{"id":"W2168937832","doi":"10.1109/newcas.2007.4487956","title":"Improving LPC analysis of speech in additive noise","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; Polytechnique Montréal","funders":"","keywords":"Noise (video); Autoregressive model; Autocorrelation; Estimator; Spectral density; Speech enhancement; Noise measurement; Noise power; Speech recognition; Mathematics; Linear prediction; Value noise; Computer science; Noise reduction; Statistics; Noise floor; Physics; Power (physics); Artificial intelligence","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":[0.0004572838,0.0000631377,0.0001606937,0.0005446399,0.00002222714,0.00003633382,0.0003363782,0.000032051,0.00005313249],"category_scores_gemma":[0.00006296971,0.000055001,0.00006470201,0.002367054,0.00001994754,0.0003081712,0.0001002291,0.00006348507,0.000007196256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000304485,"about_ca_system_score_gemma":0.00004016547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001762904,"about_ca_topic_score_gemma":0.0006330849,"domain_scores_codex":[0.9991769,0.000009674972,0.0002168202,0.0002138098,0.0001726486,0.0002101576],"domain_scores_gemma":[0.9994928,0.00008983311,0.0000873145,0.0002153353,0.00006743825,0.00004730512],"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":[0.000003786445,0.00002945679,0.009152159,0.000004825985,0.00004122175,0.00003169954,0.0002838883,0.00003610215,0.02352787,0.0005147395,0.00002765611,0.9663466],"study_design_scores_gemma":[0.0001629056,0.00002311581,0.06148685,0.00001005049,0.00002931779,0.000001925951,0.00009684645,0.02008144,0.9175571,0.0003556332,0.00008376977,0.0001110338],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2709458,0.00004638734,0.7160785,0.00007063656,0.0000396359,0.00003464032,0.000001067349,0.00004190217,0.01274137],"genre_scores_gemma":[0.8475059,0.000001696519,0.1521531,0.0001312923,0.00001910856,5.658917e-7,0.00000122129,0.000002040821,0.000185042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9662356,"threshold_uncertainty_score":0.2242876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008646314321895327,"score_gpt":0.2521419328331512,"score_spread":0.2434956185112559,"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."}}