{"id":"W1981932308","doi":"10.1109/icassp.2010.5495109","title":"I-smooth for improved minimum classification error training","year":2010,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Hidden Markov model; TIMIT; Discriminative model; Computer science; Boundary (topology); Interpolation (computer graphics); Generalization; Speech recognition; Word error rate; Pattern recognition (psychology); Confusion; Artificial intelligence; Training (meteorology); Training set; Task (project management); Mathematics; Engineering","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":[0.001765338,0.0008110969,0.0008574782,0.0006881948,0.0004552183,0.000718601,0.001526339,0.001344104,0.005049818],"category_scores_gemma":[0.008513427,0.0005455493,0.0005699915,0.0006700203,0.0005922599,0.001139169,0.001718081,0.002147816,0.002109163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004365824,"about_ca_system_score_gemma":0.0008746081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002996754,"about_ca_topic_score_gemma":0.004206562,"domain_scores_codex":[0.9991016,0.0002147185,0.00004950063,0.0002532493,0.0002790468,0.0001018363],"domain_scores_gemma":[0.9975358,0.001259353,0.0001044914,0.0005872366,0.0004290398,0.00008398842],"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":[0.0007511752,0.0002417808,0.002813642,0.000161439,0.0000625221,0.0001359829,0.0002397069,0.2194401,0.03870609,0.01072078,0.006338153,0.7203887],"study_design_scores_gemma":[0.00001522433,0.0000481454,0.0007248122,0.00001125765,0.000008090455,0.00004773562,0.00001661072,0.9862691,0.0090294,0.001993665,0.001824329,0.00001166091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02775985,0.0002421635,0.965598,0.0001666543,0.00006371193,0.00004775026,0.0001117272,0.004014256,0.001995783],"genre_scores_gemma":[0.3477462,0.0001701184,0.6422281,0.000210609,0.00005355769,0.0002022885,0.0009617117,0.0008524983,0.007574956],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005049818,"threshold_uncertainty_score":0.01689333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0834741312720563,"score_gpt":0.2978591173893709,"score_spread":0.2143849861173146,"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."}}