{"id":"W3008558269","doi":"10.48550/arxiv.2002.09026","title":"Multi-label Sound Event Retrieval Using a Deep Learning-based Siamese Structure with a Pairwise Presence Matrix","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Event (particle physics); Sound (geography); Pairwise comparison; Speech recognition; Soundscape; Artificial intelligence; Audio signal; Acoustics; Speech coding","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":[0.0008277612,0.001118309,0.0009583192,0.001025656,0.0004847005,0.00101623,0.001607335,0.00150413,0.003414933],"category_scores_gemma":[0.00216215,0.0003631458,0.0008616881,0.0009960595,0.0005781267,0.002408695,0.001281755,0.001871805,0.001318588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001058619,"about_ca_system_score_gemma":0.001190448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009578647,"about_ca_topic_score_gemma":0.01784988,"domain_scores_codex":[0.999525,0.00008304261,0.00002600369,0.0002151297,0.00009043113,0.00006044441],"domain_scores_gemma":[0.9992663,0.0002692256,0.00006708244,0.0001277331,0.0002026091,0.00006702897],"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":[0.0008477191,0.0009775765,0.002886442,0.0002530296,0.0002192784,0.0002887639,0.000209776,0.2496798,0.03422912,0.008152859,0.02153196,0.6807236],"study_design_scores_gemma":[0.00002115393,0.00006509321,0.0002175972,0.000004798375,0.00001397455,0.00003190975,0.00001576218,0.9943012,0.00204925,0.002718403,0.0005510144,0.000009760998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1439659,0.001717502,0.8402993,0.001215525,0.0002489515,0.0002007887,0.0010512,0.005975737,0.005324997],"genre_scores_gemma":[0.7317163,0.0005292968,0.2462983,0.0007764419,0.0002457069,0.0002200988,0.004442695,0.0002123752,0.01555873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009578647,"threshold_uncertainty_score":0.01904577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08251389631676702,"score_gpt":0.2272457621811828,"score_spread":0.1447318658644158,"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."}}