{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006968516,0.001724585,0.001219606,0.002909329,0.0005965426,0.002587505,0.001928518,0.001847501,0.006893593],"category_scores_gemma":[0.03264295,0.0004481718,0.0009418807,0.001180516,0.0008352132,0.002473421,0.003139438,0.001840755,0.002798048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009540007,"about_ca_system_score_gemma":0.0007400933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003048219,"about_ca_topic_score_gemma":0.005361933,"domain_scores_codex":[0.9961613,0.001303155,0.0002541214,0.0006008732,0.001449152,0.0002313632],"domain_scores_gemma":[0.9900564,0.005518329,0.0003991098,0.001479023,0.002071601,0.0004755779],"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":[0.00123515,0.000450534,0.009249698,0.0006109821,0.0002844297,0.0002925333,0.0004168018,0.1375339,0.03324182,0.007943049,0.01134961,0.7973914],"study_design_scores_gemma":[0.0001082922,0.0005505403,0.004803419,0.00007634112,0.00004216271,0.0003061205,0.0001531,0.9588099,0.0179801,0.01231529,0.004751312,0.0001034555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1014464,0.001043524,0.8713939,0.0002941621,0.000353002,0.0004456375,0.001077326,0.01673098,0.007215178],"genre_scores_gemma":[0.5019499,0.0003014988,0.4870426,0.0003016322,0.0001118013,0.0004213071,0.003417628,0.00193702,0.004516629],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006968516,"threshold_uncertainty_score":0.03685343,"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."}}