{"id":"W3106864934","doi":"10.1109/taslp.2020.3039929","title":"Speech Intelligibility Prediction Using Spectro-Temporal Modulation Analysis","year":2020,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Hearing Loss and Rehabilitation","field":"Neuroscience","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Institute on Deafness and Other Communication Disorders; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Speech recognition; Computer science; Intelligibility (philosophy); Reverberation; Speech perception; Active listening; Speech processing; Auditory scene analysis; Perception; Robustness (evolution); Acoustics; Psychology; Communication","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":[0.0002625422,0.0002176584,0.0002880298,0.0002810983,0.000436887,0.0001855913,0.0001471734,0.0001240602,0.0001161406],"category_scores_gemma":[0.0002352945,0.0002017246,0.0001524602,0.001423803,0.0001220242,0.0004769576,0.000006580378,0.0003621378,0.00001291324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001081051,"about_ca_system_score_gemma":0.00006854955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000163419,"about_ca_topic_score_gemma":0.0000296355,"domain_scores_codex":[0.9980955,0.000131072,0.0003921205,0.0007181852,0.0003747377,0.0002883642],"domain_scores_gemma":[0.9992048,0.0001181909,0.0001291432,0.0002894959,0.00006194248,0.0001964445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001243646,0.000145798,0.001837025,0.0001748514,0.00003963256,0.00002496307,0.004600214,0.01393802,0.704755,0.000003839371,0.000002776217,0.2743535],"study_design_scores_gemma":[0.0005197044,0.0002530322,0.00907314,0.00007674807,0.0003115834,0.00004196608,0.001111376,0.4867379,0.5011913,0.0002761458,0.00004486165,0.0003622628],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.679581,0.00006553654,0.3193342,0.0004361988,0.000086235,0.0002050069,0.00002744359,0.0001826201,0.0000816928],"genre_scores_gemma":[0.9844324,0.00002104097,0.0149541,0.0003474217,0.0001453999,0.000007649362,0.000006995645,0.00002461349,0.00006040145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4727999,"threshold_uncertainty_score":0.8226089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04441023226516962,"score_gpt":0.3101454051016216,"score_spread":0.265735172836452,"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."}}