{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007830872,0.001385784,0.001148021,0.001270136,0.0003855265,0.001074086,0.001602354,0.001469619,0.02951196],"category_scores_gemma":[0.002167722,0.000283704,0.0006904635,0.0006095815,0.0002835147,0.001656507,0.002302202,0.001101288,0.01453257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006218795,"about_ca_system_score_gemma":0.0006707311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002371504,"about_ca_topic_score_gemma":0.00369868,"domain_scores_codex":[0.9993978,0.00008724784,0.00003441463,0.0002234636,0.0001851882,0.0000718989],"domain_scores_gemma":[0.9994324,0.00009455848,0.00003861435,0.0001058244,0.0002697747,0.00005890383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001685911,0.0003041848,0.001678015,0.0006307752,0.000207112,0.0006252357,0.0002216662,0.00922739,0.1394598,0.005166444,0.07442176,0.7663717],"study_design_scores_gemma":[0.0002122382,0.0006619685,0.007087748,0.0001912857,0.000252701,0.001220172,0.0002000047,0.7767303,0.1105374,0.01371522,0.08894641,0.0002444739],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02585071,0.001251871,0.8629331,0.0004602921,0.0007893915,0.0006368927,0.006758037,0.08456535,0.01675445],"genre_scores_gemma":[0.3169856,0.0007367539,0.632992,0.001156188,0.0004497053,0.001367234,0.01505721,0.002378665,0.02887668],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02951196,"threshold_uncertainty_score":0.09872735,"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."}}