{"id":"W2084869268","doi":"10.1109/icassp.2013.6639037","title":"Noise aware manifold learning for robust speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Nonlinear dimensionality reduction; Discriminative model; Pattern recognition (psychology); Dimensionality reduction; Speech recognition; Computer science; Manifold alignment; Noise (video); Artificial intelligence; Feature vector; Manifold (fluid mechanics); Locality; Feature (linguistics); Linear discriminant analysis; Curse of dimensionality; Image (mathematics); Engineering","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":[0.000122723,0.00008924868,0.00008419916,0.00006065468,0.0001697569,0.0003630674,0.0002907621,0.00004578353,0.0002403051],"category_scores_gemma":[0.00005158737,0.00007745878,0.0000457086,0.0001624619,0.000006960903,0.000997398,0.00007394733,0.00008820454,0.0006646395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001863628,"about_ca_system_score_gemma":0.00002630664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000347873,"about_ca_topic_score_gemma":0.000006622925,"domain_scores_codex":[0.9992254,0.00001329203,0.0001262298,0.0002650302,0.000118939,0.0002511522],"domain_scores_gemma":[0.999512,0.00005438801,0.000055262,0.0001487771,0.0001585035,0.00007108862],"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":[0.000001440827,0.00002136519,0.0004178715,0.00002794505,0.000005005074,0.000002632765,0.00006068673,0.00007597535,0.004397563,0.00009041905,0.006692867,0.9882062],"study_design_scores_gemma":[0.001004438,0.0002511282,0.002225062,0.0001205094,0.00001229317,0.00007517442,0.000309689,0.2557468,0.7146807,0.01766145,0.007204857,0.0007078715],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0291787,0.00002688948,0.9596955,0.00125479,0.0001602562,0.0002309548,3.347818e-7,0.0003521194,0.00910048],"genre_scores_gemma":[0.2316482,0.000007273165,0.761636,0.0007964849,0.000170208,0.00006324293,0.000009749015,0.00001339981,0.005655398],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9874983,"threshold_uncertainty_score":0.8542818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03264642813348398,"score_gpt":0.2338401597893631,"score_spread":0.2011937316558791,"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."}}