{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009281001,0.0005405026,0.0004673046,0.001737129,0.0004488133,0.0008921692,0.0004110017,0.0005703712,0.001361951],"category_scores_gemma":[0.003558591,0.0001561848,0.0002911179,0.0005519544,0.0002820287,0.0007572789,0.000537036,0.0004534657,0.001566469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003073367,"about_ca_system_score_gemma":0.0002897155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003215351,"about_ca_topic_score_gemma":0.00280975,"domain_scores_codex":[0.9989861,0.0003250982,0.00007060467,0.0002605283,0.0002599843,0.00009773699],"domain_scores_gemma":[0.9974515,0.001031852,0.0001876615,0.0002810575,0.000932544,0.00011539],"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":[0.001600294,0.0002513047,0.05822514,0.0005182325,0.0001017052,0.0004604422,0.001620324,0.009231337,0.2923902,0.001119115,0.00234342,0.6321384],"study_design_scores_gemma":[0.00008699787,0.0007288669,0.2089409,0.00007609423,0.0001570857,0.001891525,0.001473921,0.4125443,0.3653953,0.001662766,0.006901322,0.0001409213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9275226,0.0004155696,0.06683265,0.0001103088,0.00007335585,0.00009899437,0.0005910728,0.001490991,0.002864526],"genre_scores_gemma":[0.9429864,0.0001893268,0.05397748,0.00003924849,0.00003036506,0.00004655467,0.001108458,0.0001193489,0.001502864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003215351,"threshold_uncertainty_score":0.006393254,"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."}}