{"id":"W4225939130","doi":"10.1109/taslp.2022.3156795","title":"Multimodal System for Audio Scene Source Counting and Analysis","year":2022,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Music and Audio Processing","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Notation; Margin (machine learning); Computer science; Audio signal processing; Speech recognition; Artificial intelligence; Audio signal; Mathematics; Arithmetic; Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0006007469,0.0002634119,0.0003912773,0.0004436582,0.002013553,0.0005190771,0.000480156,0.00006836551,0.00002691807],"category_scores_gemma":[0.00002359768,0.0002615934,0.0001359512,0.001148046,0.00007095856,0.0004826937,0.00004246052,0.0003361898,0.000001709162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001140676,"about_ca_system_score_gemma":0.000111102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000865535,"about_ca_topic_score_gemma":0.00002848852,"domain_scores_codex":[0.9979977,0.00007214907,0.0003401857,0.0007358321,0.0004020449,0.0004521113],"domain_scores_gemma":[0.9989862,0.0001403618,0.0002238378,0.0004107758,0.00008966421,0.0001491913],"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":[0.00004379193,0.0000860721,0.0002440903,0.0004706664,0.0001516103,0.00003004272,0.005529631,0.004578902,0.00520264,0.00001648906,0.00003472274,0.9836113],"study_design_scores_gemma":[0.002257193,0.0002417745,0.0004948822,0.000262596,0.0007766882,0.000420712,0.008380803,0.9489172,0.03486959,0.0001112586,0.00221739,0.00104991],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1007803,0.001699955,0.8961394,0.0004609726,0.0001827893,0.0002436699,0.00002979396,0.0003286647,0.0001343572],"genre_scores_gemma":[0.8878682,0.00001101358,0.1109172,0.0004903417,0.00008508741,0.00009546414,0.000006959296,0.0000262123,0.0004995996],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9825614,"threshold_uncertainty_score":0.9999836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01138665185019432,"score_gpt":0.2476931154263021,"score_spread":0.2363064635761078,"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."}}