{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001217579,0.001345997,0.0007609563,0.000684764,0.0002451768,0.0008242889,0.001036601,0.0008428788,0.002103517],"category_scores_gemma":[0.001677268,0.0002279053,0.0008368679,0.0003921922,0.0002193904,0.0008296089,0.0005734485,0.0009014725,0.0006869232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009798878,"about_ca_system_score_gemma":0.0006051245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01690708,"about_ca_topic_score_gemma":0.01247584,"domain_scores_codex":[0.999663,0.00007765827,0.00003012125,0.00009719271,0.0000742273,0.00005776353],"domain_scores_gemma":[0.9995236,0.0001744951,0.00002703694,0.00003627858,0.0002092171,0.00002932725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001824746,0.0007343094,0.01021269,0.0005232351,0.0006172564,0.0003343691,0.0001645164,0.4915384,0.02208844,0.001445383,0.007842923,0.4626737],"study_design_scores_gemma":[0.000009902593,0.0001354665,0.0007850772,0.00001018126,0.00004696345,0.00001718901,0.00002900866,0.9958524,0.002727668,0.0001227859,0.000256382,0.000007015892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8311326,0.005700318,0.1440313,0.001034194,0.00101599,0.0003113124,0.001179238,0.004564814,0.01103022],"genre_scores_gemma":[0.9725916,0.0005131846,0.0219415,0.0001562908,0.00004899815,0.00009837333,0.001118358,0.00005227478,0.003479304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01690708,"threshold_uncertainty_score":0.03361738,"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."}}