{"id":"https://openalex.org/W2538939196","doi":"https://doi.org/10.1109/iwaenc.2016.7602954","title":"Perceptual improvement of deep neural networks for monaural speech enhancement","display_name":"Perceptual improvement of deep neural networks for monaural speech enhancement","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2538939196","doi":"https://doi.org/10.1109/iwaenc.2016.7602954","mag":"2538939196"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2016.7602954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2016.7602954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 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/A5101655190","display_name":"Wei Han","orcid":"https://orcid.org/0000-0003-0154-5574"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011581435","display_name":"Xiongwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongwei Zhang","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085248515","display_name":"Meng Sun","orcid":"https://orcid.org/0000-0002-7435-3752"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Sun","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102107430","display_name":"Wenhua Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]},{"id":"https://openalex.org/I4210167232","display_name":"PLA Air Force Aviation University","ror":"https://ror.org/031g2ra50","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210167232"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhua Shi","raw_affiliation_strings":["Flight Instructor Training Base, Air Force Aviation University, Bengbu, China","Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Flight Instructor Training Base, Air Force Aviation University, Bengbu, China","institution_ids":["https://openalex.org/I4210167232"]},{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088216433","display_name":"Xushan Chen","orcid":"https://orcid.org/0000-0002-3665-5653"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xushan Chen","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012959870","display_name":"Yonggang Hu","orcid":"https://orcid.org/0000-0003-0414-8697"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonggang Hu","raw_affiliation_strings":["Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lab of Intelligent Information Processing, PLA University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.021,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77965406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9973000288009644,"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":0.9947999715805054,"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/monaural","display_name":"Monaural","score":0.9341037273406982},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7890199422836304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7447261214256287},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6718800067901611},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6648095846176147},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6202061176300049},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.49901652336120605},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.4830132722854614},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4802411198616028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45558270812034607},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4394492208957672},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3916561007499695},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2645260691642761},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.19237452745437622},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11418697237968445}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9341037273406982},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7890199422836304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447261214256287},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6718800067901611},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6648095846176147},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6202061176300049},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.49901652336120605},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.4830132722854614},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4802411198616028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45558270812034607},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4394492208957672},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3916561007499695},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2645260691642761},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.19237452745437622},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11418697237968445},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc.2016.7602954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2016.7602954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W176628998","https://openalex.org/W258661521","https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1968939597","https://openalex.org/W1994891831","https://openalex.org/W2013608223","https://openalex.org/W2044893557","https://openalex.org/W2051428568","https://openalex.org/W2069681747","https://openalex.org/W2096698681","https://openalex.org/W2102017903","https://openalex.org/W2111714711","https://openalex.org/W2117105730","https://openalex.org/W2130178255","https://openalex.org/W2167873188","https://openalex.org/W2291877678","https://openalex.org/W3124794156","https://openalex.org/W6607218105","https://openalex.org/W6609686331","https://openalex.org/W6675112735"],"related_works":["https://openalex.org/W1966225096","https://openalex.org/W3010327795","https://openalex.org/W4229003981","https://openalex.org/W2138406058","https://openalex.org/W2892198678","https://openalex.org/W3009491306","https://openalex.org/W2902298602","https://openalex.org/W2418631473","https://openalex.org/W2902061565","https://openalex.org/W2671186495"],"abstract_inverted_index":{"Monaural":[0],"speech":[1,19,45,119],"enhancement":[2,20,120],"is":[3,62,70],"a":[4,39,58],"key":[5],"yet":[6],"challenging":[7],"problem":[8],"for":[9,43],"many":[10],"important":[11],"real":[12],"world":[13],"applications.":[14],"Recently,":[15],"deep":[16],"neural":[17],"networks(DNNs)-based":[18],"methods,":[21,121],"which":[22,69],"extract":[23],"useful":[24],"feature":[25],"from":[26],"complex":[27],"feature,":[28],"have":[29],"demonstrated":[30],"remarkable":[31],"performance":[32],"improvement.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"present":[38],"novel":[40],"DNN":[41,67,115],"architecture":[42,85],"monaural":[44],"enhancement.":[46],"Taking":[47],"into":[48],"account":[49],"the":[50,54,65,74,78,88,110,113,117,125,131],"masking":[51],"properties":[52],"of":[53,112],"human":[55],"auditory":[56],"system,":[57],"piecewise":[59,89],"gain":[60,90],"function":[61,91],"applied":[63],"in":[64,124,130],"proposed":[66,84,114],"architecture,":[68],"used":[71],"to":[72],"reduce":[73],"noise":[75,80,101,127,133],"and":[76,92],"make":[77],"residual":[79],"perceptually":[81],"inaudible.":[82],"The":[83],"jointly":[86],"optimize":[87],"DNN.":[93],"Systematic":[94],"experiments":[95],"on":[96],"TIMIT":[97],"corpus":[98],"with":[99],"20":[100],"types":[102],"at":[103],"various":[104],"signal-to-noise":[105],"ratio":[106],"(SNR)":[107],"conditions":[108,128],"demonstrate":[109],"superiority":[111],"over":[116],"reference":[118],"no":[122],"matter":[123],"matched":[126],"or":[129],"unmatched":[132],"conditions.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}