{"id":"https://openalex.org/W4416037793","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.104","title":"Abjad AI at NADI 2025: CATT-Whisper: Multimodal Diacritic Restoration Using Text and Speech Representations","display_name":"Abjad AI at NADI 2025: CATT-Whisper: Multimodal Diacritic Restoration Using Text and Speech Representations","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037793","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.104"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.104","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.104","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.104.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.104.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065854100","display_name":"Ahmad Ghannam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153053","display_name":"King Khaled Hospital","ror":"https://ror.org/053vynf43","country_code":"SA","type":"healthcare","lineage":["https://openalex.org/I4210153053"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ahmad Ghannam","raw_affiliation_strings":["Abjad AI. King Khaled Road . Riyadh 11000 , Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Abjad AI. King Khaled Road . Riyadh 11000 , Saudi Arabia","institution_ids":["https://openalex.org/I4210153053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106356606","display_name":"Naif Wasel Alharthi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153053","display_name":"King Khaled Hospital","ror":"https://ror.org/053vynf43","country_code":"SA","type":"healthcare","lineage":["https://openalex.org/I4210153053"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Naif Alharthi","raw_affiliation_strings":["Abjad AI. King Khaled Road . Riyadh 11000 , Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Abjad AI. King Khaled Road . Riyadh 11000 , Saudi Arabia","institution_ids":["https://openalex.org/I4210153053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062834163","display_name":"Faris Alasmary","orcid":"https://orcid.org/0000-0002-5025-4020"},"institutions":[{"id":"https://openalex.org/I4210153053","display_name":"King Khaled Hospital","ror":"https://ror.org/053vynf43","country_code":"SA","type":"healthcare","lineage":["https://openalex.org/I4210153053"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Faris Alasmary","raw_affiliation_strings":["Abjad AI. King Khaled Road . Riyadh 11000 , Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Abjad AI. King Khaled Road . Riyadh 11000 , Saudi Arabia","institution_ids":["https://openalex.org/I4210153053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120309408","display_name":"Kholood Al Tabash","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kholood Al Tabash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120309409","display_name":"Shouq Sadah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shouq Sadah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069736728","display_name":"Lahouari Ghouti","orcid":"https://orcid.org/0000-0002-6381-4250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lahouari Ghouti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31039336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"757","last_page":"761"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.24150000512599945,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.24150000512599945,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.06790000200271606,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.05999999865889549,"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/natural-language","display_name":"Natural language","score":0.3206999897956848},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.29919999837875366},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26820001006126404},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.24120000004768372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6367999911308289},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5550000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550000011920929},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3862000107765198},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.24120000004768372},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.21400000154972076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.104","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.104","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.104.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.104","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.104","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.104.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037793.pdf","grobid_xml":"https://content.openalex.org/works/W4416037793.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,157],"tackle":[4],"the":[5,30,49,53,69,73,80,84,116,123,145,160,166,178,198,201],"Diacritic":[6],"Restoration":[7],"(DR)":[8],"task":[9],"for":[10,149],"Arabic":[11],"dialectal":[12],"sentences":[13],"using":[14,33],"a":[15,26,107,182,190],"multimodal":[16],"approach":[17,180],"that":[18,28,177],"combines":[19],"both":[20],"textual":[21],"and":[22,134,189,208,213],"speech":[23,44,70,96,135,161],"information.We":[24],"propose":[25],"model":[27,41,155,167,205],"represents":[29],"text":[31,117,133],"modality":[32],"an":[34,76],"encoder":[35,50,125],"extracted":[36],"from":[37],"our":[38,204],"own":[39],"pretrained":[40],"named":[42],"CATT.The":[43],"component":[45],"is":[46,59,120,141],"handled":[47],"by":[48,122],"module":[51],"of":[52,67,83,187,195,211],"OpenAI":[54],"Whisper":[55],"base":[56],"model.Our":[57],"solution":[58],"designed":[60],"following":[61],"two":[62],"integration":[63],"strategies.The":[64],"former":[65],"consists":[66],"fusing":[68],"tokens":[71,103],"with":[72,115,171],"input":[74,162],"at":[75],"early":[77],"stage,":[78],"where":[79,132],"1500":[81],"frames":[82],"audio":[85],"segment":[86],"are":[87,104,137],"averaged":[88,102],"over":[89],"10":[90],"consecutive":[91],"frames,":[92],"resulting":[93],"in":[94],"150":[95],"tokens.To":[97],"ensure":[98],"embedding":[99],"compatibility,":[100],"these":[101],"processed":[105],"through":[106],"linear":[108],"projection":[109],"layer":[110],"prior":[111],"to":[112,144,168],"merging":[113],"them":[114],"tokens.Contextual":[118],"encoding":[119],"guaranteed":[121],"CATT":[124,146],"module.The":[126],"latter":[127],"strategy":[128],"relies":[129],"on":[130,197],"cross-attention,":[131],"embeddings":[136],"fused.The":[138],"cross-attention":[139],"output":[140],"then":[142],"fed":[143],"classification":[147],"head":[148],"token-level":[150],"diacritic":[151],"prediction.To":[152],"further":[153],"improve":[154],"robustness,":[156],"randomly":[158],"deactivate":[159],"during":[163],"training,":[164],"allowing":[165],"perform":[169],"well":[170],"or":[172],"without":[173],"speech.Our":[174],"experiments":[175],"show":[176],"proposed":[179],"achieves":[181],"word":[183],"error":[184,192],"rate":[185,193],"(WER)":[186],"0.25":[188],"character":[191],"(CER)":[194],"0.9":[196],"development":[199],"set.On":[200],"test":[202],"set,":[203],"achieved":[206],"WER":[207],"CER":[209],"scores":[210],"0.55":[212],"0.13,":[214],"respectively.":[215]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}