{"id":"W1519446688","doi":"10.1109/isspit.2004.1433721","title":"Acoustic training system for speaker independent continuous Arabic speech recognition system","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Bigram; Computer science; Speech recognition; Word error rate; Acoustic model; Vocabulary; Context (archaeology); Grammar; Natural language processing; Artificial intelligence; Language model; Test set; Word (group theory); Speaker recognition; Context-free grammar; Set (abstract data type); Hidden Markov model; Rule-based machine translation; Speech processing; Linguistics; Programming 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":[0.0008389846,0.000229577,0.000365905,0.0002146303,0.0001841104,0.0003087305,0.0004899083,0.0001442325,0.0001179409],"category_scores_gemma":[0.00009262291,0.0002041608,0.000180745,0.0002415236,0.00002135151,0.0005678966,0.00006098541,0.0001223846,0.001129744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002777048,"about_ca_system_score_gemma":0.00007411586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001542455,"about_ca_topic_score_gemma":0.00005241541,"domain_scores_codex":[0.9979486,0.00009577855,0.0005203108,0.0005612018,0.00040215,0.000471938],"domain_scores_gemma":[0.9986904,0.0002882114,0.000177438,0.0004014439,0.0002632457,0.0001792712],"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":[0.00001639239,0.00005563357,0.00001642786,0.000162539,0.00004446517,0.00003859329,0.0003865383,0.000016411,0.002012643,0.002146679,0.0009038656,0.9941998],"study_design_scores_gemma":[0.006495964,0.0005438181,0.0008058198,0.001891447,0.000313544,0.005248408,0.02393061,0.6608132,0.280513,0.0008312276,0.01600783,0.002605241],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06274569,0.00004435068,0.8793246,0.0004313258,0.001091491,0.0009371871,0.00002586256,0.001432633,0.0539669],"genre_scores_gemma":[0.829774,0.000002107318,0.1682824,0.0002412472,0.0004093722,0.0001252633,0.000009941414,0.00002190491,0.001133755],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9915946,"threshold_uncertainty_score":0.999648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04519592834410268,"score_gpt":0.2445552143919086,"score_spread":0.199359286047806,"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."}}