{"id":"W4416581044","doi":"10.1016/j.csl.2025.101907","title":"A robust framework for noisy speech recognition using Frequency-Guided-Swin Transformer","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Transformer; Robustness (evolution); Convolutional neural network; Word error rate; Pattern recognition (psychology); Deep neural networks; Artificial neural network; Deep learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000583971,0.0004044914,0.0004832028,0.000513571,0.0002897349,0.0004755422,0.001158368,0.0003171749,0.0002999068],"category_scores_gemma":[0.0001494904,0.0004026027,0.0003713951,0.0009890613,0.00006696999,0.0006842744,0.0001314543,0.0003567538,0.0001478205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001701499,"about_ca_system_score_gemma":0.0001872152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001076085,"about_ca_topic_score_gemma":0.00004601509,"domain_scores_codex":[0.9973137,0.000127634,0.0006156042,0.0008952772,0.0003699261,0.0006778833],"domain_scores_gemma":[0.998121,0.0004124134,0.0001551178,0.0008600366,0.0002814334,0.0001699597],"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":[0.00001292588,0.0001410952,0.00005386869,0.0000982268,0.00008833092,0.0001293336,0.0007119045,0.00001711316,0.002303372,0.004839781,0.002575658,0.9890284],"study_design_scores_gemma":[0.004174306,0.0004301316,0.001092223,0.002000111,0.0003489004,0.0009894788,0.0006421001,0.4060981,0.3895822,0.1824249,0.009201528,0.003016073],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03595994,0.0002775863,0.9545137,0.00118967,0.001765261,0.0008198338,0.00004748227,0.0005455591,0.004881018],"genre_scores_gemma":[0.01046269,0.00001984179,0.9854031,0.003113179,0.0005929616,0.00006098418,0.00004166626,0.00003724818,0.000268313],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9860123,"threshold_uncertainty_score":0.9998426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06383290841893033,"score_gpt":0.3086372540781378,"score_spread":0.2448043456592075,"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."}}