{"id":"W2157951638","doi":"10.1007/s10278-007-9034-7","title":"Improving the Utility of Speech Recognition Through Error Detection","year":2007,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Centers for Disease Control and Prevention; Simon Fraser University","keywords":"Proofreading; Word error rate; Computer science; Speech recognition; Transcription (linguistics); Error detection and correction; Vendor; Artificial intelligence; Algorithm","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":[0.0008328806,0.00007775578,0.0001156805,0.00009424222,0.00005905844,0.0002486173,0.0004699028,0.00002453628,0.000003296452],"category_scores_gemma":[0.0003231249,0.00005130328,0.00009365974,0.0002948604,0.00005876278,0.003690427,0.0001156953,0.0002546406,0.000002028738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003754701,"about_ca_system_score_gemma":0.00003667616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001542136,"about_ca_topic_score_gemma":0.000002324515,"domain_scores_codex":[0.9990347,0.0000183869,0.0004057723,0.0001025139,0.0002874379,0.000151216],"domain_scores_gemma":[0.9987502,0.0001107825,0.0005738663,0.0001684848,0.0003668228,0.00002983943],"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":[0.0000131001,0.00001816516,0.0003285525,0.00001590587,0.000005297747,0.00002390185,0.0002566658,1.146217e-7,0.01855064,0.00002172733,0.00003846369,0.9807275],"study_design_scores_gemma":[0.0001866573,0.00007529524,0.0005386802,0.0001244524,0.0000124899,0.001171714,0.0001875716,0.005304318,0.9324858,0.05957842,0.0002172869,0.0001173623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05173198,0.0007016297,0.9457168,0.0003343647,0.0002226825,0.00005402246,0.000001032958,0.00004617061,0.001191342],"genre_scores_gemma":[0.8198062,0.000001967021,0.1800228,0.00006180874,0.00009509236,1.374281e-7,1.957127e-7,0.000004429606,0.000007383042],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9806101,"threshold_uncertainty_score":0.2675471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02334823377339283,"score_gpt":0.2892260673313842,"score_spread":0.2658778335579913,"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."}}