{"id":"W4402672168","doi":"10.11591/eei.v13i6.6044","title":"Speech emotion recognition with optimized multi-feature stack using deep convolutional neural networks","year":2024,"lang":"en","type":"article","venue":"Bulletin of Electrical Engineering and Informatics","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mel-frequency cepstrum; Spectrogram; Computer science; Convolutional neural network; Speech recognition; Classifier (UML); Artificial intelligence; Emotion recognition; Artificial neural network; Feature extraction; Feature (linguistics); Deep learning; Pattern recognition (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003135982,0.00131597,0.0005844644,0.0004231419,0.0002329283,0.0005623702,0.0008226266,0.0006006477,0.001669633],"category_scores_gemma":[0.0005757051,0.0002961999,0.0007747507,0.0002419727,0.0001399499,0.000739283,0.0005645625,0.0009292752,0.0009068655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007157499,"about_ca_system_score_gemma":0.0005242522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007471138,"about_ca_topic_score_gemma":0.01255003,"domain_scores_codex":[0.9998075,0.00001948177,0.00001203034,0.00006842201,0.00004192469,0.0000505328],"domain_scores_gemma":[0.9998479,0.00002895185,0.00001289354,0.00001406497,0.00008418341,0.0000120678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008407617,0.0006153761,0.005487697,0.0001520281,0.0003206425,0.0002662964,0.0001076521,0.1886945,0.07736336,0.00101724,0.01083855,0.714296],"study_design_scores_gemma":[0.00001302981,0.0001153273,0.001334052,0.000008985277,0.00004556138,0.0000388059,0.00002606033,0.9862964,0.01084389,0.0004587677,0.0008084031,0.00001064276],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4278655,0.003504708,0.5502147,0.0009861654,0.0006886303,0.000209604,0.001453017,0.007891433,0.007186291],"genre_scores_gemma":[0.9037951,0.0005623212,0.08409525,0.0002964399,0.00007921217,0.0001446455,0.002457478,0.0001038766,0.008465845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007471138,"threshold_uncertainty_score":0.01485533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01686054800564301,"score_gpt":0.2438034504371425,"score_spread":0.2269429024314995,"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."}}