{"id":"W2154792319","doi":"10.1109/tasl.2004.924593","title":"Feature Enhancement for Noisy Speech Recognition With a Time-Variant Linear Predictive HMM Structure","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hidden Markov model; Speech recognition; Computer science; Feature (linguistics); Noise (video); Pattern recognition (psychology); Parametric statistics; Artificial intelligence; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001753902,0.0003570376,0.0003209911,0.0002197175,0.0008244618,0.0002023504,0.0002869685,0.0001767204,0.00004448628],"category_scores_gemma":[0.00001549623,0.0002875531,0.00007880585,0.0005597481,0.0001109995,0.0009124044,0.000005141826,0.0004233857,0.00001578968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007917287,"about_ca_system_score_gemma":0.000239564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001025169,"about_ca_topic_score_gemma":0.00002929921,"domain_scores_codex":[0.9981241,0.00004334135,0.0002200137,0.0007329741,0.0003891152,0.0004905072],"domain_scores_gemma":[0.9990256,0.00007332009,0.000181893,0.0002936555,0.000239782,0.0001857603],"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":[0.0003238136,0.0002484745,0.000007990811,0.0001999908,0.00007677148,0.000198422,0.003324739,0.0001163236,0.05804158,5.808537e-7,0.0002816133,0.9371797],"study_design_scores_gemma":[0.00196254,0.0006464737,0.00002567428,0.0003941971,0.00007352816,0.001463951,0.0002508711,0.01825719,0.9760625,0.0000989188,0.0002777829,0.0004863311],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1045841,0.000646296,0.8929337,0.0006384772,0.0001367254,0.0005110358,0.0000709559,0.0002797934,0.0001988577],"genre_scores_gemma":[0.5261902,0.0000648118,0.4714507,0.0005182019,0.0002076031,0.00006888944,0.0000243822,0.00004145319,0.001433783],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9366934,"threshold_uncertainty_score":0.9999577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0102738947735903,"score_gpt":0.233010294564496,"score_spread":0.2227363997909057,"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."}}