{"id":"https://openalex.org/W2891607145","doi":"https://doi.org/10.1109/icassp.2018.8462593","title":"Perceptually Guided Speech Enhancement Using Deep Neural Networks","display_name":"Perceptually Guided Speech Enhancement Using Deep Neural Networks","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891607145","doi":"https://doi.org/10.1109/icassp.2018.8462593","mag":"2891607145"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":["Department of Computer Science and Engineering, The Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"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":"Buye Xu","raw_affiliation_strings":["Starkey Hearing Technologies, USA"],"affiliations":[{"raw_affiliation_string":"Starkey Hearing Technologies, USA","institution_ids":["https://openalex.org/I4210137835"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091775011","display_name":"Ritwik Giri","orcid":"https://orcid.org/0000-0002-8599-3229"},"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":"Ritwik Giri","raw_affiliation_strings":["Starkey Hearing Technologies, USA"],"affiliations":[{"raw_affiliation_string":"Starkey Hearing Technologies, 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":["Starkey Hearing Technologies, USA"],"affiliations":[{"raw_affiliation_string":"Starkey Hearing Technologies, 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/I52357470"],"apc_list":null,"apc_paid":null,"fwci":8.4576,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.98406504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5074","last_page":"5078"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9984999895095825,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8331073522567749},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7920874357223511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.756131112575531},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7063010334968567},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5845293998718262},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5261915326118469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4292800724506378},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41388750076293945},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4133501946926117},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3208824098110199},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2891766428947449},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14193347096443176},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07048743963241577}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8331073522567749},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7920874357223511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756131112575531},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7063010334968567},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5845293998718262},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5261915326118469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4292800724506378},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41388750076293945},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4133501946926117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3208824098110199},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2891766428947449},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14193347096443176},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07048743963241577},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1516630152","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1974387177","https://openalex.org/W1992475611","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2095705004","https://openalex.org/W2105921478","https://openalex.org/W2121061347","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2176412452","https://openalex.org/W2291877678","https://openalex.org/W2635471793","https://openalex.org/W2696558042","https://openalex.org/W2963285578","https://openalex.org/W4231807801","https://openalex.org/W6674330103","https://openalex.org/W6739504299","https://openalex.org/W6740595283"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Human":[0],"listeners":[1],"often":[2,42],"have":[3,24],"difficulties":[4],"understanding":[5,79],"speech":[6,21,73,78,98,133,147,161],"in":[7,13,80,113,116,149],"the":[8,14,33,46,51,55,60,69,102,108,114,119,124],"presence":[9],"of":[10,64,71,153],"background":[11],"noise":[12,157],"real":[15],"world.":[16],"Recently,":[17],"supervised":[18,38],"learning":[19,39],"based":[20,40,92],"enhancement":[22,74,93],"approaches":[23,41],"achieved":[25],"substantial":[26],"success,":[27],"and":[28,54,156],"show":[29,138],"significant":[30],"improvements":[31],"over":[32],"conventional":[34],"approaches.":[35],"However,":[36],"existing":[37],"try":[43],"to":[44,76,118,131,145],"minimize":[45],"mean":[47,120],"squared":[48,121],"error":[49],"between":[50],"enhanced":[52],"output":[53],"pre-defined":[56],"training":[57],"target":[58],"(e.g.,":[59],"log":[61],"power":[62],"spectrum":[63],"clean":[65],"speech),":[66],"even":[67],"though":[68],"purpose":[70],"such":[72],"is":[75,129,143],"improve":[77,132,146],"noise.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,106],"propose":[86],"a":[87,97,150],"new":[88],"deep":[89],"neural":[90],"networks":[91],"approach":[94,142],"by":[95],"incorporating":[96],"perception":[99],"model":[100],"into":[101],"loss":[103,115,128],"function.":[104],"Specifically,":[105],"use":[107],"short-time":[109],"objective":[110],"intelligibility":[111,134,148],"metric":[112],"addition":[117],"error.":[122],"Optimizing":[123],"proposed":[125,141],"perceptually":[126],"guided":[127],"expected":[130],"further.":[135],"Systematic":[136],"evaluations":[137],"that":[139],"our":[140],"able":[144],"wide":[151],"range":[152],"signal-to-noise":[154],"ratios":[155],"types":[158],"while":[159],"maintaining":[160],"quality.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}