{"id":"W2532585045","doi":"10.1109/nlpke.2003.1275932","title":"Performance improvement of automatic speech recognition systems via multiple language models produced by sentence-based clustering","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Vocabulary; Artificial intelligence; Speech recognition; Language model; Sentence; Natural language processing; Grammar; Self-organizing map","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":[0.002248014,0.001032573,0.001126745,0.0007689173,0.0005501332,0.0009669537,0.0009122334,0.0009837989,0.002046018],"category_scores_gemma":[0.00441747,0.0005268842,0.0007983628,0.0006059905,0.0003139162,0.001313903,0.0008733232,0.0007080302,0.002107598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006049299,"about_ca_system_score_gemma":0.0005842441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00479579,"about_ca_topic_score_gemma":0.004091033,"domain_scores_codex":[0.998467,0.0005493197,0.0001241984,0.0004201298,0.0003349867,0.0001044115],"domain_scores_gemma":[0.997412,0.001448489,0.00008292787,0.0002957698,0.0006857541,0.00007519143],"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":[0.002617733,0.0002908035,0.003010361,0.0002779453,0.0003668464,0.0002672602,0.0004792422,0.203198,0.1655718,0.00133802,0.003443174,0.6191387],"study_design_scores_gemma":[0.00003901968,0.0001723967,0.001257916,0.000006931399,0.00005369158,0.0001006331,0.00007624434,0.9437629,0.05333148,0.00059775,0.0005586207,0.00004241876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3718124,0.0005742086,0.6038728,0.0003034578,0.000157259,0.0001353006,0.0003186296,0.02026267,0.002563262],"genre_scores_gemma":[0.6898453,0.0001558809,0.3054895,0.0001025787,0.00004510411,0.0001410743,0.001132664,0.0006250371,0.002462931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00479579,"threshold_uncertainty_score":0.0118888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02378218736327504,"score_gpt":0.2199273004085662,"score_spread":0.1961451130452912,"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."}}