{"id":"W2023289124","doi":"10.1109/isspa.2012.6310464","title":"Developing a hybrid language model for open vocabulary automatic speech recognition in a lecture speech task","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Vocabulary; Task (project management); Lexicon; Speech recognition; Natural language processing; Artificial intelligence; Language model; Word (group theory); Domain (mathematical 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":[0.0008924822,0.0001936842,0.0002685599,0.0002456351,0.00009771503,0.0002792591,0.0008634846,0.00008254289,0.0001533879],"category_scores_gemma":[0.0002239828,0.000173964,0.00007849151,0.0003787934,0.0000149549,0.001360915,0.0003029064,0.0001243672,0.0002301881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001355436,"about_ca_system_score_gemma":0.0001563748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008543381,"about_ca_topic_score_gemma":0.0001483269,"domain_scores_codex":[0.9984828,0.00008351108,0.0003380741,0.0003686807,0.0002175817,0.0005093569],"domain_scores_gemma":[0.9991529,0.0001914028,0.00008958773,0.0003625575,0.00007928536,0.0001242574],"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":[0.000007405428,0.00009959449,0.00008235532,0.00004197587,0.00001473073,0.00001886655,0.0008957534,0.000004499775,0.0006234887,0.000642343,0.001160262,0.9964087],"study_design_scores_gemma":[0.0008078978,0.0000271436,0.0003153046,0.0001356882,0.00001317815,0.0002329572,0.0001517066,0.8896862,0.08827166,0.01951724,0.0003620375,0.0004790439],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09774013,0.00009000599,0.8955966,0.001078575,0.0001693264,0.0009231719,0.00001440424,0.0002379558,0.004149819],"genre_scores_gemma":[0.2134123,0.000007742657,0.7838337,0.00209748,0.00006021653,0.0001560087,0.00003042172,0.00001809492,0.00038405],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9959297,"threshold_uncertainty_score":0.7094048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06461673165344403,"score_gpt":0.3074663054317703,"score_spread":0.2428495737783262,"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."}}