{"id":"W4388878632","doi":"10.1007/978-3-031-48312-7_6","title":"Improvements in Language Modeling, Voice Activity Detection, and Lexicon in OpenASR21 Low Resource Languages","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Lexicon; Word error rate; Artificial intelligence; Natural language processing; Vocabulary; Speech recognition; Phone; Resource (disambiguation); 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":[0.002179198,0.001438992,0.001304597,0.001406812,0.0007869978,0.003466671,0.003309246,0.0008272838,0.01829352],"category_scores_gemma":[0.006598836,0.00107358,0.002063069,0.001162759,0.0007419123,0.007089132,0.002547617,0.002290032,0.01551669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001049432,"about_ca_system_score_gemma":0.001784936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00668304,"about_ca_topic_score_gemma":0.01174608,"domain_scores_codex":[0.9965842,0.0008848679,0.000426389,0.0008534951,0.001011265,0.0002397523],"domain_scores_gemma":[0.9950275,0.001745329,0.0001991766,0.001608205,0.00131867,0.0001011528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008010167,0.0003802117,0.003150269,0.000611975,0.0001554175,0.0003700116,0.0006863204,0.02925709,0.08236356,0.0530003,0.03090466,0.7983191],"study_design_scores_gemma":[0.0001537323,0.0003678704,0.001937002,0.0001158369,0.0002918988,0.0007968863,0.0003501949,0.6795689,0.1279314,0.05611392,0.1321193,0.0002530495],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02946377,0.0004847472,0.8693701,0.0005991597,0.0003425673,0.0001561807,0.003241997,0.08295804,0.01338346],"genre_scores_gemma":[0.2458035,0.0003827384,0.7045876,0.0005873881,0.0002927872,0.0002989884,0.01537426,0.01344871,0.01922411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01829352,"threshold_uncertainty_score":0.06119794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01335129227571051,"score_gpt":0.2744599242455162,"score_spread":0.2611086319698057,"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."}}