{"id":"W4319299923","doi":"10.1109/wacv56688.2023.00224","title":"AudioViewer: Learning to Visualize Sounds","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Speech recognition; Perception; Field (mathematics); Visualization; Substitution (logic); Natural language processing; Parsing; Artificial intelligence; Human–computer interaction; Multimedia","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":[0.0005910187,0.0003444036,0.0004745921,0.000648111,0.0003349295,0.0004572744,0.002003906,0.0001231531,0.0001473782],"category_scores_gemma":[0.00002715461,0.0003285846,0.0001902565,0.00212223,0.0001026807,0.0003998298,0.0007557711,0.0003524913,0.003159987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005182206,"about_ca_system_score_gemma":0.0001498727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001257439,"about_ca_topic_score_gemma":0.000003651744,"domain_scores_codex":[0.9969984,0.0001263426,0.0006889267,0.0009990979,0.0006653854,0.000521876],"domain_scores_gemma":[0.9975706,0.000224178,0.000304254,0.001172943,0.0004604671,0.0002675419],"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":[0.00002877856,0.0002619989,0.0001099595,0.0001359073,0.00006403206,0.00001175027,0.002187682,0.003063689,0.009178217,0.04465404,0.13083,0.8094739],"study_design_scores_gemma":[0.001141267,0.001390421,0.003213209,0.001159243,0.00003385004,0.00002765309,0.0002388783,0.508975,0.009784292,0.01407502,0.458551,0.001410073],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007271962,0.0000261844,0.9794297,0.005864916,0.000540236,0.0005387446,0.000007843532,0.0006740438,0.005646339],"genre_scores_gemma":[0.9437668,0.0000713633,0.04635018,0.002744792,0.0004685087,0.0003422879,0.00003327562,0.00005083358,0.006172007],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9364948,"threshold_uncertainty_score":0.9999166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03231023235635655,"score_gpt":0.3323631389603665,"score_spread":0.30005290660401,"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."}}