{"id":"https://openalex.org/W4319862671","doi":"https://doi.org/10.1109/slt54892.2023.10022652","title":"MASC: Massive Arabic Speech Corpus","display_name":"MASC: Massive Arabic Speech Corpus","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862671","doi":"https://doi.org/10.1109/slt54892.2023.10022652"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022652","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5084187172","display_name":"Mohammad Al-Fetyani","orcid":"https://orcid.org/0000-0002-7360-2403"},"institutions":[{"id":"https://openalex.org/I2800233941","display_name":"Jordan Hospital","ror":"https://ror.org/036wxg427","country_code":"JO","type":"healthcare","lineage":["https://openalex.org/I2800233941"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Mohammad Al-Fetyani","raw_affiliation_strings":["Appswave,Amman,Jordan","Appswave, Amman, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Appswave,Amman,Jordan","institution_ids":["https://openalex.org/I2800233941"]},{"raw_affiliation_string":"Appswave, Amman, Jordan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001422372","display_name":"Muhammad Al-Barham","orcid":"https://orcid.org/0000-0003-1552-9639"},"institutions":[{"id":"https://openalex.org/I2800233941","display_name":"Jordan Hospital","ror":"https://ror.org/036wxg427","country_code":"JO","type":"healthcare","lineage":["https://openalex.org/I2800233941"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Muhammad Al-Barham","raw_affiliation_strings":["Appswave,Amman,Jordan","Appswave, Amman, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Appswave,Amman,Jordan","institution_ids":["https://openalex.org/I2800233941"]},{"raw_affiliation_string":"Appswave, Amman, Jordan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036769756","display_name":"Gheith A. Abandah","orcid":"https://orcid.org/0000-0002-0672-809X"},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Gheith Abandah","raw_affiliation_strings":["The University of Jordan,Amman,Jordan","The University of Jordan, Amman, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Jordan,Amman,Jordan","institution_ids":["https://openalex.org/I114972647"]},{"raw_affiliation_string":"The University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006045390","display_name":"Adham Alsharkawi","orcid":"https://orcid.org/0000-0002-9354-7341"},"institutions":[{"id":"https://openalex.org/I114972647","display_name":"University of Jordan","ror":"https://ror.org/05k89ew48","country_code":"JO","type":"education","lineage":["https://openalex.org/I114972647"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Adham Alsharkawi","raw_affiliation_strings":["The University of Jordan,Amman,Jordan","The University of Jordan, Amman, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Jordan,Amman,Jordan","institution_ids":["https://openalex.org/I114972647"]},{"raw_affiliation_string":"The University of Jordan, Amman, Jordan","institution_ids":["https://openalex.org/I114972647"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047502536","display_name":"Maha Dawas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153696","display_name":"Qatar Financial Centre Authority","ror":"https://ror.org/049n5v408","country_code":"QA","type":"government","lineage":["https://openalex.org/I4210153696"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Maha Dawas","raw_affiliation_strings":["Planning and Statistics Authority,Doha,Qatar","Planning and Statistics Authority, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Planning and Statistics Authority,Doha,Qatar","institution_ids":["https://openalex.org/I4210153696"]},{"raw_affiliation_string":"Planning and Statistics Authority, Doha, Qatar","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2668,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.93571463,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1006","last_page":"1013"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T12031","display_name":"Speech and dialogue systems","score":0.9932000041007996,"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/arabic","display_name":"Arabic","score":0.7772716283798218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7762811183929443},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.7153041362762451},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6612763404846191},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6149927973747253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.609122097492218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5719643831253052},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4396611452102661},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.415568083524704},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.41269126534461975},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3581072688102722},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24438875913619995},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07584968209266663}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7772716283798218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762811183929443},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.7153041362762451},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6612763404846191},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6149927973747253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.609122097492218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5719643831253052},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4396611452102661},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.415568083524704},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41269126534461975},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3581072688102722},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24438875913619995},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07584968209266663},{"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/slt54892.2023.10022652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022652","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1922655562","https://openalex.org/W1989887389","https://openalex.org/W2021513757","https://openalex.org/W2128542418","https://openalex.org/W2251224833","https://openalex.org/W2759181158","https://openalex.org/W2787420813","https://openalex.org/W2962824709","https://openalex.org/W2963077089","https://openalex.org/W2964539095","https://openalex.org/W2991213871","https://openalex.org/W3007095894","https://openalex.org/W3030437843","https://openalex.org/W3175210284","https://openalex.org/W4287759860","https://openalex.org/W6640090968","https://openalex.org/W6680768788","https://openalex.org/W6687566353","https://openalex.org/W6691373038","https://openalex.org/W6733526828","https://openalex.org/W6770506093","https://openalex.org/W6771467084"],"related_works":["https://openalex.org/W4297524714","https://openalex.org/W1772447446","https://openalex.org/W2545528998","https://openalex.org/W2021513757","https://openalex.org/W1501126083","https://openalex.org/W1989887389","https://openalex.org/W2276683421","https://openalex.org/W4319862671","https://openalex.org/W2147500075","https://openalex.org/W39910498"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,6,43,86,124,131,138,145],"creation":[4],"of":[5,20,47,102],"Massive":[7],"Arabic":[8,48,56,93,106],"Speech":[9],"Corpus":[10],"(MASC)11https://ieee-dataport.org/open-access/massive-arabic-speech-corpus-masc.":[11],"MASC":[12],"is":[13,35,96,112,135],"a":[14,52,63,69,89,100],"dataset":[15,34,101],"that":[16],"contains":[17],"1,000":[18],"hours":[19],"speech":[21,49,57,72,94,132],"sampled":[22],"at":[23],"16":[24],"kHz":[25],"and":[26,38,45,68,78,91,98,115,142],"crawled":[27,109],"from":[28,110],"over":[29],"700":[30],"YouTube":[31],"channels.":[32],"The":[33],"multi-regional,":[36],"multi-genre,":[37],"multi-dialect":[39],"intended":[40],"to":[41,61,81],"advance":[42],"research":[44],"development":[46,140],"technology":[50],"with":[51],"special":[53],"emphasis":[54],"on":[55,118],"recognition.":[58],"In":[59],"addition":[60],"MASC,":[62],"pre-trained":[64,70],"3-gram":[65],"language":[66,87],"model":[67,74,134],"automatic":[71],"recognition":[73,133],"are":[75],"also":[76,113],"developed":[77],"made":[79],"available":[80],"interested":[82],"researchers.":[83],"To":[84],"enhance":[85],"model,":[88],"new":[90],"inclusive":[92],"corpus":[95],"required,":[97],"thus,":[99],"12":[103],"M":[104],"unique":[105],"words,":[107],"originally":[108],"Twitter,":[111],"created":[114],"released.":[116],"Evaluating":[117],"our":[119],"newly":[120],"introduced":[121],"evaluation":[122],"sets,":[123],"best":[125],"word":[126],"error":[127],"rate":[128],"achieved":[129],"by":[130],"19.8%":[136],"for":[137,144],"clean":[139,146],"set":[141],"21.8%":[143],"test":[147],"set.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}