{"id":"https://openalex.org/W2890820256","doi":"https://doi.org/10.1109/taslp.2018.2870725","title":"Two-Stage Deep Learning for Noisy-Reverberant Speech Enhancement","display_name":"Two-Stage Deep Learning for Noisy-Reverberant Speech Enhancement","publication_year":2018,"publication_date":"2018-09-17","ids":{"openalex":"https://openalex.org/W2890820256","doi":"https://doi.org/10.1109/taslp.2018.2870725","mag":"2890820256","pmid":"https://pubmed.ncbi.nlm.nih.gov/31106230"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2870725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2870725","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","pubmed"],"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/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8595-3297","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-4204-9430","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":8.5292,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.9847651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"27","issue":"1","first_page":"53","last_page":"62"},"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":0.9987000226974487,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.784313440322876},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7677951455116272},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7651936411857605},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7476578950881958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7389832139015198},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4388566017150879},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4376770257949829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41259488463401794},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14101016521453857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784313440322876},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7677951455116272},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7651936411857605},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7476578950881958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7389832139015198},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4388566017150879},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4376770257949829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41259488463401794},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14101016521453857},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2018.2870725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2870725","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":"pmid:31106230","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31106230","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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":null},{"id":"pmh:oai:europepmc.org:5891745","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6519714","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G8822322065","display_name":null,"funder_award_id":"FA9550-12-1-0130","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W30237829","https://openalex.org/W1230632900","https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1516630152","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1836465849","https://openalex.org/W1973669708","https://openalex.org/W1983108229","https://openalex.org/W1989364685","https://openalex.org/W1992475611","https://openalex.org/W2006129368","https://openalex.org/W2007673756","https://openalex.org/W2010275911","https://openalex.org/W2045956438","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2095072097","https://openalex.org/W2095705004","https://openalex.org/W2117678320","https://openalex.org/W2120847449","https://openalex.org/W2122982914","https://openalex.org/W2136682440","https://openalex.org/W2141998673","https://openalex.org/W2144786298","https://openalex.org/W2156387975","https://openalex.org/W2164502538","https://openalex.org/W2165899180","https://openalex.org/W2168379380","https://openalex.org/W2223947752","https://openalex.org/W2345844407","https://openalex.org/W2364134690","https://openalex.org/W2379331960","https://openalex.org/W2404892923","https://openalex.org/W2476521382","https://openalex.org/W2514722735","https://openalex.org/W2542605056","https://openalex.org/W2561557072","https://openalex.org/W2609317876","https://openalex.org/W2635471793","https://openalex.org/W2962866211","https://openalex.org/W2963285578","https://openalex.org/W2964121744","https://openalex.org/W3124794156","https://openalex.org/W4231807801","https://openalex.org/W4253928870","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6682889407","https://openalex.org/W6685562342"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W2231565466","https://openalex.org/W3043214604","https://openalex.org/W1505346162"],"abstract_inverted_index":{"In":[0,42,74],"real-world":[1],"situations,":[2],"speech":[3,22,38,134],"reaching":[4],"our":[5],"ears":[6],"is":[7,111],"commonly":[8],"corrupted":[9,61],"by":[10],"both":[11],"room":[12],"reverberation":[13],"and":[14,24,26,39,52,65,123,136,139],"background":[15],"noise.":[16],"These":[17],"distortions":[18],"are":[19,67],"detrimental":[20],"to":[21,32,44,59,89,115],"intelligibility":[23,135],"quality,":[25],"also":[27],"pose":[28],"a":[29,56,78],"serious":[30],"problem":[31],"many":[33],"speech-related":[34],"applications,":[35],"including":[36],"automatic":[37],"speaker":[40],"recognition.":[41],"order":[43],"deal":[45],"with":[46,104],"the":[47,117,127],"combined":[48,103],"effects":[49],"of":[50,133],"noise":[51],"reverberation,":[53],"we":[54,76],"propose":[55],"two-stage":[57,109],"strategy":[58],"enhance":[60],"speech,":[62],"where":[63],"denoising":[64],"dereverberation":[66],"conducted":[68],"sequentially":[69],"using":[70],"deep":[71],"neural":[72],"networks.":[73],"addition,":[75],"design":[77],"new":[79],"objective":[80,119,131],"function":[81],"that":[82,126],"incorporates":[83],"clean":[84],"phase":[85,100,106],"during":[86],"model":[87,110],"training":[88],"better":[90,99],"estimate":[91],"spectral":[92],"magnitudes,":[93],"which":[94],"would":[95],"in":[96],"turn":[97],"yield":[98],"estimates":[101],"when":[102],"iterative":[105],"reconstruction.":[107],"The":[108],"then":[112],"jointly":[113],"trained":[114],"optimize":[116],"proposed":[118,128],"function.":[120],"Systematic":[121],"evaluations":[122],"comparisons":[124],"show":[125],"algorithm":[129],"improves":[130],"metrics":[132],"quality":[137],"substantially,":[138],"significantly":[140],"outperforms":[141],"previous":[142],"one-stage":[143],"enhancement":[144],"systems.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}