{"id":"W4414774870","doi":"10.64701/ijrc/345/8907","title":"Speech Emotion Recognition with Hybrid CNN- LSTM and Transformers Models: Evaluating the Hybrid Model Using Grad-CAM","year":2024,"lang":"en","type":"article","venue":"International Journal of Research in Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Transformer; Convolutional neural network; Encoder; Feature extraction; Pattern recognition (psychology); Artificial neural network; Mel-frequency cepstrum; Hybrid neural network; Spectrogram","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":[0.006251228,0.0001280943,0.0001632259,0.0009655085,0.0001911526,0.000850528,0.0006960512,0.00002954107,0.000007863702],"category_scores_gemma":[0.0001925407,0.00009082208,0.00008754446,0.0004707404,0.0001015583,0.00123899,0.0001433399,0.0007721386,0.000004778965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000289734,"about_ca_system_score_gemma":0.0003905554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004776823,"about_ca_topic_score_gemma":0.000005420085,"domain_scores_codex":[0.9966872,0.0003800401,0.0005244861,0.0002948486,0.001795453,0.0003179965],"domain_scores_gemma":[0.9975729,0.001007241,0.0001404799,0.0001087908,0.001075566,0.0000950332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006722728,0.00004401209,0.00005268604,0.00003088946,0.00007959018,0.000331518,0.0006700049,0.03751238,0.0008208554,0.0005318162,0.00003880192,0.9598202],"study_design_scores_gemma":[0.000371906,0.0001453053,0.0000402514,0.001288989,0.000008894564,0.002851896,0.0002571782,0.9437224,0.002119832,0.04907069,0.0000206293,0.0001020358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5008224,0.0002190699,0.496052,0.002099351,0.0002870984,0.0001078745,0.000003103118,0.00002091889,0.0003881957],"genre_scores_gemma":[0.8921946,0.000154951,0.1072785,0.00008064772,0.0002613078,0.000001788036,0.000001647512,0.00001374188,0.00001282092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9597182,"threshold_uncertainty_score":0.8201662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2764907419420464,"score_gpt":0.4399464940596787,"score_spread":0.1634557521176322,"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."}}