{"id":"https://openalex.org/W4391454503","doi":"https://doi.org/10.1109/access.2024.3361286","title":"Spatio-Temporal Features Representation Using Recurrent Capsules for Monaural Speech Enhancement","display_name":"Spatio-Temporal Features Representation Using Recurrent Capsules for Monaural Speech Enhancement","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391454503","doi":"https://doi.org/10.1109/access.2024.3361286"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3361286","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3361286","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10418233.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/ielx7/6287639/6514899/10418233.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104238025","display_name":"Jawad Ali","orcid":null},"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"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Jawad Ali","raw_affiliation_strings":["Department of Electrical Engineering, Faculty of Engineering and Technology, Gomal University, Dera Ismail Khan, Pakistan"],"raw_orcid":null,"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"]}]},{"author_position":"middle","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"]}],"countries":["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"],"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024097894","display_name":"Sami Bourouis","orcid":"https://orcid.org/0000-0002-6638-7039"},"institutions":[{"id":"https://openalex.org/I179331831","display_name":"Taif University","ror":"https://ror.org/014g1a453","country_code":"SA","type":"education","lineage":["https://openalex.org/I179331831"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sami Bourouis","raw_affiliation_strings":["Department of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-6638-7039","affiliations":[{"raw_affiliation_string":"Department of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia","institution_ids":["https://openalex.org/I179331831"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081328154","display_name":"Eatedal Alabdulkreem","orcid":"https://orcid.org/0000-0002-3001-6818"},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Eatedal Alabdulkreem","raw_affiliation_strings":["Department of Computer Science, College of Computer and Information Science, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-3001-6818","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Computer and Information Science, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111122876","display_name":"Hela El Mannai","orcid":null},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hela El Mannai","raw_affiliation_strings":["Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-2571-1848","affiliations":[{"raw_affiliation_string":"Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026548014","display_name":"Sami Dhahbi","orcid":"https://orcid.org/0000-0002-0126-2366"},"institutions":[{"id":"https://openalex.org/I82952536","display_name":"King Khalid University","ror":"https://ror.org/052kwzs30","country_code":"SA","type":"education","lineage":["https://openalex.org/I82952536"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sami Dhahbi","raw_affiliation_strings":["Department of Computer Science, College of Science and Art at Mahayil, King Khalid University, Muhayil Aseer, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Science and Art at Mahayil, King Khalid University, Muhayil Aseer, Saudi Arabia","institution_ids":["https://openalex.org/I82952536"]}]}],"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":3.097,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92215701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"21287","last_page":"21303"},"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":0.9994999766349792,"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":0.9977999925613403,"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":0.805658757686615},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7003346681594849},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6433152556419373},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.613031804561615},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6096746325492859},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6014511585235596},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5174118280410767},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5159133672714233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.405538409948349},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25735020637512207},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24585214257240295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805658757686615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7003346681594849},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6433152556419373},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.613031804561615},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6096746325492859},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6014511585235596},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5174118280410767},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5159133672714233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.405538409948349},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25735020637512207},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24585214257240295},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3361286","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3361286","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10418233.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:doaj.org/article:21a56c9457864949be4b3aa1ab870699","is_oa":true,"landing_page_url":"https://doaj.org/article/21a56c9457864949be4b3aa1ab870699","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 12, Pp 21287-21303 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3361286","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3361286","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10418233.