{"id":"https://openalex.org/W3081608966","doi":"https://doi.org/10.1109/access.2020.3021061","title":"On Learning Spectral Masking for Single Channel Speech Enhancement Using Feedforward and Recurrent Neural Networks","display_name":"On Learning Spectral Masking for Single Channel Speech Enhancement Using Feedforward and Recurrent Neural Networks","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3081608966","doi":"https://doi.org/10.1109/access.2020.3021061","mag":"3081608966"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3021061","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3021061","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09183987.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09183987.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059780753","display_name":"Nasir Saleem","orcid":"https://orcid.org/0000-0003-0010-0629"},"institutions":[{"id":"https://openalex.org/I172324550","display_name":"Gomal University","ror":"https://ror.org/0241b8f19","country_code":"PK","type":"education","lineage":["https://openalex.org/I172324550"]},{"id":"https://openalex.org/I90610274","display_name":"University of Engineering and Technology Peshawar","ror":"https://ror.org/00p034093","country_code":"PK","type":"education","lineage":["https://openalex.org/I90610274"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Nasir Saleem","raw_affiliation_strings":["Department of Electrical Engineering, Faculty of Engineering and Technology (FET), Gomal University, Dera Ismail Khan, Pakistan","Department of Electrical Engineering, University of Engineering and Technology, Peshawar, Pakistan"],"raw_orcid":"https://orcid.org/0000-0003-0010-0629","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Faculty of Engineering and Technology (FET), Gomal University, Dera Ismail Khan, Pakistan","institution_ids":["https://openalex.org/I172324550"]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Engineering and Technology, Peshawar, Pakistan","institution_ids":["https://openalex.org/I90610274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089398004","display_name":"Muhammad Irfan Khattak","orcid":"https://orcid.org/0000-0003-4655-938X"},"institutions":[{"id":"https://openalex.org/I90610274","display_name":"University of Engineering and Technology Peshawar","ror":"https://ror.org/00p034093","country_code":"PK","type":"education","lineage":["https://openalex.org/I90610274"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Irfan Khattak","raw_affiliation_strings":["Department of Electrical Engineering, University of Engineering and Technology, Peshawar, Pakistan"],"raw_orcid":"https://orcid.org/0000-0003-4655-938X","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Engineering and Technology, Peshawar, Pakistan","institution_ids":["https://openalex.org/I90610274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072053188","display_name":"Muath Al\u2010Hasan","orcid":"https://orcid.org/0000-0002-3629-2987"},"institutions":[{"id":"https://openalex.org/I161913731","display_name":"Al Ain University","ror":"https://ror.org/023abrt21","country_code":"AE","type":"education","lineage":["https://openalex.org/I161913731"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muath Al-Hasan","raw_affiliation_strings":["College of Engineering, Al Ain University, Al Ain, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-3629-2987","affiliations":[{"raw_affiliation_string":"College of Engineering, Al Ain University, Al Ain, United Arab Emirates","institution_ids":["https://openalex.org/I161913731"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024138600","display_name":"Abdul Baseer Qazi","orcid":"https://orcid.org/0000-0003-2903-1612"},"institutions":[{"id":"https://openalex.org/I59225215","display_name":"Bahria University","ror":"https://ror.org/02v8d7770","country_code":"PK","type":"education","lineage":["https://openalex.org/I59225215"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Abdul Baseer Qazi","raw_affiliation_strings":["Department of Software Engineering, Bahria University, Islamabad, Pakistan"],"raw_orcid":"https://orcid.org/0000-0003-2903-1612","affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Bahria University, Islamabad, Pakistan","institution_ids":["https://openalex.org/I59225215"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.7514,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96073545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"8","issue":null,"first_page":"160581","last_page":"160595"},"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":0.9990000128746033,"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":0.9975000023841858,"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/speech-recognition","display_name":"Speech recognition","score":0.8064632415771484},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7978350520133972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891356945037842},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7291164994239807},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6949045062065125},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6365479230880737},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5354008674621582},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47296208143234253},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.42064282298088074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4052352011203766},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.25455331802368164},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.24040454626083374}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8064632415771484},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7978350520133972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891356945037842},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7291164994239807},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6949045062065125},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6365479230880737},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5354008674621582},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47296208143234253},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.42064282298088074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4052352011203766},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25455331802368164},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.24040454626083374},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3021061","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3021061","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09183987.