{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009713262,0.0009730087,0.0004485311,0.0006579222,0.0001890657,0.0007875106,0.0007975955,0.00064957,0.00268921],"category_scores_gemma":[0.003238403,0.0001663998,0.0005598424,0.0003484253,0.0002272272,0.001099658,0.0007290255,0.0007403709,0.001020284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005074554,"about_ca_system_score_gemma":0.0003742515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003710879,"about_ca_topic_score_gemma":0.003167725,"domain_scores_codex":[0.9995261,0.00009395678,0.00003466674,0.0001001106,0.0001898517,0.00005528009],"domain_scores_gemma":[0.9993824,0.0002084654,0.0000404682,0.00006611399,0.0002709417,0.00003165584],"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":[0.001463108,0.000581886,0.01078688,0.0004878499,0.0003002388,0.0003947103,0.000150278,0.2379414,0.08413377,0.002139464,0.006581341,0.6550391],"study_design_scores_gemma":[0.00001458867,0.0002129687,0.003381901,0.00002154042,0.0000341181,0.00006395004,0.00005909005,0.971612,0.02297826,0.0006990043,0.0009070442,0.00001546518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5454176,0.002197684,0.4357185,0.0006129087,0.0007371807,0.0002460129,0.00231202,0.005398202,0.007359851],"genre_scores_gemma":[0.9445677,0.0004260249,0.05038609,0.0001218576,0.00005233559,0.0001020979,0.002152775,0.00009348174,0.002097499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003710879,"threshold_uncertainty_score":0.008996308,"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."}}