{"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":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01189238,0.0003004072,0.000423616,0.002274364,0.0005161357,0.0004500743,0.0006559004,0.0001302845,0.00005066623],"category_scores_gemma":[0.0004186735,0.0002442166,0.0001894254,0.0007535791,0.0004038735,0.0006444909,0.0001802961,0.002386774,0.00000652203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007120601,"about_ca_system_score_gemma":0.0009476835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002135239,"about_ca_topic_score_gemma":0.00003444456,"domain_scores_codex":[0.9933388,0.001818039,0.001501929,0.0005280056,0.002128486,0.0006847337],"domain_scores_gemma":[0.9942,0.001356126,0.0007313458,0.00017875,0.003378108,0.0001556994],"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":[0.002042229,0.0004881505,0.0006400365,0.0001453091,0.0006034701,0.0002317163,0.002163327,0.1304234,0.00100028,0.0005818481,0.0001644194,0.8615159],"study_design_scores_gemma":[0.004119112,0.0006541184,0.000415996,0.005300862,0.00009519631,0.002295659,0.00335702,0.9281301,0.0008233534,0.05455226,0.00004336163,0.0002129037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7772762,0.0009617733,0.210887,0.004633342,0.001616541,0.0005604498,0.00002481034,0.00001238216,0.004027503],"genre_scores_gemma":[0.9893196,0.0009644075,0.00860754,0.0002973475,0.0006287623,0.0000045724,0.00001697206,0.00003585031,0.0001249872],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.861303,"threshold_uncertainty_score":0.9999148,"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."}}