{"id":"W4389538366","doi":"10.1109/embc40787.2023.10340283","title":"Misophonia Sound Recognition Using Vision Transformer","year":2023,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Kids Brain Health Network","keywords":"Computer science; Transformer; Convolutional neural network; Speech recognition; Feature extraction; Deep learning; Artificial intelligence; Pattern recognition (psychology); Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001648331,0.00006334276,0.00006278087,0.00008682036,0.0001588024,0.0001592705,0.0001723931,0.00003401907,0.00008879524],"category_scores_gemma":[0.00000612483,0.00005320458,0.00003353716,0.0005621587,0.00001515669,0.0005787814,0.00002577077,0.00004869615,0.0004703258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001392273,"about_ca_system_score_gemma":0.00002986278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001365011,"about_ca_topic_score_gemma":0.000003672135,"domain_scores_codex":[0.9993516,0.00001263998,0.0001094779,0.0001976474,0.0001480515,0.0001805924],"domain_scores_gemma":[0.9997596,0.00002295169,0.00002363094,0.0001208035,0.00003182498,0.0000412491],"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":[0.000003480543,0.0000251265,0.00007129694,0.00004165747,0.00000726525,0.00001559169,0.001497334,0.0001215262,0.03540287,0.0007765935,0.005012606,0.9570246],"study_design_scores_gemma":[0.0008683396,0.0001040416,0.001521935,0.0001799331,0.00001512958,0.00006337067,0.0002491239,0.7888901,0.05820027,0.13991,0.009313027,0.0006847268],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1894866,0.00001867736,0.8015838,0.0008524552,0.0002442033,0.00004482586,4.530752e-7,0.0003135759,0.007455426],"genre_scores_gemma":[0.9241183,0.00001384873,0.07388288,0.001249858,0.00009820979,0.000002820413,0.000004768322,0.000009038608,0.0006202502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9563399,"threshold_uncertainty_score":0.6045244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06952098675087608,"score_gpt":0.3074879309966584,"score_spread":0.2379669442457824,"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."}}