{"id":"W2137587425","doi":"10.1109/asru.2001.1034628","title":"Out-of-vocabulary word modeling using multiple lexical fillers","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Vocabulary; Word error rate; Computer science; Word (group theory); Natural language processing; Task (project management); Speech recognition; Artificial intelligence; Linguistics; Engineering","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":[0.0006890266,0.0009176426,0.0008017558,0.0009524585,0.0005036382,0.0007359939,0.001170125,0.0008458485,0.001921381],"category_scores_gemma":[0.003265779,0.0005491616,0.001026971,0.0007179302,0.0005885619,0.002150095,0.0006885572,0.001026063,0.001337438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003571082,"about_ca_system_score_gemma":0.0007039359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00553569,"about_ca_topic_score_gemma":0.008794114,"domain_scores_codex":[0.9994326,0.0001852051,0.00004351299,0.0001878753,0.0001135597,0.00003729964],"domain_scores_gemma":[0.9982272,0.001051846,0.00009546501,0.0003329058,0.0002481472,0.00004453411],"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":[0.0007446318,0.000367718,0.003004299,0.0003226366,0.0001850247,0.000697232,0.0006468131,0.282584,0.09284187,0.01286497,0.004309477,0.6014313],"study_design_scores_gemma":[0.00001576991,0.00008766768,0.0004922284,0.000008969878,0.0000325432,0.0001352712,0.00004386347,0.9734341,0.01592669,0.007979326,0.001816451,0.00002720258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06386911,0.0002990898,0.9308087,0.0000810797,0.00007989876,0.00007577067,0.0002077557,0.003560073,0.00101861],"genre_scores_gemma":[0.5749273,0.0003141687,0.4178804,0.0001360862,0.00006800085,0.0002591171,0.001549389,0.0009576619,0.003907863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00553569,"threshold_uncertainty_score":0.01100695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09530444043216925,"score_gpt":0.2876895838683309,"score_spread":0.1923851434361617,"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."}}