{"id":"W2144015346","doi":"10.5281/zenodo.43376","title":"Plsa Enhanced With A Long-Distance Bigram Language Model For Speech Recognition","year":2013,"lang":"en","type":"article","venue":"INFM-OAR (INFN Catania)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Perplexity; Bigram; Language model; Computer science; Probabilistic latent semantic analysis; Topic model; Natural language processing; Word error rate; Artificial intelligence; Speech recognition; Word (group theory); Hidden Markov model; Event (particle physics); Trigram; Linguistics","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":[0.001089799,0.001239295,0.0009922624,0.0009590192,0.0006961823,0.001353853,0.001225681,0.00114276,0.01730035],"category_scores_gemma":[0.002212707,0.0006332371,0.001354449,0.001041416,0.0002639279,0.002014637,0.001351879,0.002403984,0.01946271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003708937,"about_ca_system_score_gemma":0.001267138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005442606,"about_ca_topic_score_gemma":0.009763727,"domain_scores_codex":[0.9992924,0.0002707489,0.00006259198,0.0001671533,0.0001360879,0.00007114455],"domain_scores_gemma":[0.9986596,0.0005574587,0.00003496456,0.0002266288,0.0004582701,0.00006301072],"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":[0.001366466,0.0003680346,0.000759733,0.0003284063,0.000277584,0.0003235563,0.0001273393,0.03534425,0.07772186,0.004383154,0.01486716,0.8641325],"study_design_scores_gemma":[0.00006720103,0.000239661,0.0007816014,0.00003146709,0.0001111512,0.000187809,0.00007439186,0.9427828,0.04171956,0.00338973,0.01056084,0.00005387785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01914938,0.001383394,0.9539261,0.0003316485,0.0005972594,0.00009380929,0.001656599,0.01992926,0.002932522],"genre_scores_gemma":[0.2550547,0.001121296,0.7112362,0.0004973346,0.0003680015,0.0004667726,0.008863678,0.002771444,0.01962058],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01730035,"threshold_uncertainty_score":0.05787539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02486412488034375,"score_gpt":0.2465660002903537,"score_spread":0.22170187541001,"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."}}