{"id":"W2605244930","doi":"10.1002/spe.2487","title":"Deep learning and SVM‐based emotion recognition from Chinese speech for smart affective services","year":2017,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"Natural Science Foundation of Shandong Province; Ministry of Science and Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Support vector machine; Deep belief network; Computer science; Artificial intelligence; Mel-frequency cepstrum; Sadness; Surprise; Anger; Feature (linguistics); Speech recognition; Emotion recognition; Emotion classification; Cepstrum; Machine learning; Formant; Pattern recognition (psychology); Deep learning; Feature extraction; Psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002568167,0.0001483191,0.0001451213,0.00005119782,0.000800511,0.0002323262,0.00008243517,0.0001355337,0.0002158362],"category_scores_gemma":[0.00143315,0.000139103,0.00003620679,0.00003954333,0.0001043875,0.001096986,0.00004136119,0.0001784595,0.00005615988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001360634,"about_ca_system_score_gemma":0.000009314515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007939716,"about_ca_topic_score_gemma":0.0001933045,"domain_scores_codex":[0.9989971,0.0001466081,0.0001405293,0.0004254169,0.0001056344,0.0001847171],"domain_scores_gemma":[0.9984974,0.0007452587,0.0003019875,0.0001895605,0.0001772576,0.00008851325],"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":[0.0008305705,0.0002244704,0.07551859,0.0000855327,0.00006329311,0.00002139831,0.03212667,8.296516e-7,0.0008417419,0.0000263207,0.00003500026,0.8902256],"study_design_scores_gemma":[0.01023038,0.001991952,0.8181374,0.0006303966,0.000466555,0.0002931145,0.121664,0.003255755,0.003938968,0.01114208,0.02665054,0.001598894],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9695933,0.0003666076,0.02639997,0.0005092669,0.0006651126,0.0003782329,0.00001830961,0.0001134502,0.001955738],"genre_scores_gemma":[0.9865341,0.000147453,0.01210495,0.0005762172,0.0001905369,0.0001529781,0.0001302398,0.00001900563,0.0001445055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8886267,"threshold_uncertainty_score":0.6156965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02644595577279362,"score_gpt":0.3585577752525215,"score_spread":0.3321118194797279,"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."}}