{"id":"W1546453457","doi":"10.1109/icassp.2000.862072","title":"French large vocabulary recognition with cross-word phonology transducers","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Word error rate; Speech recognition; Vocabulary; Pronunciation; Word (group theory); Dictation; Context (archaeology); Language model; Artificial intelligence; Hidden Markov model; Natural language processing; Task (project management); Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001314407,0.0001338803,0.0001235869,0.0001107204,0.0001137962,0.0001552239,0.0005929344,0.0001095932,0.0005047651],"category_scores_gemma":[0.00001720155,0.0001003784,0.00003435657,0.0003926473,0.00006169784,0.0006946179,0.00006384498,0.0002126123,0.0001321889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003033899,"about_ca_system_score_gemma":0.00001649961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006144317,"about_ca_topic_score_gemma":0.00006322161,"domain_scores_codex":[0.9989553,0.00003437171,0.0001436126,0.0003788741,0.0001675377,0.0003203158],"domain_scores_gemma":[0.9994112,0.00003151099,0.00005040633,0.0003544198,0.00009323685,0.00005917336],"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":[0.00001933698,0.0003646075,0.002933759,0.00006845479,0.0000557307,0.0003053671,0.003139392,0.000002669354,0.004025598,0.01368511,0.01053562,0.9648644],"study_design_scores_gemma":[0.008039755,0.002726045,0.01017663,0.0005042803,0.0001003007,0.002383794,0.0001337565,0.09275592,0.5839266,0.2479457,0.04637222,0.004935011],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02945755,0.001519783,0.9582593,0.001301591,0.0001344809,0.0001614054,0.000003611871,0.001745578,0.007416688],"genre_scores_gemma":[0.5653462,0.00001863657,0.4329726,0.000770036,0.00002851192,0.00001453905,0.000004311202,0.000006933789,0.0008382046],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9599293,"threshold_uncertainty_score":0.5526824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174505513817706,"score_gpt":0.2516273653355634,"score_spread":0.2341768139537928,"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."}}