{"id":"W2995902718","doi":"10.48550/arxiv.1912.10458","title":"Emotion Recognition from Speech","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Spectrogram; Speech recognition; Computer science; Mel-frequency cepstrum; Hidden Markov model; Convolutional neural network; Emotion recognition; Artificial intelligence; Task (project management); Feature extraction; Pattern recognition (psychology)","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":[0.0001772013,0.0003138299,0.0003268032,0.0002971682,0.00008095493,0.00004354073,0.0003289471,0.0008069651,0.008387203],"category_scores_gemma":[0.00002572841,0.0003947155,0.0002792124,0.0002312615,0.0000661318,0.0001403523,0.0002610688,0.000786205,0.01512245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000177242,"about_ca_system_score_gemma":0.00006140795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009017775,"about_ca_topic_score_gemma":0.00009599313,"domain_scores_codex":[0.997964,0.0003124812,0.0002349832,0.001110668,0.00007733082,0.0003005338],"domain_scores_gemma":[0.9985027,0.00009454129,0.0003191841,0.000762317,0.000191591,0.0001297009],"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":[0.005381861,0.00905476,0.1017232,0.001468739,0.00815547,0.006090015,0.01353349,0.03394429,0.002441781,0.07653525,0.1475633,0.5941078],"study_design_scores_gemma":[0.01520536,0.0008858712,0.1793334,0.002251604,0.003276052,0.00008940094,0.008516734,0.03698893,0.002360389,0.7265375,0.01840308,0.006151683],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8709732,0.00004901898,0.02493083,0.00007366673,0.004942307,0.000512697,0.0003406302,0.0002873341,0.09789032],"genre_scores_gemma":[0.9814214,0.0001500773,0.0001870609,0.0002279162,0.0004328271,0.000001658857,0.002165401,0.00004403442,0.01536967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6500022,"threshold_uncertainty_score":0.9998505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1392797833587188,"score_gpt":0.2280546518621315,"score_spread":0.08877486850341271,"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."}}