{"id":"W4312232211","doi":"10.1109/ijcnn55064.2022.9892702","title":"MRGAN: Multi-Criteria Relational GAN for Lyrics-Conditional Melody Generation","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Discriminator; Lyrics; Artificial intelligence; Generator (circuit theory); BLEU; Leverage (statistics); Speech recognition; Generative grammar; Key (lock); Metric (unit); Melody; Natural language processing; Machine learning; Musical; Machine translation; Power (physics)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004494965,0.0002764716,0.0002294847,0.0002369124,0.0008133129,0.0004308357,0.0009520188,0.00007250396,0.002644855],"category_scores_gemma":[0.00007582295,0.0002889847,0.0001710259,0.0002964887,0.00006284242,0.0007432463,0.0003985981,0.0004869146,0.00002202024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002380505,"about_ca_system_score_gemma":0.0001758475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007098674,"about_ca_topic_score_gemma":0.000007610428,"domain_scores_codex":[0.997256,0.0001520575,0.0005513889,0.000758059,0.0009069717,0.0003755391],"domain_scores_gemma":[0.9987017,0.0001388506,0.000353517,0.0003069304,0.0003807197,0.0001182704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001144034,0.0004582551,0.0002487005,0.00001411544,0.00009768599,0.00003999744,0.0003704583,0.2691545,0.006715874,0.5973366,0.1052252,0.02022421],"study_design_scores_gemma":[0.001058489,0.0001537469,0.001178479,0.00001953278,0.000006152356,0.00005911399,0.0000259635,0.9797504,0.0002283285,0.005338036,0.01186002,0.0003217235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002766072,0.00003052472,0.9755163,0.01458577,0.003738956,0.001210886,0.0001132078,0.0001787678,0.001859568],"genre_scores_gemma":[0.9710188,0.000006938983,0.01486746,0.007213561,0.001445435,0.002392103,0.001096624,0.00003009626,0.001929007],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9682527,"threshold_uncertainty_score":0.9999563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1070900726682258,"score_gpt":0.3022042917470935,"score_spread":0.1951142190788677,"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."}}