{"id":"W3095237804","doi":"10.1109/access.2020.3035910","title":"Ensemble Learning With Attention-Integrated Convolutional Recurrent Neural Network for Imbalanced Speech Emotion Recognition","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Science Research of Jiangsu Higher Education Institutions of China; National Natural Science Foundation of China; Air Force Civil Engineer Center; Key Laboratory in Science and Technology Development Project of Suzhou","keywords":"Computer science; Oversampling; Recurrent neural network; Convolutional neural network; Artificial intelligence; Ensemble learning; Emotion recognition; Speech recognition; Machine learning; Pattern recognition (psychology); Artificial neural network","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":[0.0001827092,0.0001927798,0.0002148217,0.00006364543,0.0002283266,0.0000987356,0.0001471463,0.0001361493,0.0007418528],"category_scores_gemma":[0.00005673448,0.0001761229,0.0001061971,0.0003790127,0.00004571323,0.0003057027,0.00001521466,0.000326884,0.0002677111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004502001,"about_ca_system_score_gemma":0.00003458349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003631663,"about_ca_topic_score_gemma":0.00003824774,"domain_scores_codex":[0.9985003,0.000188446,0.0003102764,0.0004578084,0.0001843047,0.0003588745],"domain_scores_gemma":[0.9990497,0.00009769815,0.0002349251,0.0001005043,0.0003830959,0.0001341046],"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":[0.006938783,0.0009992953,0.07964054,0.0003759449,0.0007311142,0.00006885552,0.001673917,0.006758783,0.01269148,0.001009502,0.1642745,0.7248372],"study_design_scores_gemma":[0.05414806,0.01403946,0.6378286,0.002215446,0.001697826,0.0008136468,0.005549384,0.173068,0.01518392,0.01189331,0.0774891,0.006073304],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8856167,0.00005189383,0.1056096,0.001461095,0.002601347,0.000958784,0.0000701295,0.0003317492,0.003298694],"genre_scores_gemma":[0.9942661,0.00001533208,0.001204145,0.0008423301,0.00125368,0.0001824316,0.001624936,0.00003895369,0.0005720771],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7187639,"threshold_uncertainty_score":0.8122768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0790465265595607,"score_gpt":0.3355423317751242,"score_spread":0.2564958052155635,"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."}}