{"id":"W7130503370","doi":"10.64701/ijrc/345/8915","title":"Speech Emotion Recognition with Hybrid CNNLSTM and Transformers Models: Evaluating the Hybrid Model Using Grad-CAM","year":2025,"lang":"","type":"article","venue":"International Journal of Research in Computing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Transformer; Encoder; Feature extraction; Artificial neural network; Convolutional neural network; Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001101594,0.001311642,0.0007111619,0.0006686201,0.0002233476,0.000815028,0.001139344,0.0008518647,0.00224301],"category_scores_gemma":[0.001649269,0.0002300654,0.0008098859,0.0003567135,0.000221827,0.0009271884,0.0006379371,0.0008952675,0.0008040598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016969,"about_ca_system_score_gemma":0.0005868583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01530346,"about_ca_topic_score_gemma":0.01423976,"domain_scores_codex":[0.9996786,0.00006522002,0.00002704794,0.00009133688,0.00007889584,0.00005887588],"domain_scores_gemma":[0.9995978,0.0001379783,0.00002384841,0.00003423655,0.0001804123,0.00002566352],"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":[0.001949597,0.000721499,0.01127604,0.0005891169,0.0005903357,0.0003679854,0.0002158929,0.3803261,0.02535934,0.001870448,0.008649612,0.5680841],"study_design_scores_gemma":[0.00001569021,0.0002272439,0.001241095,0.00001597128,0.00006740944,0.00003719179,0.00005095519,0.9931064,0.004448614,0.0002087764,0.0005697779,0.00001096144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8093655,0.006104594,0.1609172,0.001136179,0.001077221,0.0003886538,0.001456472,0.005163677,0.01439045],"genre_scores_gemma":[0.9609021,0.0007035384,0.03120357,0.0002447611,0.0000602872,0.0001464245,0.00163011,0.00007254873,0.005036668],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01530346,"threshold_uncertainty_score":0.03042877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2935495145993136,"score_gpt":0.4967650860546444,"score_spread":0.2032155714553309,"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."}}