{"id":"https://openalex.org/W4389518360","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.5","title":"ArTST: Arabic Text and Speech Transformer","display_name":"ArTST: Arabic Text and Speech Transformer","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518360","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.5"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.5","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.5","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.5.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ArabicNLP 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.arabicnlp-1.5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093129978","display_name":"Hawau Olamide Toyin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hawau Toyin","raw_affiliation_strings":["University of Artificial Intelligence Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093129979","display_name":"Amirbek Djanibekov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Amirbek Djanibekov","raw_affiliation_strings":["University of Artificial Intelligence Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026752360","display_name":"Ajinkya Kulkarni","orcid":"https://orcid.org/0009-0009-5915-6513","observed_orcids":["https://orcid.org/0009-0009-5915-6513"]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ajinkya Kulkarni","raw_affiliation_strings":["University of Artificial Intelligence Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002602581","display_name":"Hanan Aldarmaki","orcid":"https://orcid.org/0000-0003-1706-1777","observed_orcids":["https://orcid.org/0000-0003-1706-1777"]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hanan Aldarmaki","raw_affiliation_strings":["University of Artificial Intelligence Abu Dhabi, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Artificial Intelligence Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113480"],"apc_list":null,"apc_paid":null,"fwci":1.5908,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86720218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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":0.8510000109672546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.9639999866485596},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.9860000014305115},{"id":"https://openalex.org/keywords/low-resource-speech-synthesis","display_name":"low-resource speech synthesis","score":0.7250000238418579},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155659437179565},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7997626066207886},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.660596489906311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6180731058120728},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6069316864013672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5798075199127197},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4944024085998535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4760544002056122},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4424419403076172},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4161493182182312},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2381455898284912},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09397321939468384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0805465579032898},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.arabicnlp-1.5","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.5","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.5.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ArabicNLP 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.16621","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.16621","pdf_url":"https://arxiv.org/pdf/2310.16621","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.16621","doi":"https://doi.org/10.48550/arxiv.2310.16621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.16621","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.arabicnlp-1.5","doi":"https://doi.org/10.18653/v1/2023.arabicnlp-1.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.arabicnlp-1.5","pdf_url":"https://aclanthology.org/2023.arabicnlp-1.5.pdf","source":{"id":"https://openalex.org/S7407104720","display_name":"Arabic Natural Language Processing Conference (ArabicNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ArabicNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.5600000023841858,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518360.pdf","grobid_xml":"https://content.openalex.org/works/W4389518360.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1978660892","https://openalex.org/W2025198378","https://openalex.org/W2626778328","https://openalex.org/W2756127416","https://openalex.org/W2769437540","https://openalex.org/W2775461895","https://openalex.org/W2786835190","https://openalex.org/W2963077089","https://openalex.org/W2963341956","https://openalex.org/W2964309797","https://openalex.org/W2971840980","https://openalex.org/W2981852735","https://openalex.org/W3007095894","https://openalex.org/W3016021175","https://openalex.org/W3016057683","https://openalex.org/W3030163527","https://openalex.org/W3036601975","https://openalex.org/W3162046328","https://openalex.org/W3169320628","https://openalex.org/W3175210284","https://openalex.org/W3205644108","https://openalex.org/W3213029956","https://openalex.org/W4225615476","https://openalex.org/W4283640572","https://openalex.org/W4285289306","https://openalex.org/W4311000453","https://openalex.org/W4313532822","https://openalex.org/W4378105483","https://openalex.org/W4385822416","https://openalex.org/W4385823222","https://openalex.org/W4385823382","https://openalex.org/W7133184166"],"related_works":["https://openalex.org/W4386056881","https://openalex.org/W3045249863","https://openalex.org/W7140119707","https://openalex.org/W4416251749","https://openalex.org/W6922514487","https://openalex.org/W4416955854","https://openalex.org/W4285289306","https://openalex.org/W7126408813","https://openalex.org/W7125155217","https://openalex.org/W4406322602"],"abstract_inverted_index":{"We":[0],"present":[1],"ArTST,":[2],"a":[3,102],"pre-trained":[4,132],"Arabic":[5,17,38,50],"text":[6,63],"and":[7,32,48,62,65,79,140],"speech":[8,13,61],"transformer":[9],"for":[10,15,30,46,68,121,145],"supporting":[11],"opensource":[12],"technologies":[14],"the":[16,22,44,55,69,107,128,137],"language.The":[18],"model":[19,45,56,133],"architecture":[20],"follows":[21],"unified-modal":[23],"framework,":[24],"SpeechT5,":[25,88],"that":[26,116],"was":[27],"recently":[28],"released":[29,144],"English,":[31],"is":[33,119,124],"focused":[34],"on":[35,59,101],"Modern":[36],"Standard":[37],"(MSA),":[39],"with":[40,87,92,104],"plans":[41],"to":[42],"extend":[43],"dialectal":[47],"codeswitched":[49],"in":[51,96,110,127],"future":[52],"editions.We":[53],"pretrained":[54],"from":[57],"scratch":[58],"MSA":[60],"data,":[64],"fine-tuned":[66,138],"it":[67],"following":[70],"tasks:":[71],"Automatic":[72],"Speech":[73],"Recognition":[74],"(ASR),":[75],"Text-To-Speech":[76],"synthesis":[77],"(TTS),":[78],"spoken":[80],"dialect":[81],"identification.In":[82],"our":[83,117],"experiments":[84],"comparing":[85],"ArTST":[86,99],"as":[89,91,134,136],"well":[90,135],"previously":[93],"reported":[94],"results":[95],"these":[97],"tasks,":[98],"performs":[100],"par":[103],"or":[105],"exceeding":[106],"current":[108],"state-of-the-art":[109],"all":[111],"three":[112],"tasks.Moreover,":[113],"we":[114],"find":[115],"pre-training":[118],"conducive":[120],"generalization,":[122],"which":[123],"particularly":[125],"evident":[126],"low-resource":[129],"TTS":[130,141],"task.The":[131],"ASR":[139],"models":[142],"are":[143],"research":[146],"use.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-12-10T00:00:00"}
