{"id":"W4399489418","doi":"10.3390/app14125050","title":"Combining Transformer, Convolutional Neural Network, and Long Short-Term Memory Architectures: A Novel Ensemble Learning Technique That Leverages Multi-Acoustic Features for Speech Emotion Recognition in Distance Education Classrooms","year":2024,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Spectrogram; Deep learning; Convolutional neural network; Artificial intelligence; Transformer; Mel-frequency cepstrum; Feature extraction; Multimedia; 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":[0.0007289997,0.0001863899,0.0001717811,0.0002580545,0.0003418548,0.0001426974,0.0001025804,0.0001531315,0.00003706883],"category_scores_gemma":[0.0000231536,0.0001731453,0.00005614897,0.0003617985,0.0002578877,0.0001475023,0.00001218989,0.0003867902,0.000004784343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005416676,"about_ca_system_score_gemma":0.00008655162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002931493,"about_ca_topic_score_gemma":0.0004666452,"domain_scores_codex":[0.9985679,0.00006890985,0.0002435881,0.0005624403,0.0001938078,0.0003633036],"domain_scores_gemma":[0.9994854,0.0002857805,0.00006212229,0.0000690809,0.00003620299,0.00006144807],"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":[0.0002000936,0.0003919826,0.004005637,0.0003714056,0.00004541725,0.000007549615,0.005882046,0.004248184,0.09355596,0.004043584,0.0002781506,0.88697],"study_design_scores_gemma":[0.01087471,0.002824129,0.6660334,0.006772656,0.0006699394,0.003213836,0.05640176,0.1297502,0.05634324,0.05957506,0.002086887,0.005454135],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5872576,0.001005659,0.4047907,0.0002109268,0.001112996,0.001367386,0.00001951744,0.0001785189,0.004056724],"genre_scores_gemma":[0.9936565,0.00004473404,0.004879871,0.0001400585,0.0001839613,0.0005327972,0.0001404689,0.00001990723,0.0004017261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8815159,"threshold_uncertainty_score":0.7060661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05644224838648238,"score_gpt":0.3282914500156595,"score_spread":0.2718492016291771,"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."}}