{"id":"W217970951","doi":"","title":"Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hidden Markov model; Computer science; Artificial intelligence; Speech recognition; Context (archaeology); Deep belief network; Vocabulary; Deep 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":[],"consensus_categories":[],"category_scores_codex":[0.000763245,0.0001332696,0.0002556066,0.0004024435,0.0001186861,0.0004245667,0.0002246209,0.00008703562,0.000004729096],"category_scores_gemma":[0.0002113834,0.000123273,0.00004269633,0.0003022582,0.00003645549,0.003209876,0.00004246485,0.0001693522,0.00000484223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002272735,"about_ca_system_score_gemma":0.0000696218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001503054,"about_ca_topic_score_gemma":0.000627518,"domain_scores_codex":[0.9986246,0.00004144628,0.0006912945,0.0001680928,0.000268557,0.000206017],"domain_scores_gemma":[0.998879,0.0001659506,0.0004416089,0.0001582487,0.0002912193,0.00006403793],"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":[0.00001615478,0.00001307343,0.0004046288,0.0003089892,0.000005102698,6.750821e-7,0.00350159,0.00003468509,0.001725116,0.0003881677,0.00003337425,0.9935684],"study_design_scores_gemma":[0.00165567,0.0001393284,0.003347272,0.000954856,0.00002043242,0.0001572047,0.003941684,0.9532833,0.03164655,0.00103197,0.003318684,0.00050308],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9327809,0.0001477271,0.0603407,0.0002795796,0.0009138031,0.001014206,0.00003007015,0.0002641313,0.004228856],"genre_scores_gemma":[0.9893546,0.000006568281,0.01028796,0.00009001032,0.000059843,0.00008711599,0.00002071331,0.000007024084,0.000086209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9930654,"threshold_uncertainty_score":0.5026926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0420777987342523,"score_gpt":0.2835390570334626,"score_spread":0.2414612582992103,"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."}}