{"id":"W2154037907","doi":"10.1109/icassp.1995.479399","title":"Analysis of acoustic-phonetic variations in fluent speech using TIMIT","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"TIMIT; Speech recognition; Computer science; Mel-frequency cepstrum; Context (archaeology); Phonetics; Variance (accounting); Cepstrum; Artificial intelligence; Hidden Markov model; Feature extraction; Linguistics; Biology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001611517,0.0000633582,0.000172944,0.0006231443,0.00002824979,0.00003877801,0.0002470982,0.00003560166,0.003063952],"category_scores_gemma":[0.00007015081,0.00005932149,0.00008743084,0.002085219,0.00001535949,0.0001307292,0.00005091019,0.00004053219,0.00005909668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003439339,"about_ca_system_score_gemma":0.000009906495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001702461,"about_ca_topic_score_gemma":0.0001834485,"domain_scores_codex":[0.9992048,0.00004847179,0.0002429916,0.0001845649,0.0001890701,0.0001301557],"domain_scores_gemma":[0.9994156,0.0001347622,0.00005773958,0.0002904643,0.00005943262,0.00004203937],"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":[0.000006227351,0.00222434,0.03874136,0.00004132256,0.001572266,0.0001249402,0.003832758,0.05646361,0.04608613,0.01160566,0.001135797,0.8381656],"study_design_scores_gemma":[0.00008854384,0.000007078489,0.01221188,0.000005062952,0.0001057908,0.00000288921,0.00002237791,0.9845812,0.002730684,0.0001428905,0.00002852237,0.00007303843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1083893,0.00002046579,0.8799917,0.0002094133,0.00007406598,0.00006786353,0.000002826938,0.00004575006,0.01119855],"genre_scores_gemma":[0.7909178,0.000009613491,0.2086556,0.0001316559,0.000006676777,0.000001821021,6.373979e-7,0.000002380272,0.0002738814],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9281176,"threshold_uncertainty_score":0.9978474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04996774319873785,"score_gpt":0.262514416545676,"score_spread":0.2125466733469382,"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."}}