{"id":"W1972404024","doi":"10.1109/dsp-spe.2013.6642556","title":"Diacritization, automatic segmentation and labeling for Levantine Arabic speech","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Arabic; Pronunciation; Transcription (linguistics); Segmentation; Speech recognition; Phonetic transcription; Artificial intelligence; Natural language processing; Speech processing; Speech corpus; Reliability (semiconductor); Speech synthesis; 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":[0.0001358373,0.00006206537,0.00007600694,0.00006700176,0.00008432451,0.00022383,0.0001036128,0.00002362898,0.0002444092],"category_scores_gemma":[0.0001096034,0.00005284072,0.00001957207,0.0001237102,0.00001166449,0.0005273488,0.00002786948,0.00001820772,0.0001260993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008173157,"about_ca_system_score_gemma":0.0000105933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001523264,"about_ca_topic_score_gemma":0.000004201012,"domain_scores_codex":[0.9994588,0.00001890397,0.0001477144,0.0001647932,0.00009428386,0.0001154783],"domain_scores_gemma":[0.9995211,0.0001573459,0.00003411693,0.0001110243,0.0001298264,0.00004657678],"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":[2.955364e-7,0.0000247376,0.0004649953,0.00003461508,0.000008066247,3.89758e-7,0.0001178241,7.254685e-7,0.01312186,0.006386127,0.001544607,0.9782957],"study_design_scores_gemma":[0.0005638594,0.0000446985,0.005655488,0.00003307575,0.00001081743,0.0000228182,0.0001474884,0.9095581,0.06020385,0.02309463,0.0004443548,0.0002208975],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1020361,0.00003480692,0.8937559,0.002027265,0.0001086583,0.0003973734,0.000001060912,0.0002149727,0.001423874],"genre_scores_gemma":[0.1371306,0.00002140489,0.8611416,0.0008407005,0.00003147162,0.00008904306,0.000005793347,0.000006273395,0.000733168],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9780748,"threshold_uncertainty_score":0.2676109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01597975717295269,"score_gpt":0.2456386191799418,"score_spread":0.2296588620069892,"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."}}