{"id":"W4415571224","doi":"10.7717/peerj-cs.3292","title":"Hybrid-Module Transformer: enhancing speech emotion recognition with HuBERT, LSTM, and ResNet-50","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Spectrogram; Generalizability theory; Emotion recognition; Mel-frequency cepstrum; Artificial neural network; Feature (linguistics); Transformer; Cepstrum; Benchmark (surveying)","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":[0.0006599755,0.0001484389,0.0001565181,0.0003663248,0.0003248421,0.0001435627,0.0001878192,0.00005151697,0.0001272589],"category_scores_gemma":[0.00001595272,0.0001310131,0.00003398188,0.0005260845,0.0002880582,0.0004123909,0.00003511953,0.0001681728,0.0001009793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005066812,"about_ca_system_score_gemma":0.00008097378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001019926,"about_ca_topic_score_gemma":0.00007867002,"domain_scores_codex":[0.9984573,0.00006684876,0.0002304109,0.0006148124,0.000282541,0.0003480715],"domain_scores_gemma":[0.9993241,0.0000540038,0.00006468781,0.0002362049,0.0002157843,0.0001051491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000621171,0.0001391272,0.0004432025,0.00004239461,0.00002134055,0.00001510994,0.001056938,0.00001030826,0.005987762,0.001055912,0.001508805,0.989657],"study_design_scores_gemma":[0.01428223,0.004387271,0.4433611,0.00293211,0.0004143599,0.002929397,0.001591493,0.05103407,0.4004302,0.04247803,0.03286747,0.003292328],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5837565,0.00005503172,0.397527,0.0008377514,0.001061987,0.0002513542,0.000005663363,0.0001173401,0.01638733],"genre_scores_gemma":[0.979202,0.00002213391,0.0183602,0.001027149,0.0001364459,0.00001804187,0.00002212163,0.000009679973,0.001202259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9863647,"threshold_uncertainty_score":0.5342559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01787606752980124,"score_gpt":0.2851272987289677,"score_spread":0.2672512311991665,"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."}}