{"id":"W2155549992","doi":"10.1109/pacrim.1991.160701","title":"Speech enhancement based on Kalman filtering and EM algorithm","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Kalman filter; Computer science; Fast Kalman filter; Speech enhancement; Algorithm; Noise (video); Speech recognition; Extended Kalman filter; SIGNAL (programming language); Signal-to-noise ratio (imaging); Invariant extended Kalman filter; Artificial intelligence; Noise reduction; Telecommunications","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":[0.00008449842,0.00008973669,0.00007567577,0.00005962574,0.00009406057,0.0001965624,0.0002229694,0.00002145688,0.0002825747],"category_scores_gemma":[0.000006918701,0.00007559554,0.00001774125,0.0001363393,0.0000111713,0.0002040302,0.00007640201,0.00005664338,0.00009453851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001664312,"about_ca_system_score_gemma":0.000005492896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002658197,"about_ca_topic_score_gemma":0.000001416879,"domain_scores_codex":[0.9992489,0.000009672601,0.00009508689,0.0002661653,0.0001832372,0.0001969295],"domain_scores_gemma":[0.9996343,0.00002256347,0.00002647231,0.0002284324,0.00001734678,0.00007091515],"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":[4.008405e-7,0.00003404505,0.00002438852,0.000005953566,0.000001688815,0.00001776826,0.00008843999,0.000008320862,0.003063009,0.00004558939,0.0007077375,0.9960027],"study_design_scores_gemma":[0.0002726427,0.0001278946,0.0001794026,0.00003605417,0.000001287628,0.00001038968,0.00001297684,0.4685669,0.5274156,0.0002046282,0.003015415,0.0001568724],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01266364,0.00008651879,0.9660482,0.0008277927,0.0001217922,0.00005811821,2.847984e-7,0.0001310527,0.0200626],"genre_scores_gemma":[0.2179575,0.00001273655,0.7773779,0.002245481,0.00006119286,0.0000051554,3.614077e-7,0.000005777971,0.002333937],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9958458,"threshold_uncertainty_score":0.3093995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01789767810244088,"score_gpt":0.2260928702942446,"score_spread":0.2081951921918037,"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."}}