{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005942423,0.0003646548,0.0004263615,0.0004857368,0.000675553,0.0009454034,0.0003834957,0.0001609422,0.00006259516],"category_scores_gemma":[0.00004446655,0.0003555264,0.0001761182,0.0006418905,0.0001069044,0.001715027,0.000004574629,0.0003366348,0.00005099336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009689033,"about_ca_system_score_gemma":0.0001357626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008874114,"about_ca_topic_score_gemma":0.00006912707,"domain_scores_codex":[0.9977495,0.00007870117,0.0005482937,0.0007471764,0.0003332287,0.0005430872],"domain_scores_gemma":[0.9986805,0.000307,0.0001566844,0.0003729381,0.000321503,0.000161376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000940089,0.0001070137,0.000009680946,0.0004259439,0.00005338309,0.00003633463,0.0008712363,0.00002368356,0.006907953,0.00002975913,0.00005453884,0.9913865],"study_design_scores_gemma":[0.002664007,0.000166807,0.0001647303,0.00158035,0.0001141825,0.0003045295,0.001337886,0.02344211,0.9660814,0.0004298362,0.002849681,0.0008644996],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1198015,0.001063064,0.873769,0.000498502,0.001233729,0.0007630979,0.00007121284,0.0004530087,0.002346829],"genre_scores_gemma":[0.9333922,0.0002947299,0.06207423,0.001115143,0.0001528527,0.0004674098,0.00001155045,0.00004049766,0.002451357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.990522,"threshold_uncertainty_score":0.9998897,"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."}}