{"id":"https://openalex.org/W4382725773","doi":"https://doi.org/10.1109/access.2023.3290908","title":"NSE-CATNet: Deep Neural Speech Enhancement Using Convolutional Attention Transformer Network","display_name":"NSE-CATNet: Deep Neural Speech Enhancement Using Convolutional Attention Transformer Network","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4382725773","doi":"https://doi.org/10.1109/access.2023.3290908"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3290908","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3290908","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10168245.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/ielx7/6287639/6514899/10168245.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/I4164984","display_name":"International Islamic University Malaysia","ror":"https://ror.org/03s9hs139","country_code":"MY","type":"education","lineage":["https://openalex.org/I4164984"]}],"countries":["MY","PK"],"is_corresponding":false,"raw_author_name":"Nasir Saleem","raw_affiliation_strings":["Department of Electrical Engineering, Faculty of Engineering and Technology, Gomal University, Dera Ismail Khan, Pakistan","Electrical and Computer Engineering Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-0010-0629","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Faculty of Engineering and Technology, Gomal University, Dera Ismail Khan, Pakistan","institution_ids":["https://openalex.org/I172324550"]},{"raw_affiliation_string":"Electrical and Computer Engineering Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I4164984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031234998","display_name":"Teddy Surya Gunawan","orcid":"https://orcid.org/0000-0003-3345-4669"},"institutions":[{"id":"https://openalex.org/I4164984","display_name":"International Islamic University Malaysia","ror":"https://ror.org/03s9hs139","country_code":"MY","type":"education","lineage":["https://openalex.org/I4164984"]},{"id":"https://openalex.org/I862893732","display_name":"Telkom University","ror":"https://ror.org/0004wsx81","country_code":"ID","type":"education","lineage":["https://openalex.org/I862893732"]}],"countries":["ID","MY"],"is_corresponding":false,"raw_author_name":"Teddy Surya Gunawan","raw_affiliation_strings":["Electrical and Computer Engineering Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia","School of Electrical Engineering, Telkom University, Bandung, Indonesia"],"raw_orcid":"https://orcid.org/0000-0003-3345-4669","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I4164984"]},{"raw_affiliation_string":"School of Electrical Engineering, Telkom University, Bandung, Indonesia","institution_ids":["https://openalex.org/I862893732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065953146","display_name":"Mira Kartiwi","orcid":"https://orcid.org/0000-0002-3686-3575"},"institutions":[{"id":"https://openalex.org/I4164984","display_name":"International Islamic University Malaysia","ror":"https://ror.org/03s9hs139","country_code":"MY","type":"education","lineage":["https://openalex.org/I4164984"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mira Kartiwi","raw_affiliation_strings":["Information Systems Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-3686-3575","affiliations":[{"raw_affiliation_string":"Information Systems Department, International Islamic University Malaysia (IIUM), Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I4164984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077120203","display_name":"Bambang Setia Nugroho","orcid":"https://orcid.org/0000-0002-8015-5592"},"institutions":[{"id":"https://openalex.org/I862893732","display_name":"Telkom University","ror":"https://ror.org/0004wsx81","country_code":"ID","type":"education","lineage":["https://openalex.org/I862893732"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Bambang Setia Nugroho","raw_affiliation_strings":["School of Electrical Engineering, Telkom University, Bandung, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Telkom University, Bandung, Indonesia","institution_ids":["https://openalex.org/I862893732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040003632","display_name":"Inung Wijayanto","orcid":"https://orcid.org/0000-0003-1412-0428"},"institutions":[{"id":"https://openalex.org/I862893732","display_name":"Telkom University","ror":"https://ror.org/0004wsx81","country_code":"ID","type":"education","lineage":["https://openalex.org/I862893732"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Inung Wijayanto","raw_affiliation_strings":["School of Electrical Engineering, Telkom University, Bandung, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Telkom University, Bandung, Indonesia","institution_ids":["https://openalex.org/I862893732"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":4.8712,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96290582,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"66979","last_page":"66994"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7366126775741577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7065152525901794},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6009488105773926},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5900200009346008},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5437641143798828},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5010054111480713},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48542889952659607},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41843000054359436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3555675148963928},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.073767751455307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7366126775741577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7065152525901794},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6009488105773926},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5900200009346008},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5437641143798828},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5010054111480713},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48542889952659607},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41843000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3555675148963928},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.073767751455307},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3290908","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3290908","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10168245.