{"id":"W4393977829","doi":"10.11591/eei.v13i3.6049","title":"Enhancing speech emotion recognition with deep learning using multi-feature stacking and data augmentation","year":2024,"lang":"en","type":"article","venue":"Bulletin of Electrical Engineering and Informatics","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Binus University","keywords":"Computer science; Convolutional neural network; Transformer; Emotion recognition; Speech recognition; Artificial intelligence; Deep learning; Pattern recognition (psychology); Machine learning; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0002755863,0.0001098459,0.0001240306,0.0001742328,0.00005528948,0.00006534798,0.00004109396,0.00009849919,0.00005584918],"category_scores_gemma":[0.00009506895,0.00009885451,0.00001360484,0.0001744564,0.00001624019,0.0001266571,0.00002821238,0.0002928135,0.00001087376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002341367,"about_ca_system_score_gemma":0.000009356933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002033528,"about_ca_topic_score_gemma":0.000001455788,"domain_scores_codex":[0.9993355,0.00002352739,0.0002488056,0.000127183,0.0001094678,0.0001555427],"domain_scores_gemma":[0.999643,0.0001020277,0.00007222245,0.00008579655,0.00004801359,0.00004896157],"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":[0.0001054673,0.00009995924,0.0002649203,0.001779053,0.0002575604,0.00001915626,0.007724742,0.002905145,0.006223635,0.0004145763,0.0004747167,0.9797311],"study_design_scores_gemma":[0.000918324,0.000342222,0.00101865,0.0007941594,0.0001345685,0.000343991,0.001358746,0.9854234,0.001753528,0.00001334902,0.007617988,0.0002810766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5348079,0.001186925,0.4627179,0.00009024157,0.0002038456,0.0002175395,0.00001031477,0.0001783591,0.0005869527],"genre_scores_gemma":[0.8742941,0.0003886578,0.1245897,0.00006717522,0.0001119917,0.000005829359,0.0002886522,0.0000350245,0.0002188388],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9825183,"threshold_uncertainty_score":0.403117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02678107744333029,"score_gpt":0.283709290229016,"score_spread":0.2569282127856857,"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."}}