{"id":"W4410840149","doi":"10.1007/s11042-025-20930-y","title":"Evaluating raw waveforms with deep learning frameworks for speech emotion recognition","year":2025,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Emotion recognition; Speech recognition; Waveform; Deep learning; Artificial intelligence; Natural language processing","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":[0.0002612946,0.0001045625,0.0001121713,0.00007438343,0.0004604998,0.0003076621,0.0001733128,0.0001098611,0.000005247121],"category_scores_gemma":[0.0001173528,0.00008533814,0.00002746936,0.0003692372,0.00003759935,0.0003922586,0.00005399262,0.0002349363,0.000010586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002526985,"about_ca_system_score_gemma":0.00004408399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003529161,"about_ca_topic_score_gemma":0.00000599527,"domain_scores_codex":[0.9991669,0.0000137698,0.0001693214,0.0003373604,0.000118517,0.0001941013],"domain_scores_gemma":[0.9992567,0.0002354015,0.0000951313,0.0001833944,0.0001757218,0.00005365255],"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":[0.000005330702,0.00002353892,0.0003448497,0.00003186441,0.000008525405,1.410448e-7,0.0001491705,0.0001758929,0.001540821,0.00032675,0.0000146008,0.9973785],"study_design_scores_gemma":[0.001641949,0.0002008191,0.005778792,0.0002960146,0.0000612065,0.00001044521,0.0004694666,0.8803999,0.06745332,0.03768439,0.005575197,0.0004284899],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02110727,0.0001391764,0.9764513,0.0007748643,0.00004187097,0.0006763872,0.000002782688,0.0001451535,0.0006612236],"genre_scores_gemma":[0.1633193,0.00003976462,0.8351261,0.0003050449,0.0001275471,0.0007962206,0.00008188084,0.000009047225,0.0001950727],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.99695,"threshold_uncertainty_score":0.3541839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0351451635607987,"score_gpt":0.3205086448370199,"score_spread":0.2853634812762212,"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."}}