{"id":"https://openalex.org/W3212140044","doi":"https://doi.org/10.3233/jifs-202841","title":"Non-diacritized Arabic speech recognition based on CNN-LSTM and attention-based models","display_name":"Non-diacritized Arabic speech recognition based on CNN-LSTM and attention-based models","publication_year":2021,"publication_date":"2021-11-09","ids":{"openalex":"https://openalex.org/W3212140044","doi":"https://doi.org/10.3233/jifs-202841","mag":"3212140044"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-202841","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-202841","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","raw_type":"journal-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/A5045319295","display_name":"Hamzah A. Alsayadi","orcid":"https://orcid.org/0000-0002-6062-0899"},"institutions":[{"id":"https://openalex.org/I107720978","display_name":"Ain Shams University","ror":"https://ror.org/00cb9w016","country_code":"EG","type":"education","lineage":["https://openalex.org/I107720978"]},{"id":"https://openalex.org/I78137547","display_name":"Ibb University","ror":"https://ror.org/00fhcxc56","country_code":"YE","type":"education","lineage":["https://openalex.org/I78137547"]}],"countries":["EG","YE"],"is_corresponding":true,"raw_author_name":"Hamzah A. Alsayadi","raw_affiliation_strings":["Computer Science Department, Faculty of Computer & Information Sciences, Ain Shams University, Egypt","Computer Science Department, Faculty of Sciences, Ibb University, Yemen"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Faculty of Computer & Information Sciences, Ain Shams University, Egypt","institution_ids":["https://openalex.org/I107720978"]},{"raw_affiliation_string":"Computer Science Department, Faculty of Sciences, Ibb University, Yemen","institution_ids":["https://openalex.org/I78137547"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031054535","display_name":"Abdelaziz A. Abdelhamid","orcid":"https://orcid.org/0000-0001-7080-1979"},"institutions":[{"id":"https://openalex.org/I107720978","display_name":"Ain Shams University","ror":"https://ror.org/00cb9w016","country_code":"EG","type":"education","lineage":["https://openalex.org/I107720978"]},{"id":"https://openalex.org/I206935292","display_name":"Shaqra University","ror":"https://ror.org/05hawb687","country_code":"SA","type":"education","lineage":["https://openalex.org/I206935292"]}],"countries":["EG","SA"],"is_corresponding":false,"raw_author_name":"Abdelaziz A. Abdelhamid","raw_affiliation_strings":["College of Computing and Information Technology, Shaqra University, Saudi Arabia","Computer Science Department, Faculty of Computer & Information Sciences, Ain Shams University, Egypt"],"affiliations":[{"raw_affiliation_string":"College of Computing and Information Technology, Shaqra University, Saudi Arabia","institution_ids":["https://openalex.org/I206935292"]},{"raw_affiliation_string":"Computer Science Department, Faculty of Computer & Information Sciences, Ain Shams University, Egypt","institution_ids":["https://openalex.org/I107720978"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018708322","display_name":"Islam Hegazy","orcid":"https://orcid.org/0000-0002-1572-463X"},"institutions":[{"id":"https://openalex.org/I107720978","display_name":"Ain Shams University","ror":"https://ror.org/00cb9w016","country_code":"EG","type":"education","lineage":["https://openalex.org/I107720978"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Islam Hegazy","raw_affiliation_strings":["Computer Science Department, Faculty of Computer & Information Sciences, Ain Shams University, Egypt"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Faculty of Computer & Information Sciences, Ain Shams University, Egypt","institution_ids":["https://openalex.org/I107720978"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110309543","display_name":"Zaki T. Fayed","orcid":null},"institutions":[{"id":"https://openalex.org/I107720978","display_name":"Ain Shams University","ror":"https://ror.org/00cb9w016","country_code":"EG","type":"education","lineage":["https://openalex.org/I107720978"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Zaki T. Fayed","raw_affiliation_strings":["Computer Science Department, Faculty of Computer & Information Sciences, Ain Shams University, Egypt"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Faculty of Computer & Information Sciences, Ain Shams