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:generic.eprints.org:106019","is_oa":true,"landing_page_url":null,"pdf_url":"http://irep.iium.edu.my/106019/8/106019_NSE-CATNet%20deep%20neural%20speech%20enhancement_Scopus.pdf","source":{"id":"https://openalex.org/S4306400713","display_name":"The International Islamic University Malaysia Repository (The International Islamic University Malaysia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4164984","host_organization_name":"International Islamic University Malaysia","host_organization_lineage":["https://openalex.org/I4164984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:69b66c56eba3490181238d4efd7f2d8e","is_oa":true,"landing_page_url":"https://doaj.org/article/69b66c56eba3490181238d4efd7f2d8e","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 11, Pp 66979-66994 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3290908","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3290908","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10168245.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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382725773.pdf","grobid_xml":"https://content.openalex.org/works/W4382725773.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1506438021","https://openalex.org/W1974387177","https://openalex.org/W2006910250","https://openalex.org/W2038484192","https://openalex.org/W2044893557","https://openalex.org/W2063378142","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2128653836","https://openalex.org/W2144404214","https://openalex.org/W2168379380","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2405774341","https://openalex.org/W2602577565","https://openalex.org/W2757519008","https://openalex.org/W2774389566","https://openalex.org/W2809456172","https://openalex.org/W2889442120","https://openalex.org/W2889890482","https://openalex.org/W2921144622","https://openalex.org/W2937484199","https://openalex.org/W2940275453","https://openalex.org/W2945191446","https://openalex.org/W2954198060","https://openalex.org/W2962843322","https://openalex.org/W2963341071","https://openalex.org/W2973006943","https://openalex.org/W2991361823","https://openalex.org/W2998445964","https://openalex.org/W3015844538","https://openalex.org/W3016056257","https://openalex.org/W3016129867","https://openalex.org/W3016447038","https://openalex.org/W3017350693","https://openalex.org/W3081608966","https://openalex.org/W3086513098","https://openalex.org/W3095057960","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3109018774","https://openalex.org/W3109196171","https://openalex.org/W3117290926","https://openalex.org/W3120336970","https://openalex.org/W3121098269","https://openalex.org/W3131443528","https://openalex.org/W3135881253","https://openalex.org/W3147539069","https://openalex.org/W3160129476","https://openalex.org/W3161950572","https://openalex.org/W3162493033","https://openalex.org/W3165858867","https://openalex.org/W3177067699","https://openalex.org/W3197729725","https://openalex.org/W3197822518","https://openalex.org/W3197912330","https://openalex.org/W3213188934","https://openalex.org/W4200079780","https://openalex.org/W4231807801","https://openalex.org/W4285791551","https://openalex.org/W4296276529","https://openalex.org/W4296959082","https://openalex.org/W4306160625","https://openalex.org/W4312271884","https://openalex.org/W4315606033","https://openalex.org/W4318975163","https://openalex.org/W4319295650","https://openalex.org/W4323338563","https://openalex.org/W6752527106","https://openalex.org/W6790928573","https://openalex.org/W6843036773"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4390516098","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W2231565466","https://openalex.org/W3043214604","https://openalex.org/W1505346162"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,80,182],"(SE)":[2],"is":[3,112,146,195,218],"a":[4,77,108,131],"critical":[5],"aspect":[6],"of":[7,27,102,142,180],"various":[8],"speech-processing":[9],"applications.":[10],"Recent":[11],"research":[12],"in":[13,47,105,178],"this":[14],"field":[15],"focuses":[16],"on":[17,155],"identifying":[18],"effective":[19,196],"ways":[20],"to":[21,30,69,124],"capture":[22,55],"the":[23,40,67,71,83,93,98,115,122,136,143,159,163,171,175,193,199,212,225],"long-term":[24,58],"contextual":[25],"dependencies":[26],"speech":[28,79,106,138,150,181,227],"signals":[29],"enhance":[31],"performance.":[32],"Deep":[33],"convolutional":[34,84,88,116],"networks":[35],"(DCN)":[36],"using":[37,82,148],"self-attention":[38],"and":[39,57,87,129,152,162,188,206,216,222],"Transformer":[41,49,90,117],"model":[42,68,123,194],"have":[43],"demonstrated":[44],"competitive":[45,176],"results":[46,168],"SE.":[48],"models":[50],"with":[51,204,209,214],"convolution":[52],"layers":[53],"can":[54],"short":[56],"temporal":[59],"sequences":[60],"by":[61,202,207,220],"leveraging":[62],"multi-head":[63],"self-attention,":[64],"which":[65],"allows":[66],"attend":[70],"entire":[72],"sequence.":[73],"This":[74,119,190],"study":[75],"proposes":[76],"neural":[78],"(NSE)":[81],"encoder-decoder":[85],"(CED)":[86],"attention":[89,110,133],"(CAT),":[91],"named":[92],"NSE-CATNet.":[94],"To":[95],"effectively":[96],"process":[97],"time-frequency":[99,137],"(T-F)":[100],"distribution":[101],"spectral":[103],"components":[104],"signals,":[107],"T-F":[109],"module":[111,120],"incorporated":[113],"into":[114],"model.":[118],"enables":[121],"explicitly":[125],"leverage":[126],"position":[127],"information":[128],"generate":[130],"two-dimensional":[132],"map":[134],"for":[135],"distribution.":[139],"The":[140,166],"performance":[141,183],"proposed":[144,172],"SE":[145,173],"evaluated":[147],"objective":[149],"quality":[151,201],"intelligibility":[153,213],"metrics":[154],"two":[156],"different":[157],"datasets,":[158],"VoiceBank-DEMAND":[160,205,215],"Corpus":[161],"LibriSpeech":[164,217],"dataset.":[165],"experimental":[167],"indicate":[169],"that":[170,192],"outperformed":[174],"baselines":[177],"terms":[179],"at":[184,197],"-":[185],"5dB,":[186],"0dB,":[187],"5dB.":[189],"suggests":[191],"improving":[198],"overall":[200],"0.704":[203],"0.692":[208],"LibriSpeech.":[210],"Further,":[211],"improved":[219],"11.325%":[221],"11.75%":[223],"over":[224],"noisy":[226],"signals.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
