{"id":"W4399748891","doi":"10.20944/preprints202404.1456.v1","title":"Combining Transformer, CNN, and LSTM Architectures: A Novel Ensemble Learning Technique That Leverages Multi-acoustic Features for Speech Emotion Recognition in Distance Education Classrooms","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Spectrogram; Transformer; Mel-frequency cepstrum; Deep learning; Artificial intelligence; Convolutional neural network; Feature extraction; 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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0009847713,0.0005231347,0.0005181396,0.0006510548,0.0001692146,0.00007763469,0.0002151501,0.000858509,0.0002069859],"category_scores_gemma":[0.0002758937,0.0005688463,0.0002260116,0.0002127207,0.0001040941,0.00007532889,0.000184065,0.002359406,0.0001125083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002344145,"about_ca_system_score_gemma":0.0001779403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003134781,"about_ca_topic_score_gemma":0.0005876689,"domain_scores_codex":[0.9969972,0.0002807348,0.0006097739,0.001405415,0.0002336862,0.0004731979],"domain_scores_gemma":[0.9987175,0.0002279849,0.0003395748,0.0004294756,0.0001622085,0.0001232342],"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":[0.001365021,0.003507358,0.0525278,0.008293287,0.0006592759,0.00003619531,0.04133851,0.001753889,0.2941483,0.0009203567,0.0002149935,0.595235],"study_design_scores_gemma":[0.009395536,0.0006231752,0.6533202,0.01971149,0.001221913,0.0009741674,0.01650176,0.003105504,0.1901036,0.09371085,0.006753562,0.004578271],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.813107,0.0007362154,0.1715261,0.0005464345,0.002355633,0.004065116,0.0001323858,0.000457525,0.00707358],"genre_scores_gemma":[0.9873948,0.0003105892,0.004152162,0.0001775073,0.000211668,0.002547372,0.0007917276,0.0001187051,0.0042955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6007924,"threshold_uncertainty_score":0.9999422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1372193832998145,"score_gpt":0.3841146379727956,"score_spread":0.2468952546729811,"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."}}