{"id":"W4408354432","doi":"10.1109/icassp49660.2025.10889092","title":"What Are They Doing? Joint Audio-Speech Co-Reasoning","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Concordia University","funders":"","keywords":"Joint (building); Computer science; Speech recognition; Engineering","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":[0.003551727,0.001611189,0.0008004939,0.000623879,0.0008630065,0.002332166,0.001761756,0.002320301,0.00639674],"category_scores_gemma":[0.02104841,0.0003953202,0.001878094,0.0006109329,0.0008249521,0.003708705,0.001608715,0.002318478,0.002195648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001116135,"about_ca_system_score_gemma":0.001579933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01156225,"about_ca_topic_score_gemma":0.01780611,"domain_scores_codex":[0.9956568,0.001797719,0.0002282918,0.001426659,0.00058624,0.0003043811],"domain_scores_gemma":[0.9899631,0.006269385,0.0006746619,0.001899131,0.0006798152,0.0005138327],"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":[0.008625937,0.002042835,0.1312065,0.003567428,0.001750934,0.001680731,0.005732309,0.1333628,0.03503834,0.03817293,0.1309838,0.5078356],"study_design_scores_gemma":[0.0004434221,0.0006785821,0.02347812,0.0003912838,0.0005453884,0.001186732,0.003563904,0.7729763,0.02724582,0.1023232,0.06696095,0.0002062744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5641683,0.004914726,0.3232092,0.00814218,0.000912297,0.0007663078,0.04236719,0.0137605,0.0417593],"genre_scores_gemma":[0.8538356,0.0004850967,0.1133128,0.001096874,0.00008772386,0.0001538909,0.02614627,0.0004858501,0.004395946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01156225,"threshold_uncertainty_score":0.02298993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01509403267989033,"score_gpt":0.2614817200377479,"score_spread":0.2463876873578576,"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."}}