{"id":"W2128028443","doi":"10.1109/icassp.1996.541097","title":"Compensated mel frequency cepstrum coefficients","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Emphasis (telecommunications); Cepstrum; Energy (signal processing); Speech recognition; Mel-frequency cepstrum; Computer science; Filter (signal processing); Noise (video); SIGNAL (programming language); Range (aeronautics); Signal-to-noise ratio (imaging); High-pass filter; Low-pass filter; Algorithm; Mathematics; Artificial intelligence; Feature extraction; Telecommunications; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007027468,0.00009531216,0.00009632568,0.00006333959,0.0001354584,0.0001809839,0.0006512444,0.00003568291,0.0005677043],"category_scores_gemma":[0.00001923104,0.00007925413,0.00003187083,0.0004346819,0.00003029764,0.0003454514,0.0001057347,0.00007731748,0.001003615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001918818,"about_ca_system_score_gemma":0.00001124033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001140297,"about_ca_topic_score_gemma":0.000003068171,"domain_scores_codex":[0.9990657,0.00001737479,0.0001419181,0.0002669694,0.0002200184,0.0002879967],"domain_scores_gemma":[0.9994661,0.00002015237,0.00004147594,0.0003221176,0.00005502962,0.00009510542],"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":[0.000003046613,0.0007407541,0.01361018,0.00004351848,0.00005195471,0.0001972956,0.001946764,0.0001322374,0.08392125,0.04359557,0.04541568,0.8103418],"study_design_scores_gemma":[0.002264449,0.0002889027,0.007649256,0.00009518072,0.00001318882,0.0001933328,0.0001066782,0.2425617,0.7142898,0.01275607,0.01840646,0.001374985],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07538336,0.0002969158,0.7293257,0.002330827,0.0005360678,0.0001076316,0.000001064601,0.0007945232,0.1912239],"genre_scores_gemma":[0.9075982,0.000004921481,0.08920443,0.000997237,0.00002676173,0.000001658821,7.142161e-7,0.000005045637,0.002161042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8322148,"threshold_uncertainty_score":0.9997742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02378993394482777,"score_gpt":0.2196919223242506,"score_spread":0.1959019883794228,"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."}}