{"id":"W1906553149","doi":"10.1109/icpr.1998.711998","title":"HMM-KNN word recognition engine for bank cheque processing","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Hidden Markov model; Cheque; Classifier (UML); Phone; Word (group theory); Alphabet; Speech recognition; Artificial intelligence; Natural language processing; Segmentation; Modular design; Document processing; Scheme (mathematics); Set (abstract data type); Pattern recognition (psychology); Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001772026,0.0001058068,0.0001136481,0.0001096922,0.0001148187,0.0001762805,0.0002583064,0.00006053437,0.001094338],"category_scores_gemma":[0.0001119008,0.00009391883,0.00006970318,0.0002756983,0.00001468766,0.0005023019,0.00003025854,0.00005958545,0.0004555848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002513721,"about_ca_system_score_gemma":0.00001243305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002854332,"about_ca_topic_score_gemma":0.000005045362,"domain_scores_codex":[0.9991584,0.00001990152,0.0001740592,0.0002823739,0.000136323,0.000228909],"domain_scores_gemma":[0.9994534,0.0001103913,0.00005037943,0.0001786584,0.0001290541,0.0000781632],"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":[0.000001626684,0.00004594131,0.000003212853,0.00001569815,0.000004227283,0.00000183812,0.00009489239,4.443573e-7,0.000325884,0.0003337591,0.003196355,0.9959762],"study_design_scores_gemma":[0.00113831,0.0001214453,0.0002291538,0.0001313187,0.00002300146,0.00007868381,0.00008608872,0.8098478,0.1172974,0.01765482,0.05268069,0.0007112671],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002303272,0.00008098458,0.952935,0.003331608,0.0001925169,0.0002557222,0.000003721901,0.0004592631,0.04043794],"genre_scores_gemma":[0.2200653,0.0000483449,0.7707546,0.002539109,0.0002481047,0.0001565146,0.000009829904,0.00002033751,0.006157881],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9952648,"threshold_uncertainty_score":0.9998188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0708022711339814,"score_gpt":0.2450067791697904,"score_spread":0.1742045080358089,"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."}}