{"id":"W4392902957","doi":"10.1109/icassp48485.2024.10446663","title":"Adapting Frechet Audio Distance for Generative Music Evaluation","year":2024,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Outlier; Sound quality; Computer science; Generative model; Popularity; Sample (material); Quality (philosophy); Perception; Generative grammar; Sample size determination; Range (aeronautics); Speech recognition; Artificial intelligence; Mathematics; Statistics; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.0006716008,0.00008039549,0.00007449563,0.00004072471,0.000140869,0.000378319,0.0002165718,0.00002887807,0.00006500187],"category_scores_gemma":[0.00007410138,0.0000642576,0.00004278227,0.0002578431,0.00001464919,0.0005491216,0.00005410986,0.00005729458,0.00002296539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006286854,"about_ca_system_score_gemma":0.0001625927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003112252,"about_ca_topic_score_gemma":0.00001737609,"domain_scores_codex":[0.9991322,0.00003072725,0.0001282776,0.0003360598,0.0002150079,0.0001576826],"domain_scores_gemma":[0.9995428,0.0001275565,0.00003019919,0.000161167,0.0001077638,0.00003048356],"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":[0.000001285594,0.00000891444,0.000005236519,0.00005821185,0.0000140591,0.000001758822,0.002163158,0.0004823215,0.002417919,0.2200767,0.02942223,0.7453482],"study_design_scores_gemma":[0.00008963364,0.00001734777,0.00001492915,0.00005895246,0.000007961265,0.000002255558,0.00005607028,0.950587,0.005231485,0.02308842,0.02074114,0.0001048395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001254713,0.001046432,0.982276,0.002069707,0.0006211239,0.0001995164,0.000001681567,0.0002209619,0.01230989],"genre_scores_gemma":[0.708591,0.000003229532,0.2875865,0.00106187,0.0003361943,0.00009109496,0.00000464913,0.000008234208,0.00231726],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9501047,"threshold_uncertainty_score":0.3648139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09499286057563092,"score_gpt":0.3283317310722939,"score_spread":0.2333388704966629,"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."}}