{"id":"W7132304290","doi":"","title":"iFLYTEK: Can the Leader in Intelligent Speech Recognition Succeed in the Era of Large Language Models?","year":2024,"lang":"","type":"other","venue":"CEIBS Institutional Repository","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Casa","funders":"","keywords":"Feature (linguistics); Natural language; Speaker recognition; Speech technology; Field (mathematics)","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":[0.01512486,0.0007393661,0.00105807,0.002501303,0.004289387,0.0134757,0.001988654,0.00324342,0.01012105],"category_scores_gemma":[0.04643567,0.0006862879,0.0007728699,0.002267217,0.01133982,0.02964056,0.004301649,0.007020875,0.00313686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004738971,"about_ca_system_score_gemma":0.006470224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01066971,"about_ca_topic_score_gemma":0.007274528,"domain_scores_codex":[0.9931818,0.003641612,0.0002779341,0.001283542,0.001212962,0.0004022098],"domain_scores_gemma":[0.9803742,0.01342952,0.0008779174,0.001721325,0.002797521,0.0007995366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001069421,0.00006303519,0.003478346,0.000170824,0.0000573845,0.0001077354,0.01052605,0.00320661,0.0006396575,0.8849396,0.01457359,0.08213013],"study_design_scores_gemma":[0.00005242351,0.00005634744,0.001610415,0.0002263865,0.0000342161,0.00007875872,0.005142117,0.01289399,0.00139806,0.9154419,0.06300067,0.00006472921],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.07497899,0.01158494,0.3317048,0.2577902,0.002984857,0.0002051377,0.0008318924,0.001525503,0.3183938],"genre_scores_gemma":[0.8581345,0.005589698,0.09091547,0.009966644,0.001738538,0.0003659479,0.0004701841,0.0004951091,0.03232393],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01512486,"threshold_uncertainty_score":0.07998884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03240390283629502,"score_gpt":0.2821756730713068,"score_spread":0.2497717702350117,"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."}}