{"id":"W2766393356","doi":"10.48550/arxiv.1710.11153","title":"Onsets and Frames: Dual-Objective Piano Transcription","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Piano; Speech recognition; Computer science; Transcription (linguistics); Inference; Convolutional neural network; Detector; Polyphony; Artificial intelligence; Pitch detection algorithm; Acoustics; Physics; Speech processing; Telecommunications","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":[0.0001913299,0.0002619711,0.0002791036,0.0001703884,0.0004452044,0.0004047271,0.0008937458,0.0002878371,0.00001814568],"category_scores_gemma":[0.00003072642,0.0002963278,0.0001130327,0.0001352653,0.0001899195,0.000729118,0.0008159601,0.0005184921,0.00002888569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000947873,"about_ca_system_score_gemma":0.0002147646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001106989,"about_ca_topic_score_gemma":0.00002635829,"domain_scores_codex":[0.9984284,0.00008091362,0.000124573,0.001016825,0.00008142921,0.0002678595],"domain_scores_gemma":[0.9985309,0.00004473461,0.000259074,0.0009157421,0.0001124407,0.0001371452],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003042134,0.0008108155,0.01235817,0.002200615,0.001093274,0.004730138,0.02601844,0.03802918,0.003216779,0.788372,0.007930303,0.114936],"study_design_scores_gemma":[0.002209635,0.0002071378,0.0247214,0.001356985,0.0002748514,0.00007933584,0.0004306951,0.4177262,0.001647678,0.5410003,0.008009299,0.002336433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2607616,0.0002019206,0.7291358,0.0003890346,0.0006333591,0.0001870443,0.00001092984,0.0001890374,0.008491395],"genre_scores_gemma":[0.9957586,0.0002387665,0.001768534,0.0002171071,0.00008468792,7.31047e-7,0.000005434435,0.00001153204,0.001914605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.734997,"threshold_uncertainty_score":0.9999489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07067842926005172,"score_gpt":0.1974737256133174,"score_spread":0.1267952963532656,"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."}}