{"id":"W2015926323","doi":"10.1016/s0167-6393(00)00081-9","title":"Speech enhancement using fourth-order cumulants and optimum filters in the subband domain","year":2002,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Speech recognition; Speech enhancement; Computer science; Noise (video); Frequency domain; Gaussian noise; Noise reduction; Speech processing; Spectrogram; Linear predictive coding; Mathematics; Algorithm; 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":[0.0007969296,0.0001390593,0.0001361549,0.0001131937,0.0002917656,0.0003198287,0.001221129,0.00005713219,0.00002842992],"category_scores_gemma":[0.0000436466,0.0001127975,0.00002495473,0.0005429999,0.00007834613,0.0005727978,0.0003217671,0.000231485,0.00002166527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000635915,"about_ca_system_score_gemma":0.00001923543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009047562,"about_ca_topic_score_gemma":0.00008663704,"domain_scores_codex":[0.9987222,0.0001890479,0.0002526347,0.0002607741,0.0002967185,0.0002786292],"domain_scores_gemma":[0.9985318,0.0001278329,0.0001243256,0.001109632,0.00006352953,0.00004287088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002893104,0.0007628471,0.007287392,0.00009832086,0.00005667889,0.0001061709,0.0289678,0.0007711025,0.07406516,0.001742297,0.002112271,0.884001],"study_design_scores_gemma":[0.005328243,0.0003855533,0.009163622,0.0009981787,0.00005409475,0.001067568,0.003261744,0.5709387,0.3536303,0.03841667,0.01474016,0.00201518],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8896834,0.002006538,0.09898572,0.004634294,0.00007441409,0.0003135085,8.732116e-7,0.00005314158,0.004248175],"genre_scores_gemma":[0.5612091,0.0004878164,0.4377607,0.0004412689,0.00001981262,0.000009229567,0.000002922998,0.000006998528,0.00006212033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8819858,"threshold_uncertainty_score":0.4599748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0416666573999727,"score_gpt":0.2793254558020496,"score_spread":0.2376587984020769,"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."}}