{"id":"W1525833316","doi":"10.1109/isspit.2003.1341231","title":"On the use of dynamic spectral parameters in speech recognition","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Speech recognition; Computer science; Mel-frequency cepstrum; Cepstrum; Feature extraction; Set (abstract data type); Feature (linguistics); Dynamics (music); Speech processing; Pattern recognition (psychology); Artificial intelligence; Task (project management); Linear predictive coding; Feature vector; Acoustics; 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":[0.0001670749,0.00007211458,0.0000880958,0.0001299222,0.00002359706,0.00005864714,0.0002429019,0.00003374512,0.0001049473],"category_scores_gemma":[0.000162457,0.0000482057,0.00005682433,0.0003182908,0.00003390467,0.0002557826,0.00002569007,0.0000878211,0.0001865688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005492582,"about_ca_system_score_gemma":0.00002374133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001642516,"about_ca_topic_score_gemma":0.0002512698,"domain_scores_codex":[0.999304,0.00005500533,0.0001646781,0.0001747315,0.000163803,0.0001377616],"domain_scores_gemma":[0.9992937,0.0003477965,0.00004448963,0.0002600847,0.00002647795,0.00002744755],"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":[0.00002809048,0.0003713782,0.00008705245,0.000006595584,0.00001946902,0.00005181528,0.0003094067,0.0002355955,0.001824979,0.03639266,0.0003283501,0.9603446],"study_design_scores_gemma":[0.001409407,0.0004120186,0.01418459,0.0002415437,0.00001135276,0.0000854425,0.0001755826,0.04046035,0.5076726,0.4346308,0.0001822029,0.000534091],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9548802,0.000001699559,0.0395537,0.002432487,0.00009152591,0.0001467097,0.000002423583,0.00005183413,0.002839458],"genre_scores_gemma":[0.7847764,0.00001131194,0.2141125,0.001011151,0.000003071162,0.000006835012,0.000001354611,0.000003864071,0.00007344368],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9598105,"threshold_uncertainty_score":0.2398027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07952758791153693,"score_gpt":0.2500826680213651,"score_spread":0.1705550801098282,"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."}}