{"id":"W1885745269","doi":"10.1109/icassp.2005.1415064","title":"Discriminative Training Based on the Criterion of Least Phone Competing Tokens for Large Vocabulary Speech Recognition","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University","keywords":"Security token; Computer science; Discriminative model; Hidden Markov model; Speech recognition; Word error rate; Phone; Normalization (sociology); Vocabulary; Sigmoid function; Artificial intelligence; Set (abstract data type); Generalization; Overfitting; Pattern recognition (psychology); Artificial neural network; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002002879,0.0009383766,0.001705822,0.0006691224,0.0005145305,0.0005906657,0.001878611,0.0008906688,0.002229635],"category_scores_gemma":[0.006862669,0.000708915,0.0004858928,0.001096784,0.0008400689,0.001447984,0.001422319,0.001315312,0.001226967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006948979,"about_ca_system_score_gemma":0.001386735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003109506,"about_ca_topic_score_gemma":0.00670455,"domain_scores_codex":[0.9984864,0.0005165321,0.00009500892,0.0004073922,0.0003735597,0.0001211466],"domain_scores_gemma":[0.9971498,0.001803252,0.0001752952,0.0004119671,0.0003537786,0.0001059357],"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":[0.0004097392,0.0002849676,0.002410283,0.0002285612,0.0001238407,0.0001561091,0.0001469839,0.2569126,0.03657201,0.009110552,0.004821427,0.6888231],"study_design_scores_gemma":[0.0000254114,0.00006678528,0.0008513503,0.000005321208,0.00001359508,0.0001071495,0.00001723013,0.9882423,0.006897568,0.002969163,0.0007900013,0.00001408368],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0122929,0.0001442246,0.9859157,0.00009110622,0.00001843137,0.00004630041,0.00004933187,0.0009293889,0.0005126175],"genre_scores_gemma":[0.4595674,0.0001865086,0.532752,0.0004154907,0.00007887361,0.0004637092,0.001043754,0.0005523688,0.00493984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003109506,"threshold_uncertainty_score":0.01059234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06140262388372575,"score_gpt":0.26316123209178,"score_spread":0.2017586082080542,"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."}}