{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007874299,0.0005485009,0.0005154683,0.0004277588,0.0002689591,0.0007834947,0.001040524,0.0006388401,0.001948297],"category_scores_gemma":[0.001352207,0.0003431761,0.0006308029,0.0002782577,0.0002627113,0.001145422,0.0006215655,0.0009962232,0.001853508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000432012,"about_ca_system_score_gemma":0.0007489649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004717097,"about_ca_topic_score_gemma":0.006723317,"domain_scores_codex":[0.9996701,0.00009134342,0.00002414402,0.0001021295,0.00008033201,0.0000319309],"domain_scores_gemma":[0.9994428,0.0003078882,0.00003100451,0.00003880675,0.0001556462,0.000024003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004339601,0.0002493543,0.002139742,0.0001895945,0.0002081154,0.0002370609,0.0002940831,0.4607081,0.06644357,0.01277034,0.003427646,0.4528983],"study_design_scores_gemma":[0.000008023841,0.00004413601,0.0001373136,0.000003549031,0.00001585165,0.00003073032,0.00001598606,0.9946794,0.003208207,0.001130978,0.0007166842,0.000009155243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02099178,0.0001584948,0.975872,0.0001191102,0.00005415717,0.00005174134,0.0001167569,0.001644742,0.0009912149],"genre_scores_gemma":[0.5212131,0.0003458252,0.4691742,0.0002294223,0.0001095529,0.0004152816,0.0008413098,0.0004349719,0.007236443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004717097,"threshold_uncertainty_score":0.009379327,"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."}}