{"id":"W3154935508","doi":"10.1007/s12559-021-09865-2","title":"When Old Meets New: Emotion Recognition from Speech Signals","year":2021,"lang":"en","type":"article","venue":"Cognitive Computation","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Politecnico di Milano","keywords":"Computer science; Speech recognition; Artificial intelligence; Convolutional neural network; Feature (linguistics); Spectrogram; Mel-frequency cepstrum; Support vector machine; Artificial neural network; Pattern recognition (psychology); Feature extraction; Emotion recognition","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002142654,0.0002455439,0.0002646577,0.0001897758,0.0001525849,0.0001077947,0.00005442818,0.0002467465,0.01028758],"category_scores_gemma":[0.000232429,0.0002898703,0.0001473889,0.0003203342,0.00005122032,0.0002985417,0.00004248357,0.0002545673,0.00557517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006725926,"about_ca_system_score_gemma":0.00009426814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002382746,"about_ca_topic_score_gemma":0.00008052099,"domain_scores_codex":[0.9976943,0.000550399,0.0004487015,0.0006970231,0.000308773,0.0003007711],"domain_scores_gemma":[0.9980393,0.0004712705,0.0002462894,0.00009115091,0.0009652905,0.0001867145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001247037,0.0003468238,0.0004162219,0.00001154151,0.000215041,0.0001110416,0.002199609,0.000004979722,0.003770768,0.00007461579,0.01162866,0.981096],"study_design_scores_gemma":[0.02822714,0.0013827,0.3351769,0.002703832,0.002264533,0.0006435937,0.02346154,0.007581179,0.2050373,0.3809704,0.008855225,0.003695664],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5732041,0.0004521838,0.3845969,0.001270216,0.002254382,0.0004723074,0.000217971,0.0003006877,0.03723132],"genre_scores_gemma":[0.9807154,0.00004248162,0.004051172,0.002341145,0.0009458326,0.00003364717,0.007463401,0.00005021962,0.004356704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9774004,"threshold_uncertainty_score":0.9999554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07578580399662282,"score_gpt":0.3358346409619837,"score_spread":0.2600488369653609,"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."}}