],"was":[110],"conducted,":[111],"results":[114,149],"show":[115,150],"that":[116,151],"proposed":[118],"algorithm":[119],"able":[121],"improve":[123],"of":[126],"HI":[127],"listeners":[128],"some":[130],"conditions.":[131],"Moreover,":[132],"develop":[134],"masking-based":[136,153],"method":[137,154],"denoising":[139],"compare":[141],"with":[143],"method.":[147,158],"Evaluation":[148],"outperforms":[155],"mapping-based":[157]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}