{"id":"W2124479510","doi":"10.1109/lsp.2006.874462","title":"Linear Dynamic Models With Mixture of Experts Architecture for Recognition of Speech Under Additive Noise Conditions","year":2006,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Speech recognition; Feature (linguistics); Noise (video); Pattern recognition (psychology); Dynamic Bayesian network; Speech processing; Kalman filter; Mixture model; Linear predictive coding; Speech enhancement; Bayesian probability; Artificial intelligence; Noise reduction","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":[0.0001057266,0.0002127268,0.0002666937,0.0002048785,0.0001577567,0.00006750946,0.0003275512,0.00008418402,0.000005110114],"category_scores_gemma":[0.00000618734,0.0001787943,0.00009011145,0.000411747,0.0001946038,0.0006058645,0.00002013075,0.0001425921,8.328211e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003889045,"about_ca_system_score_gemma":0.0001470294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001652825,"about_ca_topic_score_gemma":0.00001580191,"domain_scores_codex":[0.9986116,0.00003188486,0.0003221256,0.0003991136,0.0003339038,0.0003013827],"domain_scores_gemma":[0.9989841,0.0001106529,0.0003664033,0.0001710634,0.0003166684,0.00005112396],"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":[0.00009451775,0.0001154852,0.000008306071,0.0002956439,0.00003445429,0.0000134378,0.0005856698,0.06401968,0.8375289,0.00003585422,0.0009403071,0.09632777],"study_design_scores_gemma":[0.0008839794,0.0001676886,0.00005332329,0.0007420548,0.00004320939,0.00005959435,0.00008318858,0.07433293,0.9006733,0.0225757,0.00003769801,0.0003473762],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1633233,0.00009972476,0.834323,0.001728763,0.00004423783,0.0002253979,0.00007744059,0.00007265482,0.0001055473],"genre_scores_gemma":[0.7905832,0.000001088151,0.2082388,0.0009216652,0.000117083,0.00003335914,0.00006251723,0.00002172747,0.00002060179],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6272599,"threshold_uncertainty_score":0.7291021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01417999286233152,"score_gpt":0.2401982753902103,"score_spread":0.2260182825278788,"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."}}