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":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1243384461","display_name":null,"funder_award_id":"RGP2/383/44","funder_id":"https://openalex.org/F4320324433","funder_display_name":"King Khalid University"},{"id":"https://openalex.org/G6545283446","display_name":null,"funder_award_id":"PNURSP2024R161","funder_id":"https://openalex.org/F4320322484","funder_display_name":"Princess Nourah Bint Abdulrahman University"}],"funders":[{"id":"https://openalex.org/F4320322484","display_name":"Princess Nourah Bint Abdulrahman University","ror":"https://ror.org/05b0cyh02"},{"id":"https://openalex.org/F4320324433","display_name":"King Khalid University","ror":"https://ror.org/052kwzs30"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391454503.pdf","grobid_xml":"https://content.openalex.org/works/W4391454503.grobid-xml"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1897240248","https://openalex.org/W2006910250","https://openalex.org/W2044893557","https://openalex.org/W2058502470","https://openalex.org/W2102950268","https://openalex.org/W2128604088","https://openalex.org/W2130178255","https://openalex.org/W2141998673","https://openalex.org/W2364134690","https://openalex.org/W2626544737","https://openalex.org/W2740616313","https://openalex.org/W2747664154","https://openalex.org/W2794295502","https://openalex.org/W2889018940","https://openalex.org/W2889442120","https://openalex.org/W2889450888","https://openalex.org/W2889890482","https://openalex.org/W2897371647","https://openalex.org/W2936689732","https://openalex.org/W2937484199","https://openalex.org/W2940275453","https://openalex.org/W2943554574","https://openalex.org/W2950448225","https://openalex.org/W2954198060","https://openalex.org/W2962843322","https://openalex.org/W2963045393","https://openalex.org/W2963341071","https://openalex.org/W2972381775","https://openalex.org/W2973006943","https://openalex.org/W2974481323","https://openalex.org/W2986634321","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W2998445964","https://openalex.org/W3015844538","https://openalex.org/W3016129867","https://openalex.org/W3016447038","https://openalex.org/W3017350693","https://openalex.org/W3049430014","https://openalex.org/W3081608966","https://openalex.org/W3086177986","https://openalex.org/W3086513098","https://openalex.org/W3095057960","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3117290926","https://openalex.org/W3139177929","https://openalex.org/W3161950572","https://openalex.org/W3164605550","https://openalex.org/W3165858867","https://openalex.org/W3197729725","https://openalex.org/W3197912330","https://openalex.org/W3198686072","https://openalex.org/W3213188934","https://openalex.org/W4200079780","https://openalex.org/W4226157755","https://openalex.org/W4231807801","https://openalex.org/W4232282348","https://openalex.org/W4285791551","https://openalex.org/W4311772362","https://openalex.org/W4312431055","https://openalex.org/W4315606033","https://openalex.org/W4317388017","https://openalex.org/W4318833180","https://openalex.org/W4319998010","https://openalex.org/W4322102269","https://openalex.org/W4323338563","https://openalex.org/W4324092848","https://openalex.org/W4353050204","https://openalex.org/W4362579345","https://openalex.org/W4364323053","https://openalex.org/W4365504037","https://openalex.org/W4365816291","https://openalex.org/W4379193822","https://openalex.org/W4379380529","https://openalex.org/W4384131022","https://openalex.org/W4386159007","https://openalex.org/W6743446608","https://openalex.org/W6749897870","https://openalex.org/W6783437975","https://openalex.org/W6790928573","https://openalex.org/W6803594737"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W2100772705","https://openalex.org/W2538939196","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Single-channel":[0],"speech":[1,26,56,71,102,131,208,213,225],"enhancement":[2,103,209,226],"is":[3,36,46,161],"important":[4,37,48],"for":[5,38,100],"modern":[6],"communication":[7],"systems":[8],"and":[9,67,83,111,167,184,202,215,220,230,234],"has":[10],"received":[11],"a":[12,98,109,149],"lot":[13],"of":[14,55,91,136,144],"attention.":[15],"A":[16],"convolutional":[17,190],"neural":[18,204],"network":[19],"(CNN)":[20],"successfully":[21],"learns":[22],"feature":[23,44,85],"representations":[24,54],"from":[25,133],"spectrograms":[27],"but":[28],"loses":[29],"spatial":[30,106,182],"information":[31,107],"due":[32],"to":[33,40,51,79,115,118,129,169,180,196],"distortion,":[34],"which":[35],"humans":[39],"understand":[41],"speech.":[42],"Speech":[43],"learning":[45],"an":[47],"ongoing":[49],"research":[50],"capture":[52],"higher-level":[53],"that":[57,104],"go":[58],"beyond":[59],"conventional":[60],"techniques.":[61],"By":[62,87],"considering":[63,88],"the":[64,77,89,124,134,137,145,164,170,174,197,218,223,228,238],"hierarchical":[65],"structure":[66],"temporal":[68,186],"relationships":[69],"within":[70],"signals,":[72],"capsule":[73,110,171],"networks":[74],"(CapsNets)":[75],"have":[76],"potential":[78],"provide":[80],"more":[81],"expressive":[82],"context-aware":[84],"representations.":[86],"advantages":[90],"CapNets":[92],"over":[93,237],"CNN,":[94],"this":[95],"study":[96],"presents":[97],"model":[99],"monaural":[101],"keeps":[105],"in":[108,173],"uses":[112],"dynamic":[113],"routing":[114,122],"pass":[116],"it":[117,178],"higher":[119],"layers.":[120],"Dynamic":[121],"replaces":[123],"pooling":[125],"recurrent":[126,151,154,191,203],"hidden":[127],"states":[128],"get":[130],"features":[132,183],"outputs":[135],"capsule.":[138],"Leveraging":[139],"long-term":[140,185],"contexts":[141],"provides":[142],"identification":[143],"target":[146],"speaker.":[147],"Therefore,":[148],"gated":[150,153],"layer,":[152],"unit":[155],"(GRU),":[156],"or":[157],"long-short-term":[158],"memory":[159],"(LSTM),":[160],"placed":[162],"above":[163],"CNN":[165],"module":[166,172],"next":[168],"architecture.":[175],"This":[176],"makes":[177],"viable":[179],"extract":[181],"dynamics.":[187],"The":[188,206],"suggested":[189,207,224],"CapNet":[192],"performs":[193],"better":[194,212],"compared":[195],"models":[198],"based":[199],"on":[200],"CNNs":[201],"networks.":[205],"produces":[210],"considerably":[211],"quality":[214,231],"intelligibility.":[216],"With":[217],"LibriSpeech":[219],"VoiceBank+DEMAND":[221],"databases,":[222],"improves":[227],"intelligibility":[229],"by":[232],"18.33%":[233],"(0.94)":[235],"36.82%":[236],"noisy":[239],"mixtures.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}