{"id":"https://openalex.org/W4393059574","doi":"https://doi.org/10.1109/dese60595.2023.10469031","title":"Arabic Speech Recognition based on Self Supervised Learning","display_name":"Arabic Speech Recognition based on Self Supervised Learning","publication_year":2023,"publication_date":"2023-12-18","ids":{"openalex":"https://openalex.org/W4393059574","doi":"https://doi.org/10.1109/dese60595.2023.10469031"},"language":"en","primary_location":{"id":"doi:10.1109/dese60595.2023.10469031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dese60595.2023.10469031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 16th International Conference on Developments in eSystems Engineering (DeSE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001369639","display_name":"Hiba Adreese Younis","orcid":null},"institutions":[{"id":"https://openalex.org/I12150220","display_name":"University of Mosul","ror":"https://ror.org/039cf4q47","country_code":"IQ","type":"education","lineage":["https://openalex.org/I12150220"]}],"countries":["IQ"],"is_corresponding":false,"raw_author_name":"Hiba Adreese Younis","raw_affiliation_strings":["University of Mosul,College of Computer Science and Mathematics,Department of Computer Science,Mosul,IRAQ","Department of Computer Science, College of Computer Science and Mathematics, University of Mosul, Mosul, IRAQ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mosul,College of Computer Science and Mathematics,Department of Computer Science,Mosul,IRAQ","institution_ids":["https://openalex.org/I12150220"]},{"raw_affiliation_string":"Department of Computer Science, College of Computer Science and Mathematics, University of Mosul, Mosul, IRAQ","institution_ids":["https://openalex.org/I12150220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050050274","display_name":"Yusra Faisal Mohammad","orcid":null},"institutions":[{"id":"https://openalex.org/I12150220","display_name":"University of Mosul","ror":"https://ror.org/039cf4q47","country_code":"IQ","type":"education","lineage":["https://openalex.org/I12150220"]}],"countries":["IQ"],"is_corresponding":false,"raw_author_name":"Yusra Faisal Mohammad","raw_affiliation_strings":["University of Mosul,College of Computer Science and Mathematics,Department of Computer Science,Mosul,IRAQ","Department of Computer Science, College of Computer Science and Mathematics, University of Mosul, Mosul, IRAQ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mosul,College of Computer Science and Mathematics,Department of Computer Science,Mosul,IRAQ","institution_ids":["https://openalex.org/I12150220"]},{"raw_affiliation_string":"Department of Computer Science, College of Computer Science and Mathematics, University of Mosul, Mosul, IRAQ","institution_ids":["https://openalex.org/I12150220"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12150220"],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52385841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2023","issue":null,"first_page":"528","last_page":"533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9297999739646912,"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":0.9297999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7724431753158569},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6874398589134216},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6445209980010986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.528617799282074},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4161217510700226},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07631325721740723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724431753158569},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6874398589134216},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6445209980010986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.528617799282074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4161217510700226},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07631325721740723},{"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:10.1109/dese60595.2023.10469031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dese60595.2023.10469031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 16th International Conference on Developments in eSystems Engineering (DeSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1989887389","https://openalex.org/W2586619907","https://openalex.org/W3167101391","https://openalex.org/W3207558756","https://openalex.org/W3209059054","https://openalex.org/W4225534571","https://openalex.org/W4226139546","https://openalex.org/W4280644286","https://openalex.org/W4297841583","https://openalex.org/W4319862410","https://openalex.org/W4322622823","https://openalex.org/W4360942793","https://openalex.org/W4378105483","https://openalex.org/W4385569523","https://openalex.org/W6803191155","https://openalex.org/W6838637163","https://openalex.org/W6846714717","https://openalex.org/W6850036998","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4249048193","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Automatic":[0],"Arabic":[1,124,187],"Speech":[2],"Recognition":[3],"(AASR)":[4],"has":[5],"gained":[6],"significant":[7],"attention":[8],"in":[9,17,148],"recent":[10],"years":[11],"due":[12],"to":[13,47,70,129,139],"its":[14],"potential":[15],"applications":[16],"various":[18],"fields":[19],"such":[20],"as":[21,66,137,214],"transcription,":[22],"voice":[23,189],"assistants,":[24],"and":[25,45,93,111,132,154,167,180,211,226,229,235,242],"language":[26,125],"learning.":[27],"However,":[28],"ASR":[29,72,157],"systems":[30],"typically":[31],"require":[32],"a":[33,67,113],"large":[34,217],"amount":[35],"of":[36,82,123,162,200],"labelled":[37],"data":[38],"for":[39,50,117,151,232,239],"training,":[40],"which":[41,127],"can":[42],"be":[43],"expensive":[44],"time-consuming":[46],"obtain,":[48],"especially":[49],"languages":[51],"with":[52,119,197,216],"limited":[53],"resources":[54],"like":[55],"Arabic.":[56],"To":[57],"address":[58],"this":[59,78,149],"challenge,":[60],"self-supervised":[61],"learning":[62,201],"techniques":[63],"have":[64],"emerged":[65],"promising":[68],"approach":[69],"improve":[71],"performance":[73,131],"by":[74,88,104],"leveraging":[75],"unlabeled":[76],"data.In":[77],"research,":[79],"the":[80,83,90,120,192],"architecture":[81],"HUBERT":[84,140,178,209,243],"model":[85,175,179,184,196,210,234],"was":[86],"enhanced":[87],"removing":[89],"last":[91],"layer":[92,102,116],"adding":[94],"additional":[95],"layers":[96],"including":[97],"(normalization":[98],"layer,":[99],"two":[100],"linear":[101,114],"followed":[103],"RELU":[105],"activation":[106],"function,":[107],"drop":[108],"out":[109],"layer),":[110],"finally":[112],"projection":[115],"alignment":[118],"vocabulary":[121],"size":[122],"dataset":[126],"led":[128],"better":[130,205],"smaller":[133],"word":[134],"error":[135],"rate(WER)":[136],"compared":[138,215],"base":[141,208,244],"model.":[142,219],"Many":[143],"experiments":[144],"were":[145,222],"also":[146],"applied":[147],"research":[150],"enhancing":[152],"mono":[153],"multi":[155,172],"lingual":[156,173],"models":[158,221,245],"using":[159,224],"different":[160],"combination":[161],"hyper":[163],"parameters":[164],"through":[165],"trial":[166],"error.":[168],"Results":[169],"showed":[170,230],"that":[171],"wav2vec2XLSR":[174],"outperformed":[176],"monolingual":[177],"massive":[181],"multilingual":[182],"speech(MMS)":[183],"fine-tuned":[185],"on":[186],"common":[188],"dataset.":[190],"also,":[191],"proposed":[193],"modified":[194],"Hubert":[195],"specific":[198],"type":[199],"rate":[202],"scheduler(MHLR)":[203],"gave":[204],"results":[206,213],"than":[207],"good":[212],"MMS":[218],"These":[220],"evaluated":[223],"WER":[225],"WRR":[227],"metrics":[228],"40%":[231],"wav2vec2xlsr":[233],"42%,":[236],"45%,":[237],"54%,":[238],"MMS,":[240],"MHLR":[241],"respectively.":[246]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}