{"id":"W2167191127","doi":"10.1109/icassp.1989.266415","title":"A comparison of several acoustic representations for speech recognition with degraded and undegraded speech","year":2003,"lang":"en","type":"article","venue":"International Conference on Acoustics, Speech, and Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Speech recognition; Cepstrum; Mel-frequency cepstrum; Computer science; Weighting; Noise (video); Filter (signal processing); Filter bank; Pattern recognition (psychology); Mathematics; Artificial intelligence; Feature extraction; Acoustics","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":[0.0003272082,0.0002529319,0.0003472191,0.0002915036,0.0002260047,0.0004009448,0.0002981034,0.0001160877,0.0001100952],"category_scores_gemma":[0.0002875671,0.0002266784,0.00005411427,0.0002076783,0.0001945798,0.0004969682,0.00004330405,0.0002142599,0.000004524756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004920146,"about_ca_system_score_gemma":0.0002021509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002616599,"about_ca_topic_score_gemma":0.00003254113,"domain_scores_codex":[0.9981011,0.00007925168,0.0004722827,0.0005574941,0.0005242187,0.0002656188],"domain_scores_gemma":[0.9981411,0.0003759021,0.000329916,0.0001614663,0.0008513931,0.0001402308],"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":[0.0003609279,0.0006856981,0.002236552,0.0002954062,0.0001801319,0.00005741455,0.001262284,0.0001953864,0.04958961,0.01605208,0.0003434296,0.9287411],"study_design_scores_gemma":[0.002860837,0.0008441822,0.001836114,0.0008054633,0.0001755974,0.0004799555,0.003271317,0.8128352,0.1036616,0.07219441,0.0001745675,0.0008607252],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09952361,0.00007561113,0.8930845,0.0007522169,0.0001882954,0.000441611,0.00006997891,0.00009432064,0.005769856],"genre_scores_gemma":[0.7847447,0.00004716525,0.2146803,0.0001790591,0.00005278606,0.00002357869,0.0000314838,0.00001524532,0.0002257248],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9278803,"threshold_uncertainty_score":0.9243675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1034577501804792,"score_gpt":0.3427565667719608,"score_spread":0.2392988165914816,"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."}}