{"id":"W2106901945","doi":"10.1109/slt.2012.6424216","title":"Topic n-gram count language model adaptation for speech recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"n-gram; Gram; Latent Dirichlet allocation; Topic model; Cluster analysis; Word (group theory); Set (abstract data type); Computer science; Artificial intelligence; Test set; Adaptation (eye); Natural language processing; Language model; Speech recognition; Mathematics; Statistics","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":[0.0002742732,0.0000783835,0.00008170698,0.00006851739,0.00006474504,0.00006945803,0.0001615394,0.00005272009,0.0001294535],"category_scores_gemma":[0.000067876,0.00006954915,0.00005997816,0.0001013584,0.000008148116,0.0006781518,0.00002424518,0.00003803587,0.0002444825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003267885,"about_ca_system_score_gemma":0.00002231847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002295226,"about_ca_topic_score_gemma":0.00002152443,"domain_scores_codex":[0.9993271,0.00002104732,0.0001318212,0.0001509638,0.0001487326,0.0002203254],"domain_scores_gemma":[0.9995191,0.00009132633,0.00004108172,0.0001813828,0.00008771996,0.00007936633],"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":[0.000003370694,0.00006127328,0.00001967814,0.000007969106,0.000005760064,4.47197e-7,0.00068666,0.000007353341,0.000802868,0.006403304,0.001298015,0.9907033],"study_design_scores_gemma":[0.0004009589,0.00004112299,0.0002338078,0.00001243057,0.00001407077,0.00001820792,0.0004655921,0.9291231,0.05544453,0.01086584,0.003131823,0.0002485263],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03046972,0.00003901952,0.9536755,0.0003757378,0.0002508108,0.0002266512,0.000008208332,0.000203057,0.0147513],"genre_scores_gemma":[0.2988817,0.00000811373,0.6983525,0.0008459459,0.0001259113,0.00006143554,0.00002060608,0.000006517453,0.001697283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9904548,"threshold_uncertainty_score":0.314241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07775270899817129,"score_gpt":0.2867773065104716,"score_spread":0.2090245975123003,"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."}}