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:12de9f9193ea4b56a8222c2093bb2e70","is_oa":true,"landing_page_url":"https://doaj.org/article/12de9f9193ea4b56a8222c2093bb2e70","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 160581-160595 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3021061","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3021061","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09183987.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2916335103","display_name":null,"funder_award_id":"AARE19-245","funder_id":"https://openalex.org/F4320329011","funder_display_name":"Department of Education and Knowledge"}],"funders":[{"id":"https://openalex.org/F4320329011","display_name":"Department of Education and Knowledge","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3081608966.pdf","grobid_xml":"https://content.openalex.org/works/W3081608966.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1516630152","https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1897240248","https://openalex.org/W1963970749","https://openalex.org/W1974387177","https://openalex.org/W1974774036","https://openalex.org/W1995536493","https://openalex.org/W2013608223","https://openalex.org/W2030885260","https://openalex.org/W2031647436","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2059045901","https://openalex.org/W2062445706","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2085191029","https://openalex.org/W2086139506","https://openalex.org/W2112124574","https://openalex.org/W2120847449","https://openalex.org/W2121973264","https://openalex.org/W2122982914","https://openalex.org/W2128653836","https://openalex.org/W2131030892","https://openalex.org/W2141411743","https://openalex.org/W2151500768","https://openalex.org/W2153894152","https://openalex.org/W2168379380","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2516001803","https://openalex.org/W2532111990","https://openalex.org/W2561557072","https://openalex.org/W2584505851","https://openalex.org/W2741913599","https://openalex.org/W2765164841","https://openalex.org/W2765976216","https://openalex.org/W2791874741","https://openalex.org/W2809941692","https://openalex.org/W2891759647","https://openalex.org/W2894651928","https://openalex.org/W2899269477","https://openalex.org/W2915844545","https://openalex.org/W2942231644","https://openalex.org/W2954198060","https://openalex.org/W2962776038","https://openalex.org/W2964057032","https://openalex.org/W2964273174","https://openalex.org/W2973006943","https://openalex.org/W3011982609","https://openalex.org/W3019975421","https://openalex.org/W3124794156","https://openalex.org/W3147539069","https://openalex.org/W4293404878","https://openalex.org/W6678144778","https://openalex.org/W6717768942","https://openalex.org/W6759805140","https://openalex.org/W6765046127"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2342810974","https://openalex.org/W2058482658","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4386746628","https://openalex.org/W1980687383","https://openalex.org/W2037635165","https://openalex.org/W2738829087"],"abstract_inverted_index":{"Human":[0],"speech":[1,19,38,50,67,81,174,182,213,221,227],"in":[2,27,74],"real-world":[3],"environments":[4],"is":[5,83,118,135,188,192],"typically":[6],"degraded":[7,113],"by":[8,194,206],"the":[9,44,48,58,62,104,108,112,127,140,157,162,172,197,211,219,225],"background":[10,163],"noise.":[11,164],"They":[12],"have":[13],"a":[14,121],"negative":[15,59],"impact":[16],"on":[17,61],"perceptual":[18,53],"quality":[20,63,175],"and":[21,36,51,95,176,202,208],"intelligibility":[22,132],"which":[23,55],"causes":[24],"performance":[25],"degradation":[26],"various":[28],"speech-related":[29],"technological":[30],"applications,":[31],"such":[32],"as":[33,120,178,180],"hearing":[34],"aids":[35],"automatic":[37,181],"recognition":[39],"systems.":[40],"It":[41],"also":[42,136],"degrades":[43],"original":[45],"phase":[46],"of":[47,64,88,111,171],"clean":[49],"introduces":[52],"disturbance":[54],"leads":[56],"to":[57,102,124,138,168],"impacts":[60],"speech.":[65,114,199],"Therefore,":[66],"enhancement":[68,82,222,228],"must":[69],"vigilantly":[70],"be":[71],"dealt":[72],"with":[73,126],"everyday":[75],"listening":[76],"environments.":[77],"In":[78,184],"this":[79],"article,":[80],"performed":[84],"using":[85],"supervised":[86],"learning":[87],"spectral":[89,105],"masking.":[90],"Deep":[91],"neural":[92,97],"networks":[93,98],"(DNN)":[94],"recurrent":[96],"(RNN)":[99],"are":[100,204],"trained":[101],"learn":[103],"masking":[106],"from":[107],"magnitude":[109],"spectrograms":[110],"An":[115],"iterative":[116],"procedure":[117],"adopted":[119],"post-processing":[122],"step":[123],"deal":[125],"noisy":[128,198,212],"phase.":[129],"Additionally,":[130],"an":[131],"improvement":[133],"filter":[134],"used":[137],"incorporate":[139],"critical":[141],"band":[142],"importance":[143],"function":[144],"weights":[145,148],"where":[146],"higher":[147],"contribute":[149],"more":[150],"towards":[151],"intelligibility.":[152],"Systematic":[153],"experiments":[154],"demonstrated":[155],"that":[156,218],"proposed":[158,220],"approaches":[159,223],"greatly":[160],"attenuated":[161],"Also,":[165,200],"they":[166],"led":[167],"large":[169],"improvements":[170],"perceived":[173],"intelligibility,":[177],"well":[179],"recognition.":[183],"experiments,":[185],"TIMIT":[186],"database":[187],"used.":[189],"The":[190],"STOI":[191],"improved":[193,205],"17.6%":[195],"over":[196,210],"SDR":[201],"PESQ":[203],"5.22dB":[207],"19%":[209],"utterances.":[214],"These":[215],"comparisons":[216],"showed":[217],"outperformed":[224],"related":[226],"methods.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":10}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}