{"id":"W2405082712","doi":"10.21437/interspeech.2012-171","title":"A correlational discriminant approach to feature extraction for robust speech recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Linear discriminant analysis; Pattern recognition (psychology); Artificial intelligence; Euclidean distance; Speech recognition; Feature vector; Noise (video); Dimensionality reduction; Feature extraction; Discriminant; Mathematics; Computer science; Word error rate; Locality; Feature (linguistics); Correlation; Image (mathematics)","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":[0.0002391834,0.00008949895,0.00007511505,0.00007629875,0.0001507992,0.0001253592,0.0001678798,0.00006255351,0.00001217766],"category_scores_gemma":[0.00005813228,0.00007233282,0.00004329385,0.0002205829,0.000007064216,0.001295079,0.00004182231,0.00008214706,0.00007243729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004014459,"about_ca_system_score_gemma":0.00002713713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000364371,"about_ca_topic_score_gemma":0.000001851384,"domain_scores_codex":[0.9992335,0.00001236499,0.00009838765,0.0002182837,0.0001677831,0.0002697171],"domain_scores_gemma":[0.9995609,0.00004607429,0.00004877207,0.0001357247,0.00008772909,0.0001207964],"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":[0.00002342214,0.0002833686,0.0005709226,0.00003659097,0.00000889692,4.496762e-7,0.0005158756,0.0001367394,0.004829939,0.002544535,0.03308446,0.9579648],"study_design_scores_gemma":[0.002483934,0.0004496714,0.05641564,0.0002187458,0.0001106857,0.001125774,0.001196126,0.19652,0.626696,0.01675932,0.09574568,0.002278414],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003457179,0.00005723265,0.980164,0.001292784,0.0004908497,0.0002544609,0.000002962197,0.0001109103,0.01416961],"genre_scores_gemma":[0.07012338,0.000001335789,0.9263996,0.0004552208,0.0003541975,0.00005418194,0.00003417684,0.000006978265,0.002570964],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9556864,"threshold_uncertainty_score":0.2949647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06804125987193632,"score_gpt":0.2841385356375415,"score_spread":0.2160972757656052,"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."}}