{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002497906,0.0002864683,0.0002955128,0.0001650086,0.000173062,0.0003654374,0.0007104265,0.0001406686,0.0001904335],"category_scores_gemma":[0.0001436208,0.0002539198,0.0001175436,0.0004364189,0.00007650792,0.001121796,0.00008676849,0.000182787,0.0009676347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008949454,"about_ca_system_score_gemma":0.0001280443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001454123,"about_ca_topic_score_gemma":0.0006291803,"domain_scores_codex":[0.9980394,0.00004470219,0.0003499357,0.0006365684,0.0004069437,0.0005224952],"domain_scores_gemma":[0.9982535,0.0001960095,0.0001851969,0.0007562973,0.0004073271,0.0002017121],"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":[0.00006071074,0.0001803292,0.00005957828,0.00008633344,0.00006011367,0.00003142468,0.001846705,0.00005376989,0.01166859,0.0006563459,0.003536133,0.98176],"study_design_scores_gemma":[0.002923153,0.0004942644,0.001225408,0.0003687587,0.00008217391,0.0001789312,0.0006284539,0.61633,0.3625212,0.0116449,0.001832621,0.001770098],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.211875,0.00008469402,0.7822483,0.0006077184,0.000160673,0.0009414662,0.00008488928,0.0004353549,0.003561891],"genre_scores_gemma":[0.6952581,0.00002535388,0.3010767,0.001139034,0.0001249331,0.0005813331,0.00008223754,0.00004133406,0.001670996],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9799899,"threshold_uncertainty_score":0.9999913,"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."}}