{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001053367,0.0002264034,0.0003123494,0.0002883057,0.0001074691,0.0002986434,0.0009391077,0.0002332393,0.00009589051],"category_scores_gemma":[0.0001874326,0.000205438,0.0001984292,0.0001860065,0.00001091402,0.0001013476,0.0007011723,0.0002505741,0.00003542799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002010255,"about_ca_system_score_gemma":0.0001729447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002287712,"about_ca_topic_score_gemma":0.0008010367,"domain_scores_codex":[0.9983924,0.0001331991,0.0002367026,0.0006609431,0.0002587541,0.0003179827],"domain_scores_gemma":[0.9981032,0.0008784071,0.00008663826,0.0007645079,0.00009203524,0.00007522989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004571019,0.0003083556,0.00005941126,0.000246026,0.0001929784,0.00003035556,0.0009702647,0.000387827,0.00001197806,0.8643088,0.04324704,0.09019119],"study_design_scores_gemma":[0.0004916233,0.0000352328,0.0001137895,0.0002413538,0.00001546172,0.000001331792,0.0002020756,0.7554904,0.001777387,0.2407504,0.0004093425,0.000471583],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002036357,0.00003847106,0.9097978,0.0004539142,0.0006886717,0.0004805167,0.0004735357,0.0003095487,0.08755393],"genre_scores_gemma":[0.4554358,0.00008148358,0.4968867,0.005328291,0.0002242712,0.0002583154,0.0004765857,0.00004867771,0.04125993],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7551026,"threshold_uncertainty_score":0.8377517,"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."}}