{"id":"https://openalex.org/W2635471793","doi":"https://doi.org/10.1109/icassp.2017.7953224","title":"A two-stage algorithm for noisy and reverberant speech enhancement","display_name":"A two-stage algorithm for noisy and reverberant speech enhancement","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2635471793","doi":"https://doi.org/10.1109/icassp.2017.7953224","mag":"2635471793"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/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":true,"raw_author_name":"Yan Zhao","raw_affiliation_strings":["DNN. of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"DNN. of Computer Science and Engineering, The Ohio State University, 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":["DNN. of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"DNN. of Computer Science and Engineering, The Ohio State University, 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":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076372893"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":5.7327,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96908853,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5580","last_page":"5584"},"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":0.9993000030517578,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.8152309060096741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7860490083694458},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7383926510810852},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7083237171173096},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7046226263046265},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5804992914199829},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.429060697555542},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41059818863868713},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4050959050655365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3250640630722046},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.131591796875}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8152309060096741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860490083694458},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7383926510810852},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7083237171173096},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7046226263046265},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5804992914199829},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.429060697555542},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41059818863868713},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4050959050655365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3250640630722046},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.131591796875},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W30237829","https://openalex.org/W1230632900","https://openalex.org/W1482149378","https://openalex.org/W1516630152","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1989364685","https://openalex.org/W1992475611","https://openalex.org/W2006129368","https://openalex.org/W2010275911","https://openalex.org/W2031647436","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2095705004","https://openalex.org/W2117678320","https://openalex.org/W2120847449","https://openalex.org/W2122982914","https://openalex.org/W2141998673","https://openalex.org/W2144786298","https://openalex.org/W2156387975","https://openalex.org/W2168379380","https://openalex.org/W2176412452","https://openalex.org/W2345844407","https://openalex.org/W2364134690","https://openalex.org/W2379331960","https://openalex.org/W2398264106","https://openalex.org/W2404892923","https://openalex.org/W2949117887","https://openalex.org/W2963285578","https://openalex.org/W4231807801","https://openalex.org/W6601235113","https://openalex.org/W6628167197","https://openalex.org/W6674330103","https://openalex.org/W6682889407"],"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/W2092735486","https://openalex.org/W2156376969","https://openalex.org/W2117416982","https://openalex.org/W3108403339"],"abstract_inverted_index":{"In":[0,36,66],"daily":[1],"listening":[2],"environments,":[3],"speech":[4,19,31,116],"is":[5,94],"commonly":[6],"corrupted":[7],"by":[8],"room":[9],"reverberation":[10,53],"and":[11,21,23,32,52,57,118,121],"background":[12],"noise.":[13],"These":[14],"distortions":[15],"are":[16,59],"detrimental":[17],"to":[18,44,104],"intelligibility":[20,117],"quality,":[22],"also":[24],"severely":[25],"degrade":[26],"the":[27,47,82,101,106],"performance":[28],"of":[29,50,115],"automatic":[30],"speaker":[33],"recognition":[34],"systems.":[35],"this":[37],"paper,":[38],"we":[39,68],"propose":[40],"a":[41,70],"two-stage":[42,102],"algorithm":[43,111],"deal":[45],"with":[46],"confounding":[48],"effects":[49],"noise":[51],"separately,":[54],"where":[55],"denoising":[56],"dereverberation":[58],"conducted":[60],"sequentially":[61],"using":[62],"deep":[63],"neural":[64],"networks.":[65],"addition,":[67],"design":[69],"new":[71],"objective":[72,83,108,113],"function":[73,84],"that":[74],"incorporates":[75],"clean":[76],"phase":[77],"information":[78],"during":[79,96],"training.":[80],"As":[81],"emphasizes":[85],"more":[86],"important":[87],"time-frequency":[88],"(T-F)":[89],"units,":[90],"better":[91],"estimated":[92],"magnitude":[93],"obtained":[95],"testing.":[97],"By":[98],"jointly":[99],"training":[100],"model":[103],"optimize":[105],"proposed":[107],"function,":[109],"our":[110],"improves":[112],"metrics":[114],"quality":[119],"significantly,":[120],"substantially":[122],"outperforms":[123],"one-stage":[124],"enhancement":[125],"baselines.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}