{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008292379,0.001490232,0.0006300459,0.0004409027,0.0002269869,0.0006607579,0.0006907936,0.000479758,0.001700463],"category_scores_gemma":[0.002464811,0.0001949229,0.0008816792,0.0003540996,0.0002635115,0.001397857,0.001002307,0.001214392,0.001074385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003565366,"about_ca_system_score_gemma":0.0003581733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002249547,"about_ca_topic_score_gemma":0.003972791,"domain_scores_codex":[0.9996226,0.00008185365,0.00002557151,0.0001156025,0.00008718944,0.00006703739],"domain_scores_gemma":[0.9994681,0.000212804,0.00003625976,0.0001026204,0.0001493065,0.00003097105],"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":[0.0009467811,0.0008237474,0.009617045,0.0002539487,0.0002390982,0.0002006893,0.0001815556,0.06976904,0.07183339,0.0008659997,0.008157896,0.8371108],"study_design_scores_gemma":[0.00004523243,0.0005718817,0.007397747,0.00003749871,0.0001348981,0.0001472515,0.0002039161,0.9365892,0.04860917,0.001913117,0.004302225,0.00004779109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6187507,0.004342056,0.3563073,0.001204382,0.001268937,0.0002375508,0.00182437,0.007811307,0.008253478],"genre_scores_gemma":[0.895512,0.0007070192,0.09632863,0.0003612291,0.0001018708,0.0001423167,0.003188053,0.0001169182,0.003542073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002249547,"threshold_uncertainty_score":0.005688608,"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."}}