{"id":"W2248508985","doi":"10.21437/interspeech.2016-1297","title":"Automatic Dialect Detection in Arabic Broadcast Speech","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Modern Standard Arabic; Support vector machine; Artificial intelligence; Arabic; Classifier (UML); Speech recognition; Natural language processing; Language identification; Identification (biology); Linguistics; Natural language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000437343,0.0002482027,0.0003253875,0.000502528,0.00004532466,0.0002432578,0.0008645674,0.0002712614,0.0006930587],"category_scores_gemma":[0.000175266,0.0001916304,0.0001544364,0.0002868048,0.0000292227,0.0002216409,0.0006102098,0.0003275224,0.001094006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001929121,"about_ca_system_score_gemma":0.0001228277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001047038,"about_ca_topic_score_gemma":0.000222807,"domain_scores_codex":[0.9981381,0.0001792256,0.0003963118,0.0006599529,0.0003161048,0.0003103119],"domain_scores_gemma":[0.9986912,0.000213175,0.0001440304,0.000792486,0.00006779845,0.00009130128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001306677,0.00003643502,0.00006833448,0.00003312182,0.00001006929,0.00002805896,0.00005875731,8.450464e-7,0.0006441931,0.0002361424,0.0001332332,0.9987495],"study_design_scores_gemma":[0.001370093,0.0001371775,0.02271189,0.001468055,0.00003568092,0.0003208123,0.00003796778,0.460896,0.3129795,0.1940244,0.003816621,0.002201766],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1384199,0.00008720983,0.789383,0.001223808,0.002355791,0.0006494497,0.00000541375,0.001120248,0.06675515],"genre_scores_gemma":[0.9327797,0.00006562013,0.06508784,0.0002926548,0.000193024,0.0001286402,0.000002151414,0.0000229149,0.001427407],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9965478,"threshold_uncertainty_score":0.9996837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02530634784559521,"score_gpt":0.2544226352888353,"score_spread":0.2291162874432401,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}