{"id":"W4408051557","doi":"10.3390/electronics14050973","title":"Efficient Ensemble of Deep Neural Networks for Multimodal Punctuation Restoration and the Spontaneous Informal Speech Dataset","year":2025,"lang":"en","type":"article","venue":"Electronics","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Punctuation; Computer science; Artificial neural network; Deep neural networks; Speech recognition; Recurrent neural network; Artificial intelligence; Natural language processing","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":[0.001418341,0.002478323,0.0008785311,0.001514262,0.0008304023,0.0007501942,0.002087589,0.001358138,0.00425485],"category_scores_gemma":[0.003692709,0.0003455903,0.000976103,0.0009445209,0.0005283119,0.001132804,0.001781405,0.002035956,0.004841192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008636613,"about_ca_system_score_gemma":0.001211956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01321012,"about_ca_topic_score_gemma":0.03444658,"domain_scores_codex":[0.9989626,0.0002835874,0.000070323,0.000311887,0.0002594261,0.0001121788],"domain_scores_gemma":[0.9988157,0.0002763668,0.00005640784,0.0004170448,0.0003297869,0.0001047047],"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":[0.001637411,0.001220087,0.01323004,0.0009476462,0.0006123062,0.001580213,0.0004597696,0.06972762,0.02700114,0.002615433,0.3306118,0.5503565],"study_design_scores_gemma":[0.0005019226,0.000864752,0.03057822,0.0001899756,0.0002940835,0.001526485,0.0009295306,0.7505667,0.04984643,0.006598504,0.1577831,0.0003203112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5336342,0.00477338,0.1598915,0.002066897,0.002001122,0.001062302,0.2031387,0.07395191,0.01947998],"genre_scores_gemma":[0.3224247,0.0005447057,0.09888042,0.0004603234,0.0001776929,0.0009562802,0.5582886,0.001503107,0.01676415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01321012,"threshold_uncertainty_score":0.02626646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008051341541456172,"score_gpt":0.2394607650231359,"score_spread":0.2314094234816797,"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."}}