{"id":"W2795552730","doi":"10.1177/0023830918765012","title":"Investigating Perceptual Biases, Data Reliability, and Data Discovery in a Methodology for Collecting Speech Errors From Audio Recordings","year":2018,"lang":"en","type":"article","venue":"Language and Speech","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Speech recognition; Reliability (semiconductor); Perception; Sound quality; Sound recording and reproduction; Natural language processing; Psychology; Acoustics","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":[0.002436739,0.0001802132,0.0003538972,0.0001490064,0.0001984815,0.0003161505,0.001237152,0.0001248629,0.00005595182],"category_scores_gemma":[0.007619148,0.0001640715,0.00002351895,0.0003743284,0.0002039128,0.001220209,0.002004089,0.0001837602,0.000006577912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002659244,"about_ca_system_score_gemma":0.00007918967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005035441,"about_ca_topic_score_gemma":0.00626263,"domain_scores_codex":[0.997686,0.0003122604,0.0003520216,0.001153797,0.000166691,0.0003291775],"domain_scores_gemma":[0.9955074,0.002724677,0.0001201801,0.001485408,0.00005274311,0.0001096303],"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":[0.00004205571,0.00007159427,0.01444813,0.00005476242,0.00004341694,0.00008258803,0.0118324,1.985344e-7,0.01408181,0.0001562953,0.005245151,0.9539416],"study_design_scores_gemma":[0.009100369,0.001506827,0.05457206,0.001831499,0.0004102481,0.001340872,0.08015806,0.6693115,0.1118244,0.04749897,0.01816126,0.004283883],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9678424,0.0002413905,0.02959712,0.00090534,0.000244365,0.0003036926,0.0003455846,0.00008276013,0.0004373436],"genre_scores_gemma":[0.1595512,0.00005211399,0.838592,0.0008772921,0.0003398721,0.000009929631,0.0002638745,0.00001809595,0.0002956548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9496577,"threshold_uncertainty_score":0.9121382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.231578198380963,"score_gpt":0.3871973809097454,"score_spread":0.1556191825287824,"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."}}