{"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":{"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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5084187172","display_name":"Mohammad Al-Fetyani","orcid":"https://orcid.org/0000-0002-7360-2403"},"institutions":[],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Mohammad Al-Fetyani","raw_affiliation_strings":["Appswave, Amman, Jordan"],"affiliations":[{"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":[],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Muhammad Al-Barham","raw_affiliation_strings":["Appswave, Amman, Jordan"],"affiliations":[{"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"],"affiliations":[{"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"],"affiliations":[{"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":[],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Maha Dawas","raw_affiliation_strings":["Planning and Statistics Authority, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Planning and Statistics Authority, Doha, Qatar","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.412,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.558059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":78,"max":84},"biblio":{"volume":null,"issue":null,"first_page":"1006","last_page":"1013"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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":0.9982,"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":0.9932,"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/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.71530414}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7772716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762811},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.71530414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.66127634},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6149928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6091221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5719644},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.43966115},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41556808},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41269127},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.35810727},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24438876},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07584968},{"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":[{"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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality education","score":0.41,"id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":16,"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"],"related_works":["https://openalex.org/W4319862671","https://openalex.org/W4297524714","https://openalex.org/W39910498","https://openalex.org/W2545528998","https://openalex.org/W2276683421","https://openalex.org/W2147500075","https://openalex.org/W2021513757","https://openalex.org/W1989887389","https://openalex.org/W1772447446","https://openalex.org/W1501126083"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,6,50,93,131,138,145,152],"creation":[4],"of":[5,27,54,109],"Massive":[7],"Arabic":[8,55,63,100,113],"Speech":[9],"Corpus":[10],"(MASC)":[11],"1":[14,17],"https://ieee-dataport.org/open-access/massive-arabic-speech-corpus-masc.":[18],"MASC":[19],"is":[20,42,103,119,142],"a":[21,59,70,76,96,107],"dataset":[22,41,108],"that":[23],"contains":[24],"1,000":[25],"hours":[26],"speech":[28,56,64,79,101,139],"sampled":[29],"at":[30],"16":[31],"kHz":[32],"and":[33,45,52,75,85,98,105,122,149],"crawled":[34,116],"from":[35,117],"over":[36],"700":[37],"YouTube":[38],"channels.":[39],"The":[40],"multi-regional,":[43],"multi-genre,":[44],"multi-dialect":[46],"intended":[47],"to":[48,68,88],"advance":[49],"research":[51],"development":[53,147],"technology":[57],"with":[58],"special":[60],"emphasis":[61],"on":[62,125],"recognition.":[65],"In":[66],"addition":[67],"MASC,":[69],"pre-trained":[71,77],"3-gram":[72],"language":[73,94],"model":[74,81,141],"automatic":[78],"recognition":[80,140],"are":[82],"also":[83,120],"developed":[84],"made":[86],"available":[87],"interested":[89],"researchers.":[90],"To":[91],"enhance":[92],"model,":[95],"new":[97],"inclusive":[99],"corpus":[102],"required,":[104],"thus,":[106],"12":[110],"M":[111],"unique":[112],"words,":[114],"originally":[115],"Twitter,":[118],"created":[121],"released.":[123],"Evaluating":[124],"our":[126],"newly":[127],"introduced":[128],"evaluation":[129],"sets,":[130],"best":[132],"word":[133],"error":[134],"rate":[135],"achieved":[136],"by":[137],"19.8%":[143],"for":[144,151],"clean":[146,153],"set":[148],"21.8%":[150],"test":[154],"set.":[155]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4319862671","counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-01-01T20:37:43.090197","created_date":"2023-02-11"}