{"id":"W1603105762","doi":"10.1109/icassp.2015.7178988","title":"Document-specific context plsa language model for speech recognition","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Bigram; Perplexity; Computer science; Natural language processing; Artificial intelligence; Language model; Word error rate; Word (group theory); Context (archaeology); Speech recognition; Probabilistic latent semantic analysis; Context model; Probabilistic logic; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004181909,0.0001179893,0.0001390515,0.0001017348,0.00005816101,0.0001957831,0.0003665441,0.00006515172,0.0001926915],"category_scores_gemma":[0.00008431172,0.0001036103,0.00008394913,0.0001427365,0.00002031767,0.0005851086,0.00006336083,0.00005831139,0.0008927623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000548347,"about_ca_system_score_gemma":0.00005548233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002389874,"about_ca_topic_score_gemma":0.00004020076,"domain_scores_codex":[0.9989771,0.00003536247,0.0001980702,0.0003194844,0.000236728,0.000233208],"domain_scores_gemma":[0.9991371,0.0001070206,0.00005449978,0.0003207267,0.0002101362,0.0001705024],"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":[0.00001606866,0.00004078209,0.000002994156,0.000003777925,0.000008215231,0.000005954292,0.0007591281,0.000003517141,0.0003691543,0.006298114,0.03656261,0.9559297],"study_design_scores_gemma":[0.002953536,0.0001809164,0.00001442574,0.00003851181,0.00001571555,0.00007606411,0.002382466,0.695403,0.1340235,0.120517,0.04367307,0.0007217097],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01193639,0.0001217871,0.9544692,0.001239627,0.0003052953,0.0003403971,0.00001552597,0.0003245778,0.03124717],"genre_scores_gemma":[0.2600935,0.00002649636,0.7286832,0.002159167,0.000145953,0.0001025561,0.00003270095,0.00001795375,0.008738475],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9552079,"threshold_uncertainty_score":0.9998851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1046583248701937,"score_gpt":0.2911833286154523,"score_spread":0.1865250037452586,"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."}}