{"id":"W2034149345","doi":"10.1016/j.specom.2010.05.005","title":"Discrete cosine transform particle filter speech enhancement","year":2010,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University; University of Ottawa; Innovation, Science and Economic Development Canada","funders":"Siemens","keywords":"Discrete cosine transform; Speech enhancement; Speech recognition; Computer science; Autoregressive model; Algorithm; Noise reduction; Filter (signal processing); Intelligibility (philosophy); Mathematics; Artificial intelligence; Computer vision; 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":[0.0005414985,0.0001513212,0.0001428887,0.00005081008,0.0003037892,0.0002897193,0.001602942,0.0000753124,0.0001519547],"category_scores_gemma":[0.00004818651,0.0001385566,0.00006166143,0.0003621744,0.00009149293,0.0009160937,0.0002648979,0.0003788996,0.0002346789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003551885,"about_ca_system_score_gemma":0.00005754859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004193978,"about_ca_topic_score_gemma":0.0002107524,"domain_scores_codex":[0.9987013,0.00005392284,0.0002972286,0.0002859418,0.0003265737,0.0003350145],"domain_scores_gemma":[0.9978992,0.00006663898,0.000110034,0.001683191,0.0001274367,0.0001134773],"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":[0.00001061832,0.0001410342,0.0003427108,0.00001533716,0.0000133709,0.000004190969,0.0006856493,0.000002611256,0.3856892,0.00471236,0.0009425389,0.6074404],"study_design_scores_gemma":[0.0003517159,0.00004865702,0.0006540225,0.00003467068,0.000005942304,0.0000244418,0.00002565077,0.003286429,0.9698549,0.00826428,0.01725244,0.000196864],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6431033,0.0004617291,0.2918312,0.0274965,0.0004343307,0.0005731093,0.000004416174,0.0005190265,0.0355764],"genre_scores_gemma":[0.7569376,0.00007403601,0.2418653,0.0004161444,0.00004575151,0.00002626227,0.00001459403,0.00001031176,0.0006100424],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6072435,"threshold_uncertainty_score":0.5650173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01437912466771747,"score_gpt":0.2704167718987001,"score_spread":0.2560376472309826,"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."}}