{"id":"W2809456243","doi":"10.5539/cis.v11n3p50","title":"Music Generation Based on Convolution-LSTM","year":2018,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Music and Audio Processing","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Convolution (computer science); MIDI; Speech recognition; Convolutional neural network; Artificial intelligence; Feature (linguistics); Overlap–add method; Domain (mathematical analysis); Musical notation; Pattern recognition (psychology); Matrix (chemical analysis); Musical; Algorithm; Artificial neural network; Fourier transform; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002618566,0.0006031276,0.0003466078,0.000273262,0.0002475438,0.0004282434,0.0008499013,0.0006096683,0.003479634],"category_scores_gemma":[0.0005383441,0.000248706,0.0004450185,0.000361255,0.0002695239,0.0009990875,0.0004693394,0.0007182871,0.000811219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005065976,"about_ca_system_score_gemma":0.0004552959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004297459,"about_ca_topic_score_gemma":0.00609393,"domain_scores_codex":[0.9998546,0.00001650752,0.000009316952,0.00005571373,0.00003455744,0.00002937815],"domain_scores_gemma":[0.9999031,0.00003141783,0.00001050713,0.00001362057,0.00003000364,0.00001131311],"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":[0.0003881415,0.0001843367,0.001643708,0.0002793443,0.0001897674,0.0004795213,0.0001579864,0.2608816,0.1116493,0.0107836,0.005883296,0.6074795],"study_design_scores_gemma":[0.00001163904,0.00005004841,0.0003309855,0.000008978177,0.00002362298,0.00007816798,0.000009600839,0.9826818,0.01258312,0.002619831,0.001592622,0.000009566584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06229195,0.001395484,0.9178718,0.0004464755,0.0004416073,0.00008159672,0.0003093825,0.00631882,0.01084272],"genre_scores_gemma":[0.8550279,0.0005957318,0.1354248,0.0002654603,0.00007601931,0.00006549201,0.0004665148,0.0001568998,0.007921078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004297459,"threshold_uncertainty_score":0.01164055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02620112331652731,"score_gpt":0.2424372670229367,"score_spread":0.2162361437064094,"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."}}