{"id":"W2944458161","doi":"10.3390/e21050479","title":"3D CNN-Based Speech Emotion Recognition Using K-Means Clustering and Spectrograms","year":2019,"lang":"en","type":"article","venue":"Entropy","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":155,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Spectrogram; Computer science; Speech recognition; Cluster analysis; Artificial intelligence; Preprocessor; Mel-frequency cepstrum; Pattern recognition (psychology); Convolutional neural network; SIGNAL (programming language); Feature extraction","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001609402,0.0001303844,0.0001373955,0.0001263093,0.00006851584,0.00004607817,0.00004317132,0.0001138622,0.004876019],"category_scores_gemma":[0.00001244379,0.0001352599,0.00005849007,0.0001175798,0.0000297701,0.0000951762,0.00001497057,0.0001520369,0.001379338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000569988,"about_ca_system_score_gemma":0.0000110753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009475098,"about_ca_topic_score_gemma":0.00001955756,"domain_scores_codex":[0.9990193,0.0001119304,0.0001856464,0.0003019792,0.0001233814,0.0002578177],"domain_scores_gemma":[0.9995915,0.00003283151,0.00009277116,0.0001641122,0.00004672989,0.00007210387],"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":[0.0007373079,0.001005039,0.03848471,0.000248249,0.0002306908,0.00009418197,0.002425878,0.0003394987,0.09262419,0.001243312,0.001106185,0.8614607],"study_design_scores_gemma":[0.05499985,0.006388615,0.2856389,0.002399354,0.001225828,0.001926686,0.01084683,0.5254868,0.04655036,0.0135272,0.04512476,0.005884786],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9545357,0.00004189635,0.03260931,0.0001578797,0.001378154,0.0003682061,0.000009383953,0.0001333066,0.01076622],"genre_scores_gemma":[0.9875587,0.00001006814,0.0111247,0.0003599892,0.0003050378,0.000007275393,0.0001311378,0.00002986073,0.0004732585],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.855576,"threshold_uncertainty_score":0.9993982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03641278431305226,"score_gpt":0.2962719814800268,"score_spread":0.2598591971669745,"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."}}