{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001556383,0.001320623,0.001236997,0.0009995946,0.0004617313,0.0009136599,0.001716907,0.0008209192,0.0027208],"category_scores_gemma":[0.005269511,0.0005006257,0.001153193,0.001375358,0.000421008,0.001856256,0.001310587,0.002326277,0.003376155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007130828,"about_ca_system_score_gemma":0.0008137801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004240735,"about_ca_topic_score_gemma":0.007471219,"domain_scores_codex":[0.9985239,0.0006280016,0.00008192634,0.0003865309,0.0003087248,0.00007087566],"domain_scores_gemma":[0.9982692,0.0008580282,0.00009022024,0.0003853542,0.0003350273,0.0000622416],"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":[0.000486811,0.0003390005,0.002308778,0.0002301656,0.0003863894,0.0001997752,0.0003551549,0.214783,0.03899468,0.01051915,0.01205458,0.7193425],"study_design_scores_gemma":[0.00001303761,0.00003435442,0.00054045,0.000008208836,0.00002358889,0.00005999477,0.0000231727,0.9818534,0.008332991,0.004519938,0.004558419,0.00003237922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008792207,0.0003862177,0.9849337,0.0001012206,0.0001368436,0.00005928152,0.0002052273,0.004435525,0.0009498912],"genre_scores_gemma":[0.2389258,0.000889677,0.7455238,0.0003384782,0.0003349321,0.0007145143,0.002740368,0.002164011,0.008368481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004240735,"threshold_uncertainty_score":0.009101987,"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."}}