{"id":"W47819768","doi":"10.21437/interspeech.2008-201","title":"Long-term spectro-temporal information for improved automatic speech emotion classification","year":2008,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Filter bank; Computer science; Classifier (UML); Salient; Speech recognition; Pattern recognition (psychology); Discrete cosine transform; Artificial intelligence; Support vector machine; Feature selection; Term (time); Curse of dimensionality; Feature extraction; Dimensionality reduction; Filter (signal processing); 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":[0.0001852467,0.0001175806,0.0001202451,0.0001378335,0.0002351236,0.0002103142,0.0003593067,0.00006343886,0.00002116358],"category_scores_gemma":[0.0000470152,0.0001040077,0.00006145276,0.0002827326,0.00002680859,0.002815827,0.00004470993,0.00006541349,0.00009516771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008044992,"about_ca_system_score_gemma":0.0001150313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005694678,"about_ca_topic_score_gemma":0.000005214573,"domain_scores_codex":[0.9990662,0.00001393659,0.0003195181,0.0001907237,0.0001672564,0.0002423573],"domain_scores_gemma":[0.9992633,0.00002704982,0.0001941395,0.0003062362,0.0001413067,0.00006789628],"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":[0.00001172859,0.00009209682,0.007724589,0.0001362054,0.00001611418,0.000002928085,0.0007339254,0.000002964501,0.02063693,0.002389586,0.002202385,0.9660506],"study_design_scores_gemma":[0.001488165,0.000263898,0.2040345,0.00004719122,0.00001115933,0.0002317257,0.00005116057,0.5088617,0.2805281,0.003246343,0.0007573306,0.0004786318],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2195219,0.00000914026,0.7773721,0.0009830352,0.0001883356,0.0003210657,9.560232e-7,0.0003938765,0.001209534],"genre_scores_gemma":[0.6433976,0.000007353201,0.3557804,0.000345083,0.00008396719,0.00002372318,0.00004642619,0.000005367589,0.0003101065],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9655719,"threshold_uncertainty_score":0.4241312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02643282965209102,"score_gpt":0.2586512006591988,"score_spread":0.2322183710071077,"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."}}