{"id":"W7052987733","doi":"","title":"Speech enhancement using a reduced complexity MFCC-based Deep Neural Network","year":2018,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Particle Accelerators and Free-Electron Lasers","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Speech enhancement; Mel-frequency cepstrum; Cepstrum; Noise (video); Benchmark (surveying); Artificial neural network; Logarithm; Noise reduction; Frequency domain; Reduction (mathematics)","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005239939,0.001004772,0.0008885111,0.0002497029,0.001011942,0.0001591922,0.0006868646,0.000655666,0.0004894394],"category_scores_gemma":[0.00009725658,0.001159345,0.0003759758,0.0008515012,0.00009718491,0.0005108961,0.00006464375,0.001318,0.000216174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001177687,"about_ca_system_score_gemma":0.00005085546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001825142,"about_ca_topic_score_gemma":0.001918333,"domain_scores_codex":[0.9955633,0.0001939176,0.001008643,0.0009530321,0.0007386281,0.001542447],"domain_scores_gemma":[0.9979435,0.00007917015,0.0003284875,0.0008856491,0.0002980818,0.0004650666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005705955,0.0003378098,0.00006103708,0.0005834819,0.0007779729,0.0001524621,0.00001392532,0.03549476,0.8356168,0.004475194,0.00008726331,0.1218287],"study_design_scores_gemma":[0.001538508,0.0003156655,0.0005601894,0.0003300456,0.0004039338,0.00002085723,0.00005688499,0.1697599,0.8056304,0.003414315,0.01576181,0.002207535],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819176,0.00042527,0.00001687822,0.000004251097,0.002739383,0.0007337284,0.000209856,0.0006562627,0.01329673],"genre_scores_gemma":[0.9925023,0.00004384948,0.005426895,0.0001736051,0.0003317605,0.0001036558,0.000835645,0.0003350505,0.0002471903],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1342651,"threshold_uncertainty_score":0.9990857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03223565658942936,"score_gpt":0.2569105805143486,"score_spread":0.2246749239249193,"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."}}