{"id":"W2011688148","doi":"10.1109/socialcom-passat.2012.83","title":"Dimensionality Reduction for Emotional Speech Recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dimensionality reduction; Principal component analysis; Pattern recognition (psychology); Computer science; Reduction (mathematics); Artificial intelligence; Curse of dimensionality; Projection (relational algebra); Filter (signal processing); Speech recognition; Feature extraction; Feature selection; Mathematics; Algorithm; Computer vision","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":[0.0003395109,0.00006791938,0.00006172989,0.00005265014,0.0001435671,0.00003602788,0.0001026949,0.00005391892,0.0002162554],"category_scores_gemma":[0.00003718251,0.00005816324,0.00005691229,0.0001119652,0.00001285635,0.001190489,0.00004370843,0.00004535314,0.0003849454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002361852,"about_ca_system_score_gemma":0.000016221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007462503,"about_ca_topic_score_gemma":4.015588e-7,"domain_scores_codex":[0.9992973,0.00003334146,0.0001320981,0.0001712873,0.0001672404,0.0001987762],"domain_scores_gemma":[0.999541,0.0000504115,0.00004433301,0.0001460197,0.0001321593,0.00008603591],"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":[0.00003540168,0.0004999004,0.0003508665,0.00003364092,0.00002125972,3.769313e-7,0.0002077895,0.000005625705,0.04567667,0.03251703,0.1173751,0.8032764],"study_design_scores_gemma":[0.001557771,0.0001950621,0.01401119,0.0001108968,0.00002643772,0.0002685689,0.0002206526,0.01051326,0.713937,0.207625,0.0507439,0.0007902891],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2327023,0.00004833414,0.7540162,0.00275216,0.002293167,0.0003753228,0.00001430588,0.0003039487,0.007494298],"genre_scores_gemma":[0.5801112,0.000008515301,0.4176389,0.0004094336,0.0005432104,0.00006126722,0.0001271447,0.000006653216,0.001093649],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8024861,"threshold_uncertainty_score":0.4947822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05657887062820809,"score_gpt":0.2846824535745897,"score_spread":0.2281035829463816,"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."}}