{"id":"W4322495088","doi":"10.4028/p-0892re","title":"Deep Learning-Based Speech Emotion Recognition","year":2023,"lang":"en","type":"article","venue":"Advances in science and technology","topic":"Music and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Computer science; Emotion recognition; Mel-frequency cepstrum; Artificial neural network; Classifier (UML); Emotion classification; Tone (literature); Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0006189144,0.0000634882,0.00008085502,0.000821891,0.0002441348,0.00006951352,0.0004639029,0.00005571682,0.000003641627],"category_scores_gemma":[0.000376899,0.00005887635,0.000006600681,0.005593019,0.0005386555,0.001168751,0.0001623725,0.0001528625,0.00004419092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002866978,"about_ca_system_score_gemma":0.00006955094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002182219,"about_ca_topic_score_gemma":0.00001598422,"domain_scores_codex":[0.9989898,0.00001171051,0.0001118635,0.0003849762,0.0002175267,0.0002840802],"domain_scores_gemma":[0.9996023,0.00003998145,0.00005717092,0.0001604982,0.0001129588,0.00002716001],"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":[5.464146e-7,0.000006315112,0.002288185,0.000007510551,1.488232e-7,0.00001143803,0.00006114331,0.0002386124,0.0009486697,0.002122768,0.000007300711,0.9943073],"study_design_scores_gemma":[0.0005470593,0.0002373399,0.003564449,0.0001369739,0.000002049073,0.00005383614,0.0005269713,0.6528342,0.04329283,0.2775591,0.02087668,0.0003684986],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4842401,0.001195672,0.4986287,0.009895095,0.0005775389,0.0001856736,2.723081e-7,0.00147693,0.003800026],"genre_scores_gemma":[0.9835154,0.0003338862,0.01588075,0.000216915,0.00001235337,0.00001174883,9.0394e-7,0.000002625922,0.00002535656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9939389,"threshold_uncertainty_score":0.268726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01334714685813124,"score_gpt":0.2761912751693509,"score_spread":0.2628441283112197,"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."}}