{"id":"W2074176370","doi":"10.1109/icassp.2013.6639312","title":"Comparison of a bigram PLSA and a novel context-based PLSA language model for speech recognition","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Bigram; Probabilistic latent semantic analysis; Perplexity; Computer science; Context (archaeology); Artificial intelligence; Language model; Natural language processing; Topic model; Context model; Speech recognition; Word (group theory); Latent semantic analysis; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001870259,0.0001160026,0.0002446735,0.0001340967,0.00005403416,0.00009967464,0.0002175333,0.00008101235,0.0000975693],"category_scores_gemma":[0.00009888979,0.0001034636,0.00007615462,0.0001413295,0.00004597789,0.0002866612,0.00004099443,0.00006375428,0.00004183266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001281445,"about_ca_system_score_gemma":0.00004321555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001912317,"about_ca_topic_score_gemma":0.0001474612,"domain_scores_codex":[0.9990764,0.00002215966,0.0002797452,0.0002709654,0.0001664364,0.0001842435],"domain_scores_gemma":[0.9990627,0.0002942348,0.0001104457,0.0002267799,0.000214587,0.00009128318],"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":[0.00001514327,0.0002806251,0.0001437693,0.00004796499,0.00001589747,4.00163e-7,0.000559694,0.00001306832,0.0199294,0.001491702,0.001273161,0.9762292],"study_design_scores_gemma":[0.0007798368,0.00008175409,0.0002011205,0.00003189737,0.000009373465,0.000003314128,0.0003346655,0.8773194,0.1188781,0.002170244,0.00005084214,0.0001394324],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2103727,0.00003070164,0.7874269,0.000593756,0.00003920048,0.0004340847,0.00002739403,0.0001027507,0.0009724768],"genre_scores_gemma":[0.6468731,0.00000124211,0.3523215,0.0005516351,0.00001069553,0.00007288221,0.000009727786,0.000006170109,0.000153075],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9760897,"threshold_uncertainty_score":0.4219122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08940868257063371,"score_gpt":0.319210289139827,"score_spread":0.2298016065691932,"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."}}