{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003671203,0.0002126083,0.0001987186,0.0003463968,0.0003416402,0.0003653727,0.0001853299,0.0001159908,0.00001409738],"category_scores_gemma":[0.0001316635,0.000228134,0.00007914816,0.0008028043,0.00006169345,0.001333102,0.00004075822,0.0002000151,0.00003388216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009597849,"about_ca_system_score_gemma":0.0003181257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003216501,"about_ca_topic_score_gemma":0.00002898888,"domain_scores_codex":[0.9983832,0.0001389723,0.0003488759,0.0005963811,0.0002161545,0.0003164683],"domain_scores_gemma":[0.9989961,0.0001258113,0.0001445018,0.00008726456,0.0005583175,0.00008805072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003739696,0.0001107444,0.0002910165,0.00004106853,0.00002315698,0.00000704132,0.0005699921,0.00005388389,0.01904958,0.0000165772,0.000004804736,0.9797947],"study_design_scores_gemma":[0.002221662,0.000272123,0.01250756,0.0004801834,0.00009018362,0.00003140692,0.000605614,0.4209012,0.5358744,0.02645902,0.00001938111,0.0005372337],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4418686,0.00004298092,0.5564638,0.0001044398,0.0002827516,0.0002373904,0.000004820974,0.0001699761,0.0008251769],"genre_scores_gemma":[0.939078,0.000005148021,0.06005117,0.0005702723,0.0001228395,0.000007472011,0.0001267014,0.00001354543,0.00002479723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9792575,"threshold_uncertainty_score":0.9303036,"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."}}