{"id":"W4399434529","doi":"10.1038/s41598-024-63776-4","title":"An enhanced speech emotion recognition using vision transformer","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Computer science; Emotion recognition; Leverage (statistics); Speech recognition; Transformer; Spectrogram; Feature extraction; Artificial intelligence; Benchmark (surveying); Machine learning; Psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001360119,0.0001393954,0.0001229858,0.0003980919,0.0002594847,0.0004348916,0.00005488937,0.0001497986,0.004942765],"category_scores_gemma":[0.00001941521,0.0001297444,0.0001184774,0.0006160208,0.000109739,0.0006393751,0.000005140189,0.0001609333,0.0009066819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006358107,"about_ca_system_score_gemma":0.00006619019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003511155,"about_ca_topic_score_gemma":0.00002400279,"domain_scores_codex":[0.9979065,0.0001142424,0.000456088,0.0008886294,0.0003504317,0.0002840751],"domain_scores_gemma":[0.9991689,0.0000156404,0.00009743258,0.0004310474,0.0001632082,0.0001237313],"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":[0.00001298191,0.0001681056,0.00002062872,0.00003627959,0.00001847739,0.0002876647,0.001807717,0.000006819955,0.4407411,0.00004318956,0.003180594,0.5536764],"study_design_scores_gemma":[0.0009216198,0.0007457415,0.00364474,0.001412724,0.000366337,0.007204162,0.003750357,0.006695039,0.7988636,0.09919041,0.07567478,0.001530415],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9160476,0.0001194861,0.02381855,0.00007454467,0.03385749,0.0003533828,0.000006640992,0.0003490034,0.02537328],"genre_scores_gemma":[0.9944142,0.000005142921,0.001223391,0.00004000508,0.0002872267,0.00001468521,0.0004592016,0.00002929191,0.003526898],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.552146,"threshold_uncertainty_score":0.9998713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04669083380122481,"score_gpt":0.3621511617437113,"score_spread":0.3154603279424865,"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."}}