{"id":"W4414834375","doi":"10.1007/s00034-025-03333-0","title":"SNRENN: A Transformer-Based Neural Network with Self-Supervised Learning for Auditory Steady State Response Signal SNR Enhancement","year":2025,"lang":"en","type":"article","venue":"Circuits Systems and Signal Processing","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Biometrics; Regularization (linguistics); Authentication (law); Pattern recognition (psychology); Artificial neural network; SIGNAL (programming language); Noise reduction; Transformer","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":[],"consensus_categories":[],"category_scores_codex":[0.001673058,0.0002776532,0.0003714155,0.000199164,0.0006799684,0.0007860703,0.0003415987,0.0001019805,0.00000258922],"category_scores_gemma":[0.00001177095,0.0002400539,0.00006077823,0.0005229998,0.00005904994,0.0006175963,0.00002534191,0.0002728421,9.355125e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009888703,"about_ca_system_score_gemma":0.0007057092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001010147,"about_ca_topic_score_gemma":0.00000368906,"domain_scores_codex":[0.9976792,0.0004177555,0.0004847805,0.000578079,0.0003584076,0.000481784],"domain_scores_gemma":[0.9988266,0.0003546976,0.0002236045,0.0001864856,0.0002931764,0.0001154755],"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":[0.001685686,0.0004600265,0.001342114,0.004698188,0.0002890531,0.00004854958,0.02029043,0.3133995,0.06661589,0.003200925,0.001256533,0.5867131],"study_design_scores_gemma":[0.00134261,0.0008594356,0.000152381,0.0008935423,0.00003210716,0.000009552496,0.0002663432,0.9882913,0.003668127,0.0002230958,0.003885381,0.0003761536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05358378,0.001067487,0.9432409,0.0002338596,0.0001218404,0.0009486513,0.000001901009,0.0004564634,0.0003451116],"genre_scores_gemma":[0.9933313,0.000004616003,0.005499979,0.0003282444,0.0001121972,0.0002968043,0.000005359059,0.00002312737,0.0003984266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9397475,"threshold_uncertainty_score":0.9789115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01609492159668924,"score_gpt":0.2533535620127594,"score_spread":0.2372586404160701,"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."}}