{"id":"W4385422383","doi":"10.31234/osf.io/h9mna","title":"Leveraging Natural Language Processing Models to Automate Speech-Intelligibility Scoring","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Noise Effects and Management","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Intelligibility (philosophy); Active listening; Computer science; Speech recognition; Speech perception; Perception; Natural language processing; Artificial intelligence; Audiology; Psychology; Communication; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004257746,0.001481423,0.0006292348,0.001548649,0.0003508219,0.002470148,0.001108611,0.0007613146,0.004205735],"category_scores_gemma":[0.01606642,0.0004550065,0.001219681,0.0005031562,0.0005590988,0.003022016,0.001411984,0.00129826,0.004496871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007945558,"about_ca_system_score_gemma":0.001024444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005296446,"about_ca_topic_score_gemma":0.009453509,"domain_scores_codex":[0.9978636,0.0006996019,0.0002015632,0.0005534834,0.0006148288,0.00006697013],"domain_scores_gemma":[0.9931345,0.004217809,0.0004268929,0.0005638683,0.001556603,0.0001003455],"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":[0.0006835003,0.0004176705,0.01747287,0.001521034,0.0004904625,0.0004998943,0.001638871,0.06161954,0.08976282,0.005773905,0.01293684,0.8071826],"study_design_scores_gemma":[0.00005926743,0.0003552053,0.01677863,0.0001952062,0.0001589519,0.0006180669,0.0003604661,0.9091025,0.04196741,0.01496238,0.01525908,0.0001827987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06911025,0.0005757998,0.9024179,0.0003736275,0.0002077707,0.0008175707,0.002141932,0.01904303,0.005312021],"genre_scores_gemma":[0.4038416,0.000720917,0.5844,0.0003566811,0.00009015945,0.001340555,0.004553302,0.001383292,0.003313439],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005296446,"threshold_uncertainty_score":0.02251732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1695954069559005,"score_gpt":0.4634092932595349,"score_spread":0.2938138863036345,"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."}}