{"id":"https://openalex.org/W3010411659","doi":"https://doi.org/10.1109/icspcs47537.2019.9008709","title":"Monaural Speech Enhancement Based On Two Stage Long Short-Term Memory Networks","display_name":"Monaural Speech Enhancement Based On Two Stage Long Short-Term Memory Networks","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3010411659","doi":"https://doi.org/10.1109/icspcs47537.2019.9008709","mag":"3010411659"},"language":"en","primary_location":{"id":"doi:10.1109/icspcs47537.2019.9008709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs47537.2019.9008709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 13th International Conference on Signal Processing and Communication Systems (ICSPCS)","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/A5031139212","display_name":"Yang Xian","orcid":"https://orcid.org/0000-0002-3896-234X"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Xian","raw_affiliation_strings":["Intelligent Sensing and Communications Research Group, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714901","display_name":"Yang Sun","orcid":"https://orcid.org/0000-0002-5483-0953"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Sun","raw_affiliation_strings":["Intelligent Sensing and Communications Research Group, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053121936","display_name":"Syed Mohsen Naqvi","orcid":"https://orcid.org/0000-0002-1547-0908"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syed Mohsen Naqvi","raw_affiliation_strings":["Intelligent Sensing and Communications Research Group, Newcastle University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University, UK","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1669,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49595228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"21","issue":null,"first_page":"1","last_page":"5"},"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":0.9970999956130981,"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":0.9965999722480774,"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/monaural","display_name":"Monaural","score":0.9466322064399719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7978113889694214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.72991943359375},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6664102673530579},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5664382576942444},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5423205494880676},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4161965847015381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3914593458175659},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3562990128993988},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22708463668823242},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.11917364597320557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08730953931808472},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08161354064941406}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9466322064399719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978113889694214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.72991943359375},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6664102673530579},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5664382576942444},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5423205494880676},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4161965847015381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3914593458175659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3562990128993988},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22708463668823242},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.11917364597320557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08730953931808472},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08161354064941406},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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":1,"locations":[{"id":"doi:10.1109/icspcs47537.2019.9008709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcs47537.2019.9008709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 13th International Conference on Signal Processing and Communication Systems (ICSPCS)","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":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1790748249","https://openalex.org/W1974387177","https://openalex.org/W1992879732","https://openalex.org/W2018797163","https://openalex.org/W2034361824","https://openalex.org/W2069681747","https://openalex.org/W2079226880","https://openalex.org/W2088399049","https://openalex.org/W2096301647","https://openalex.org/W2104887782","https://openalex.org/W2127851351","https://openalex.org/W2142920810","https://openalex.org/W2167734090","https://openalex.org/W2291877678","https://openalex.org/W2678916739","https://openalex.org/W2776765712","https://openalex.org/W2897917529","https://openalex.org/W3122775348","https://openalex.org/W3124794156","https://openalex.org/W3127686677","https://openalex.org/W4231807801","https://openalex.org/W6684365440"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2538939196","https://openalex.org/W3045520545"],"abstract_inverted_index":{"The":[0,25,112],"performance":[1],"of":[2,37,119],"the":[3,22,32,35,60,63,78,83,86,94,103,108,117,120],"deep":[4],"neural":[5],"networks":[6],"(DNNs)":[7],"based":[8],"monaural":[9],"speech":[10,42,80,105,110],"enhancement":[11],"methods":[12],"is":[13,67,91,99],"still":[14],"limited":[15],"in":[16,34],"real":[17],"room":[18],"environments,":[19],"particularly":[20],"for":[21],"speaker-independent":[23],"case.":[24],"surface":[26],"reflections":[27],"and":[28],"unseen":[29],"speakers":[30],"increase":[31],"challenge":[33],"estimation":[36],"sources":[38],"from":[39,107],"reverberant":[40],"noisy":[41,79],"mixtures.":[43],"To":[44],"address":[45],"these":[46],"issues,":[47],"we":[48],"propose":[49],"a":[50,71],"two-stage":[51],"approach":[52],"using":[53,70],"long":[54],"short-term":[55],"memory":[56],"(LSTM)":[57],"networks.":[58],"In":[59,82],"first":[61],"stage,":[62,85],"dereverberation":[64],"mask":[65,89],"(DM)":[66],"obtained":[68],"by":[69,93],"trained":[72,96],"LSTM,":[73,97],"which":[74,98],"aims":[75],"to":[76,101],"dereverberate":[77],"mixture.":[81,111],"second":[84,95],"ideal":[87],"ratio":[88,114],"(IRM)":[90],"estimated":[92],"exploited":[100],"separate":[102],"desired":[104],"signal":[106],"dereverberated":[109],"signal-to-distortion":[113],"(SDR)":[115],"shows":[116],"efficacy":[118],"LSTMs":[121],"over":[122],"DNNs.":[123]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
