{"id":"W2222372807","doi":"10.5281/zenodo.44180","title":"Robust Feature Extractors For Continuous Speech Recognition","year":2014,"lang":"en","type":"article","venue":"INFM-OAR (INFN Catania)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Mel-frequency cepstrum; Robustness (evolution); Speech recognition; Computer science; Multitaper; Cepstrum; Filter bank; Estimator; Feature extraction; Pattern recognition (psychology); Reverberation; Feature (linguistics); Artificial intelligence; Filter (signal processing); Mathematics; Computer vision; Engineering; Statistics","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":[0.0005134962,0.0002453626,0.0002806239,0.0001281551,0.0002528163,0.0004581617,0.0008018415,0.000197525,0.00002515005],"category_scores_gemma":[0.0003947634,0.0002367823,0.0001222547,0.0003552916,0.00005131607,0.001007628,0.0001211768,0.0002637006,0.0002047959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006239899,"about_ca_system_score_gemma":0.00009099691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001872601,"about_ca_topic_score_gemma":0.0000328045,"domain_scores_codex":[0.9982808,0.00004472732,0.0002720843,0.0005690862,0.0003157759,0.0005174773],"domain_scores_gemma":[0.9985492,0.000220435,0.0002133788,0.0005795993,0.0002668416,0.0001705897],"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":[0.00002706015,0.00007444608,0.0005708536,0.000079807,0.00002393422,0.00001795011,0.0003304581,0.00002272222,0.0143907,0.0002830774,0.03421388,0.9499651],"study_design_scores_gemma":[0.002255436,0.0005321418,0.002763684,0.0002803522,0.00006234245,0.0003055498,0.0001203555,0.007032016,0.5834416,0.01369987,0.3881513,0.00135536],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.19671,0.0005094768,0.7803673,0.005884349,0.002964878,0.0009709407,0.00007209267,0.001151121,0.01136985],"genre_scores_gemma":[0.3987207,0.00002423663,0.5941598,0.002724077,0.002169538,0.00008988811,0.0001387529,0.00007075603,0.001902243],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9486098,"threshold_uncertainty_score":0.96557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03317134805386213,"score_gpt":0.2394458743714554,"score_spread":0.2062745263175932,"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."}}