University, Egypt","institution_ids":["https://openalex.org/I107720978"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045319295"],"corresponding_institution_ids":["https://openalex.org/I107720978","https://openalex.org/I78137547"],"apc_list":null,"apc_paid":null,"fwci":1.9563,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88777043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"41","issue":"6","first_page":"6207","last_page":"6219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958000183105469,"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":0.8534022569656372},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7839254140853882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7033137083053589},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6397450566291809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6191040873527527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.56253582239151},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5135455131530762},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5132710933685303},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.49702051281929016},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49299857020378113},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.41342511773109436},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15655848383903503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8534022569656372},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7839254140853882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7033137083053589},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6397450566291809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6191040873527527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.56253582239151},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5135455131530762},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5132710933685303},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.49702051281929016},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49299857020378113},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.41342511773109436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15655848383903503},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-202841","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-202841","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1995562189","https://openalex.org/W2079735306","https://openalex.org/W2148154194","https://openalex.org/W2890640437","https://openalex.org/W2891290234","https://openalex.org/W2902860900","https://openalex.org/W2906152891","https://openalex.org/W2906891164","https://openalex.org/W2912581782","https://openalex.org/W2919448963","https://openalex.org/W2940606701","https://openalex.org/W2944177268","https://openalex.org/W2950533189","https://openalex.org/W2953521532","https://openalex.org/W2960038063","https://openalex.org/W2964539095","https://openalex.org/W2977945941","https://openalex.org/W2991526691","https://openalex.org/W3017022801","https://openalex.org/W6754662006"],"related_works":["https://openalex.org/W1989705153","https://openalex.org/W2962966012","https://openalex.org/W2608962050","https://openalex.org/W4300437043","https://openalex.org/W2147931688","https://openalex.org/W2913200330","https://openalex.org/W2048917925","https://openalex.org/W2075815989","https://openalex.org/W1928807591","https://openalex.org/W2033350476"],"abstract_inverted_index":{"Arabic":[0,66,114,137,162],"language":[1,140,195],"has":[2,106],"a":[3,31,126],"set":[4],"of":[5,19,36,42,52,62,97,102,113,156,187,193],"sound":[6],"letters":[7,44],"called":[8],"diacritics,":[9,170],"these":[10,43],"diacritics":[11,28,188],"play":[12],"an":[13],"essential":[14],"role":[15],"in":[16,26,33,45,83,110,142,216],"the":[17,34,37,40,46,50,60,65,84,95,100,111,157,169,177,185,194,199],"meaning":[18],"words":[20],"and":[21,79,93,149,151,175,191],"their":[22],"articulations.":[23],"The":[24,73,139,160,212],"change":[25,32],"some":[27],"leads":[29],"to":[30,94,173,209],"context":[35],"sentence.":[38],"However,":[39],"existence":[41],"corpus":[47],"transcription":[48,155],"affects":[49],"accuracy":[51],"speech":[53,67,116,158],"recognition.":[54],"In":[55,91,197],"this":[56,121,123,143],"paper,":[57],"we":[58],"investigate":[59],"effect":[61],"diactrics":[63],"on":[64,130,153],"recognition":[68,117],"based":[69,129,134,152],"end-to-end":[70,75],"deep":[71,178],"learning.":[72],"applied":[74],"approach":[76,101,128,144],"includes":[77],"CNN-LSTM":[78,103,131],"attention-based":[80,105],"technique":[81],"presented":[82],"state-of-the-art":[85],"framework":[86],"namely,":[87],"Espresso":[88],"using":[89,147],"Pytorch.":[90],"addition,":[92,198],"best":[96],"our":[98],"knowledge,":[99],"with":[104,132],"not":[107],"been":[108],"used":[109,172],"task":[112],"Automatic":[115],"(ASR).":[118],"To":[119],"fill":[120],"gap,":[122],"paper":[124],"proposes":[125],"new":[127],"attention":[133],"method":[135],"for":[136],"ASR.":[138],"model":[141],"is":[145,171,204,218],"trained":[146],"RNN-LM":[148],"LSTM-LM":[150],"nondiacritized":[154],"corpus.":[159],"Standard":[161],"Single":[163],"Speaker":[164],"Corpus":[165],"(SASSC),":[166],"after":[167],"omitting":[168],"train":[174],"test":[176],"learning":[179],"model.":[180,196],"Experimental":[181],"results":[182],"show":[183],"that":[184],"removal":[186],"decreased":[189],"out-of-vocabulary":[190],"perplexity":[192],"word":[200],"error":[201],"rate":[202],"(WER)":[203],"significantly":[205],"improved":[206],"when":[207],"compared":[208],"diacritized":[210],"data.":[211],"achieved":[213],"average":[214],"reduction":[215],"WER":[217],"13.52%.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
