{"id":"W1963733617","doi":"10.1007/s10772-012-9146-4","title":"Speaker-independent ASR for Modern Standard Arabic: effect of regional accents","year":2012,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Speech recognition; Hidden Markov model; Arabic; Stress (linguistics); Modern Standard Arabic; Natural language processing; Artificial intelligence; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0009445513,0.0001482891,0.0003471565,0.0008181737,0.00003536967,0.0000440769,0.001600742,0.0001734349,0.00006613276],"category_scores_gemma":[0.0004425246,0.0001196441,0.0002432143,0.0001976574,0.00008627564,0.0005924415,0.0001856827,0.0002442145,0.00001621596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001611736,"about_ca_system_score_gemma":0.0000802042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002796408,"about_ca_topic_score_gemma":0.000002171513,"domain_scores_codex":[0.9981272,0.00004945345,0.0005737797,0.0001623588,0.0008202199,0.0002670286],"domain_scores_gemma":[0.9978858,0.0002610164,0.0006272923,0.0002275856,0.0009039968,0.00009431333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000356793,0.0001468851,0.009803661,0.00001355154,0.0003204619,0.00005033211,0.00008281356,0.000005714831,0.009412422,0.01187828,0.001266878,0.9666622],"study_design_scores_gemma":[0.004428855,0.001396549,0.003405634,0.0002439448,0.00007311768,0.004210714,0.00006969796,0.001658959,0.8930755,0.05262996,0.03845209,0.0003549669],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5369667,0.0005248546,0.4508267,0.007830136,0.002676678,0.0002733956,0.00002752642,0.00008328895,0.0007906384],"genre_scores_gemma":[0.9134395,0.00008644439,0.08590204,0.0001277947,0.0003498298,0.000008320448,0.000001938896,0.00001190316,0.00007228641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9663072,"threshold_uncertainty_score":0.4878946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02049470695497841,"score_gpt":0.304830386805333,"score_spread":0.2843356798503546,"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."}}