{"id":"W2254811285","doi":"10.5430/air.v5n2p14","title":"A robust BFCC feature extraction for ASR system","year":2016,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mel-frequency cepstrum; Spectrogram; Speech recognition; Feature extraction; Cepstrum; Computer science; Hidden Markov model; Robustness (evolution); Pattern recognition (psychology); Artificial intelligence; Noise (video); Wavelet","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002202059,0.0001219195,0.0001412621,0.0002686375,0.0005326172,0.0004695096,0.0009676467,0.0001243883,0.00002282322],"category_scores_gemma":[0.0006405122,0.0000831037,0.0000802967,0.0008421387,0.0001319595,0.0008000617,0.0001694656,0.0002398272,0.0005318708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002114345,"about_ca_system_score_gemma":0.0002072029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000275831,"about_ca_topic_score_gemma":0.00004199384,"domain_scores_codex":[0.9976358,0.0001390728,0.0002570267,0.0005697212,0.0006545062,0.0007438764],"domain_scores_gemma":[0.9977819,0.0008003632,0.00006605445,0.0005069664,0.0006764763,0.0001681962],"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":[0.00003559281,0.0000424036,0.00002767159,0.0000458097,0.000006986967,0.00001355155,0.0001566753,0.00003124803,0.08717158,0.07942665,0.001709437,0.8313324],"study_design_scores_gemma":[0.00003133312,0.0001515441,0.00001762312,0.0001984581,0.000002020557,0.00002741441,0.0004511946,0.0119296,0.9278884,0.05393623,0.005208267,0.0001579442],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005440065,0.0001703933,0.984047,0.007766434,0.0004678082,0.0003823422,0.000003528379,0.0002024015,0.001520017],"genre_scores_gemma":[0.9475666,0.00003419958,0.05045477,0.00003665344,0.0005392868,0.0001238439,9.534065e-7,0.0000168425,0.001226888],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9421265,"threshold_uncertainty_score":0.68363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2723750335187968,"score_gpt":0.4239095653915988,"score_spread":0.151534531872802,"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."}}