{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008204354,0.001347408,0.0007069113,0.0005845791,0.000309484,0.001034795,0.001165192,0.001292287,0.007085185],"category_scores_gemma":[0.002912825,0.0002793214,0.0004630101,0.0004019143,0.0003092878,0.001146075,0.001854331,0.002009939,0.004873692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004358092,"about_ca_system_score_gemma":0.0008551816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004849392,"about_ca_topic_score_gemma":0.01228586,"domain_scores_codex":[0.99923,0.0001264333,0.00002786514,0.0003114051,0.0002092233,0.00009511613],"domain_scores_gemma":[0.9994104,0.000216951,0.0000317444,0.0001407382,0.0001260083,0.00007421598],"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":[0.002500456,0.0003732455,0.002468353,0.0003258176,0.0001069689,0.0003649336,0.0001816892,0.05381364,0.05576618,0.001771154,0.02739858,0.8549289],"study_design_scores_gemma":[0.000328601,0.0005549054,0.004872754,0.00006946164,0.00007097635,0.0002858989,0.0002592694,0.9188721,0.05090588,0.007343535,0.01636417,0.00007242898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2565253,0.004194003,0.6635307,0.00154242,0.001713883,0.0004174629,0.01383806,0.03346958,0.02476852],"genre_scores_gemma":[0.6377047,0.0007924798,0.2919135,0.0005305249,0.0005962788,0.0002186035,0.03118405,0.001186448,0.03587348],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007085185,"threshold_uncertainty_score":0.02370226,"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."}}