{"id":"W2122421814","doi":"10.1109/icecs.2007.4511252","title":"Iterative Noise-Compensated Method to Improve LPC Based Speech Analysis","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; Polytechnique Montréal","funders":"","keywords":"Autocorrelation; Noise (video); Noise power; Estimator; Linear predictive coding; Noise measurement; Linear prediction; Spectral density; Computer science; Speech enhancement; Mathematics; Algorithm; Autocorrelation matrix; Speech recognition; Spectral density estimation; Noise reduction; Speech coding; Fourier transform; Statistics; Power (physics); Artificial intelligence; Physics","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":[0.001238651,0.0001853136,0.0002925136,0.0005914386,0.0001381653,0.0003506239,0.0007017752,0.00006314588,0.0001920969],"category_scores_gemma":[0.00006723449,0.0001514201,0.0001535185,0.003647312,0.00001527752,0.0003808273,0.0001444128,0.000124096,0.0001316456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006482175,"about_ca_system_score_gemma":0.00008016996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007666262,"about_ca_topic_score_gemma":0.0001294123,"domain_scores_codex":[0.9981799,0.00006757435,0.0003126059,0.0006168531,0.0003555701,0.0004675159],"domain_scores_gemma":[0.9986602,0.0002376057,0.00009091448,0.0005386451,0.0002101506,0.000262451],"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":[0.00003576952,0.0001169431,0.002235375,0.0000113255,0.000253147,0.000112108,0.0006524944,0.0009448086,0.3112621,0.001050119,0.0007179641,0.6826078],"study_design_scores_gemma":[0.0002548935,0.00007254622,0.004054527,0.000006095321,0.00004889753,0.000003141694,0.00002635914,0.0608918,0.932838,0.0004154392,0.001147001,0.0002413462],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01005531,0.00001553801,0.9766034,0.001076902,0.000114229,0.0001486493,0.000001945554,0.0002678602,0.01171619],"genre_scores_gemma":[0.2177497,9.780358e-8,0.7775918,0.003658238,0.00004829177,0.000003484052,0.000003523582,0.000006624228,0.0009382598],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6823664,"threshold_uncertainty_score":0.6174734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01296510318368516,"score_gpt":0.3067240807342361,"score_spread":0.293758977550551,"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."}}