{"id":"W3124875196","doi":"10.1109/access.2021.3054345","title":"Efficient Feature-Aware Hybrid Model of Deep Learning Architectures for Speech Emotion Recognition","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Softmax function; Computer science; Speech recognition; Convolutional neural network; Deep learning; Artificial intelligence; Feature extraction; Mel-frequency cepstrum; Feature (linguistics); Artificial neural network; Pattern recognition (psychology); Feedforward neural network","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":[0.0001753475,0.0001183679,0.0001618965,0.0001055283,0.0001584767,0.0002222789,0.0004726575,0.00004774234,0.000005699901],"category_scores_gemma":[0.0001120456,0.0001141892,0.00009106556,0.0002977038,0.00002175309,0.0001233333,0.0001102181,0.0001645297,0.000003273266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002614459,"about_ca_system_score_gemma":0.00007636069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004429803,"about_ca_topic_score_gemma":0.000008136976,"domain_scores_codex":[0.9989353,0.00004114618,0.0001722076,0.0003697797,0.0002416289,0.0002398997],"domain_scores_gemma":[0.9991647,0.00008166631,0.0001517392,0.0002234712,0.0003231591,0.00005525602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001635399,0.00006003449,0.0001398621,0.0001321372,0.00001226565,0.00001076722,0.000292659,0.4046262,0.02748657,0.000007919498,0.0000957823,0.5671195],"study_design_scores_gemma":[0.0001878439,0.00001803401,0.00009785446,0.00004920968,0.000006330662,0.00002054121,0.0000098547,0.474692,0.5216926,0.003127919,0.00001144523,0.00008640624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4533447,0.00008461622,0.5459582,0.0001623977,0.0001716779,0.00007695529,0.000004336708,0.00005881517,0.0001384],"genre_scores_gemma":[0.9282768,0.000004614147,0.07131865,0.0001686915,0.0001018968,0.00001304479,0.00001481382,0.00001158805,0.00008991981],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5670331,"threshold_uncertainty_score":0.46565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03479177377877663,"score_gpt":0.2885383254490828,"score_spread":0.2537465516703062,"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."}}