{"id":"W4412566360","doi":"10.36227/techrxiv.175321809.95815200/v1","title":"A Survey on Speech Large Language Models for Understanding","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Linguistics; Computer science; Indirect speech; Natural language processing; Philosophy","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":[0.003631691,0.001926419,0.001381799,0.003952923,0.0006271991,0.003979079,0.002766272,0.00197482,0.01171699],"category_scores_gemma":[0.01580172,0.0009138067,0.001484849,0.003752354,0.0009831851,0.008714201,0.002043872,0.002569147,0.00538889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001637155,"about_ca_system_score_gemma":0.003180862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004793379,"about_ca_topic_score_gemma":0.004484161,"domain_scores_codex":[0.997928,0.000830082,0.0002630564,0.0003922741,0.000524118,0.00006247887],"domain_scores_gemma":[0.9909725,0.007058197,0.0002454306,0.000706385,0.0009019508,0.0001155165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001044428,0.0000927055,0.001581525,0.006025023,0.000165827,0.0001588251,0.0007384128,0.01344438,0.001686733,0.06141227,0.04265662,0.8719332],"study_design_scores_gemma":[0.00003032553,0.0001827911,0.00234323,0.004926945,0.0002777189,0.0007934755,0.0008635932,0.09557939,0.003461495,0.1352858,0.7561047,0.0001505934],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.006060995,0.4787446,0.4756126,0.008235142,0.001212571,0.0002600099,0.0030381,0.003426982,0.0234091],"genre_scores_gemma":[0.07057094,0.6313863,0.2670243,0.003161947,0.002640734,0.0007642303,0.01260826,0.001525155,0.01031808],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01171699,"threshold_uncertainty_score":0.03919727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1551207402031654,"score_gpt":0.3327232833825202,"score_spread":0.1776025431793548,"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."}}