{"id":"W1677248707","doi":"10.1109/icassp.2001.940836","title":"Towards non-stationary model-based noise adaptation for large vocabulary speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Speech recognition; Computer science; Vocabulary; Noise (video); Adaptation (eye); Hidden Markov model; Artificial intelligence; Natural language processing; Linguistics; Psychology","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":[0.0002092095,0.0001218785,0.0001052288,0.0001242454,0.0001825822,0.0001305035,0.0002653868,0.00006378048,0.00008072413],"category_scores_gemma":[0.00004449857,0.0001182753,0.00006895446,0.0002700983,0.00001024696,0.0009384594,0.00003251263,0.00006514513,0.0001053408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000397763,"about_ca_system_score_gemma":0.0000851172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004671417,"about_ca_topic_score_gemma":0.00000649124,"domain_scores_codex":[0.998939,0.00001535595,0.0001985086,0.0003326987,0.0002429744,0.0002714678],"domain_scores_gemma":[0.9993598,0.00004875526,0.00007797739,0.0002098244,0.0002249383,0.00007865924],"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":[0.00001401455,0.0001881715,0.000023087,0.00005227576,0.000007454876,0.000007412004,0.0004140984,0.004228485,0.002385465,0.0003600043,0.006129246,0.9861903],"study_design_scores_gemma":[0.0006900966,0.00006452819,0.00005016623,0.00002195231,0.000005811185,0.000003906917,0.00002827171,0.8990176,0.09167428,0.0079087,0.0003677179,0.0001669497],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007147821,0.00006621528,0.9857412,0.001567396,0.0001337128,0.0002608727,0.00001677972,0.0002064234,0.004859565],"genre_scores_gemma":[0.3316167,0.000006346358,0.6660634,0.001643197,0.00005885947,0.00004698299,0.00005203469,0.000009787551,0.0005027215],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9860233,"threshold_uncertainty_score":0.4823129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04768072532420265,"score_gpt":0.2590581993003347,"score_spread":0.2113774739761321,"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."}}