{"id":"W2796517058","doi":"10.3390/app8040606","title":"End-to-End Neural Optical Music Recognition of Monophonic Scores","year":2018,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Music and Audio Processing","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada; Ministerio de Economía y Competitividad","keywords":"Connectionism; Computer science; Artificial neural network; Convolutional neural network; Musical notation; Scalability; Notation; Artificial intelligence; Speech recognition; Pattern recognition (psychology); End-to-end principle; Musical; Arithmetic; Mathematics","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":[0.0005086664,0.0001027141,0.0001374213,0.0001397411,0.0003105103,0.0001826808,0.000918093,0.00003442608,0.0001078448],"category_scores_gemma":[0.0000356254,0.00008215135,0.00002988255,0.001042861,0.0007357144,0.0003613322,0.000254285,0.00006885172,0.0001587589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001130973,"about_ca_system_score_gemma":0.0001204429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001754253,"about_ca_topic_score_gemma":0.00001692148,"domain_scores_codex":[0.998576,0.00001553403,0.0002073646,0.0004582154,0.0004245437,0.0003182826],"domain_scores_gemma":[0.9994248,0.00008816963,0.0000916924,0.0002260372,0.00006862998,0.000100693],"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":[0.0000111608,0.00005557251,0.0001949943,0.00001824606,0.000005100143,0.000002426266,0.002064912,0.00006036906,0.1159841,0.03602264,0.001235809,0.8443447],"study_design_scores_gemma":[0.000582359,0.0008968453,0.01005019,0.0001222277,0.00001877884,0.00003227974,0.000457882,0.04471839,0.8713661,0.06948113,0.001499028,0.0007747473],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8614849,0.0000330726,0.1066558,0.0007859429,0.0004102741,0.0001283693,0.000001061611,0.00007899576,0.0304215],"genre_scores_gemma":[0.9349501,0.000001204003,0.06362375,0.001230845,0.0001574732,0.00001047004,4.513761e-7,0.000003143258,0.00002252678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8435699,"threshold_uncertainty_score":0.3350035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05113765583816901,"score_gpt":0.2677386336652907,"score_spread":0.2166009778271217,"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."}}