{"id":"https://openalex.org/W4416037644","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.103","title":"MarsadLab at NADI Shared Task: Arabic Dialect Identification and Speech Recognition using ECAPA-TDNN and Whisper","display_name":"MarsadLab at NADI Shared Task: Arabic Dialect Identification and Speech Recognition using ECAPA-TDNN and Whisper","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037644","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.103"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.103","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.103.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.103.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051403530","display_name":"Md. Rafiul Biswas","orcid":"https://orcid.org/0000-0002-5145-1990"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Rafiul Biswas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kais Attia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kais Attia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036724034","display_name":"Shimaa Ibrahim","orcid":"https://orcid.org/0000-0002-9360-3673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shimaa Ibrahim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104453218","display_name":"Mabrouka Bessghaier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mabrouka Bessghaier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047390057","display_name":"Wajdi Zaghouani","orcid":"https://orcid.org/0000-0003-1521-5568"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wajdi Zaghouani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"752","last_page":"756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3427000045776367,"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":0.3427000045776367,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.15189999341964722,"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":0.1444000005722046,"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/identification","display_name":"Identification (biology)","score":0.6506999731063843},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5152999758720398},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.31150001287460327},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29989999532699585}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6506999731063843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.613099992275238},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5587999820709229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5182999968528748},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.503600001335144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4426000118255615},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2978000044822693}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.103","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.103.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.103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.103","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.103.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037644.pdf","grobid_xml":"https://content.openalex.org/works/W4416037644.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"participated":[1],"in":[2],"NADI":[3],"2025":[4],"shared":[5],"tasks":[6],"on":[7],"Arabic":[8,19],"Dialect":[9],"Identification":[10],"(ADI)":[11],"and":[12,38,47,61,73],"Automatic":[13],"Speech":[14],"Recognition":[15],"(ASR)":[16],"across":[17],"eight":[18],"dialects.For":[20],"ADI,":[21],"we":[22,52],"employ":[23],"an":[24],"enhanced":[25],"ECAPA-TDNN":[26],"with":[27,44,63,71],"VoxLin-gua107":[28],"initialization,":[29],"featuring":[30],"self-attention":[31],"classification":[32,86],"head,":[33],"progressive":[34],"unfreezing,":[35],"advanced":[36],"augmentation,":[37],"test-time":[39],"augmentation.This":[40],"approach":[41],"ranked":[42],"third":[43],"61.6%":[45],"accuracy":[46],"0.3068":[48],"macro":[49],"cost.For":[50],"ASR,":[51],"implement":[53],"a":[54],"zero-shot":[55],"cascaded":[56],"system":[57],"using":[58],"Whisper":[59],"Large-v3":[60],"MARBERT":[62],"extreme":[64],"parameter":[65],"efficiency":[66],"(0.0004%":[67],"trainable),":[68],"ranking":[69],"seventh":[70],"104.895WER":[72],"84.693":[74],"CER.Our":[75],"results":[76],"validate":[77],"complementary":[78],"paradigms:":[79],"direct":[80],"audio":[81],"processing":[82],"for":[83,91],"competitive":[84],"dialect":[85],"versus":[87],"foundation":[88],"model":[89],"robustness":[90],"cross-dialectal":[92],"transcription.":[93]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}