{"id":"W4412423937","doi":"10.1007/s12559-025-10484-4","title":"SwinTSER: An Improved Bilingual Speech Emotion Recognition Using Shift Window Transformer","year":2025,"lang":"en","type":"article","venue":"Cognitive Computation","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of South Africa","keywords":"Transformer; Speech recognition; Computer science; Window (computing); Natural language processing; Artificial intelligence; Voltage; Engineering","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":[0.0002556518,0.0006409819,0.0004266467,0.00031062,0.0001872158,0.0003839173,0.0005749823,0.0003112547,0.003658956],"category_scores_gemma":[0.0004402268,0.000145577,0.0004735082,0.0002177081,0.0001542467,0.0007588356,0.0005973798,0.0005682647,0.001526898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002428646,"about_ca_system_score_gemma":0.0003919248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003172375,"about_ca_topic_score_gemma":0.003620493,"domain_scores_codex":[0.9998317,0.00002453213,0.00001069754,0.00006046135,0.00004592403,0.00002665448],"domain_scores_gemma":[0.9999045,0.0000160319,0.000006689186,0.00001336869,0.00004556775,0.00001381067],"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":[0.001551813,0.0003722642,0.003034913,0.000153398,0.0001364472,0.0004500224,0.0001245882,0.03593252,0.2220114,0.002344128,0.01101158,0.7228768],"study_design_scores_gemma":[0.00004032192,0.0002223138,0.001421407,0.000008558318,0.00004566898,0.0001726082,0.00006185233,0.9386841,0.05558065,0.0009721737,0.002769773,0.00002053396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.217087,0.0007804186,0.7634707,0.0003350456,0.0003805407,0.0001623478,0.0007332698,0.009365655,0.007684873],"genre_scores_gemma":[0.8778125,0.0003408836,0.1098785,0.0002853874,0.00005386149,0.0001041041,0.001809185,0.0002036822,0.009511898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003658956,"threshold_uncertainty_score":0.01224041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03457323903747449,"score_gpt":0.3206670504625328,"score_spread":0.2860938114250583,"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."}}