{"id":"W2150638823","doi":"10.1109/icassp.2002.5743654","title":"Accounting for uncertainity in observations: A new paradigm for Robust Automatic Speech Recognition","year":2002,"lang":"en","type":"article","venue":"IEEE International Conference on Acoustics Speech and Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Noise (video); Variance (accounting); Speech recognition; Adaptation (eye); Artificial intelligence; Machine learning; Pattern recognition (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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004240245,0.0002551955,0.0002621326,0.0002965746,0.0002848641,0.001040251,0.0005842054,0.0001306709,0.00005206152],"category_scores_gemma":[0.0003424913,0.0002580062,0.00006419599,0.0003214562,0.00005096325,0.00127716,0.00004558329,0.0002332274,0.000008833327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000123241,"about_ca_system_score_gemma":0.0002469767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002058936,"about_ca_topic_score_gemma":0.00002206187,"domain_scores_codex":[0.9980943,0.00002264425,0.0005127017,0.0005610638,0.0003908765,0.000418383],"domain_scores_gemma":[0.9985865,0.0003451655,0.0003113722,0.0001413477,0.0004855923,0.00012997],"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":[0.00003587143,0.0001283022,0.0001927055,0.0001694404,0.00001714494,0.00001090337,0.0003320513,0.0007955052,0.009574424,0.0007074235,0.0007005707,0.9873357],"study_design_scores_gemma":[0.001066948,0.0001377283,0.0001625408,0.0006000191,0.00001547431,0.00003055266,0.0001033589,0.9183719,0.007562377,0.0715274,0.000104696,0.0003169996],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04071907,0.0001161975,0.9546553,0.002753798,0.0003327875,0.0005142911,0.00002853921,0.0001429911,0.00073704],"genre_scores_gemma":[0.5200164,0.00004727544,0.4785165,0.0007318073,0.0003373115,0.00007046608,0.00002506778,0.0000182181,0.0002369547],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9870186,"threshold_uncertainty_score":0.9999968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1685601413058974,"score_gpt":0.3141590910809067,"score_spread":0.1455989497750093,"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."}}