{"id":"W2098507061","doi":"10.1109/icme.2005.1521436","title":"Segment-Based Approach to the Recognition of Emotions in Speech","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Utterance; Computer science; Speech recognition; Support vector machine; Context (archaeology); Representation (politics); Pattern recognition (psychology); Artificial intelligence; Scheme (mathematics); Object (grammar); Natural language processing; Mathematics","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":[0.0002223493,0.00004460235,0.00005359131,0.00008426206,0.00003902916,0.00004251913,0.0003024773,0.00001751631,0.00001595837],"category_scores_gemma":[0.00002022116,0.00003043529,0.0000206562,0.0004812046,0.000009826508,0.0001709145,0.00004067991,0.00004889315,0.00006247569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002071519,"about_ca_system_score_gemma":0.00003672564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001352844,"about_ca_topic_score_gemma":0.00004484248,"domain_scores_codex":[0.9994898,0.00002194945,0.0001062188,0.0001393121,0.0001264168,0.000116319],"domain_scores_gemma":[0.999696,0.00002178707,0.0000279484,0.0001891411,0.00003625358,0.00002884046],"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":[0.000002384174,0.0001927504,0.000200633,0.000009685152,0.000002009149,4.421786e-7,0.00031425,0.002642303,0.004036163,0.0003085522,0.001650047,0.9906408],"study_design_scores_gemma":[0.0006450564,0.00006764659,0.004256193,0.00006266993,0.000003921332,0.00001080316,0.0001934567,0.1110867,0.8782286,0.001057777,0.004174392,0.0002127414],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05973139,0.00001188917,0.9093105,0.007115196,0.00003233788,0.0001195916,7.846634e-7,0.00004369632,0.02363463],"genre_scores_gemma":[0.5186675,5.677296e-7,0.4801174,0.001023298,0.0000267066,0.000006441504,0.000001355765,0.000001657958,0.0001550935],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.990428,"threshold_uncertainty_score":0.1241115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03222835632734909,"score_gpt":0.2500438902212239,"score_spread":0.2178155338938748,"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."}}