{"id":"W4413979917","doi":"10.1109/taslpro.2025.3606235","title":"Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"National Natural Science Foundation of China","keywords":"Utterance; Speech recognition; Computer science; Speech processing; Natural language processing; Artificial intelligence","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":[0.001356232,0.001175456,0.0007196207,0.0005259602,0.0004356692,0.0009190681,0.0009970968,0.0006716285,0.001954491],"category_scores_gemma":[0.003877142,0.0005913433,0.0007925704,0.0003788081,0.0004973396,0.002241803,0.001887778,0.001070809,0.000995011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004491371,"about_ca_system_score_gemma":0.0009141662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005026942,"about_ca_topic_score_gemma":0.007562959,"domain_scores_codex":[0.9985431,0.0005267136,0.00007699346,0.0005530943,0.0001968628,0.0001032197],"domain_scores_gemma":[0.9986796,0.0007023428,0.00009623992,0.0002312702,0.0002242411,0.00006629818],"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":[0.001844637,0.0003065048,0.006118167,0.0002647733,0.0002061662,0.0006579557,0.001093031,0.3053651,0.1123638,0.009920225,0.002035881,0.5598238],"study_design_scores_gemma":[0.00002203259,0.0003142255,0.001649621,0.00001361118,0.0000538017,0.0001673914,0.000258625,0.9662417,0.02496762,0.004096796,0.002181476,0.00003321028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.165726,0.0008635608,0.8278738,0.0001820493,0.00007629282,0.0001033161,0.0002137668,0.002780879,0.00218031],"genre_scores_gemma":[0.8790269,0.0003308049,0.1178723,0.000103197,0.00005025083,0.0001207222,0.0007317804,0.0002643202,0.001499693],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005026942,"threshold_uncertainty_score":0.009995341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05215438308880152,"score_gpt":0.2992675605736401,"score_spread":0.2471131774848386,"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."}}