{"id":"W4412020141","doi":"10.19139/soic-2310-5070-2521","title":"A Hybrid Approach of Long Short Term Memory and Transformer Models for Speech Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"Statistics Optimization & Information Computing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Speech recognition; Term (time); Transformer; Long short term memory; Computer science; Short-term memory; Cognitive psychology; Natural language processing; Psychology; Artificial intelligence; Cognition; Engineering; Artificial neural network; Working memory; Electrical engineering; Recurrent neural network; Neuroscience","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":[0.0004961538,0.0001501946,0.0002213766,0.0004101361,0.0002163481,0.0002136157,0.0001849029,0.00006535298,0.00000922121],"category_scores_gemma":[0.0001383804,0.0001642306,0.00004939794,0.000296239,0.00004462142,0.001652931,0.00004048764,0.00008053896,0.000001869911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004520354,"about_ca_system_score_gemma":0.00008275796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005455964,"about_ca_topic_score_gemma":6.192671e-7,"domain_scores_codex":[0.9986487,0.0000466957,0.0007009956,0.000194108,0.0002253952,0.0001840738],"domain_scores_gemma":[0.9986418,0.0002367138,0.0002218608,0.0001659085,0.0006818539,0.00005180819],"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":[0.00001434648,0.00003494734,0.00001752419,0.0002908781,0.00002699107,2.854822e-7,0.0006111627,0.160537,0.000008512582,0.008529663,0.0002187777,0.8297099],"study_design_scores_gemma":[0.0004971173,0.00003198663,0.0001126611,0.00008859535,0.00003024051,0.00001673837,0.0001426457,0.9919602,0.002233935,0.004710632,0.00001435224,0.0001608823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001481144,0.00001114817,0.9912814,0.00006024511,0.000199653,0.0006579433,0.0001521647,0.0001129711,0.00604333],"genre_scores_gemma":[0.1304319,0.00003801594,0.8686324,0.0001670724,0.00001680243,0.00001919672,0.0006672379,0.000006376125,0.00002094334],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8314232,"threshold_uncertainty_score":0.6697131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02329019575944726,"score_gpt":0.2514189199685227,"score_spread":0.2281287242090755,"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."}}