{"id":"W4318350603","doi":"10.1007/s10772-023-10018-z","title":"Plain-to-clear speech video conversion for enhanced intelligibility","year":2023,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Simon Fraser University","keywords":"Computer science; Intelligibility (philosophy); Speech recognition; Image warping; Perception; Artificial intelligence; Psychology","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":[0.0007953327,0.0001475728,0.0002635168,0.001380326,0.00008301856,0.0001295386,0.002452308,0.0001644591,0.00003075909],"category_scores_gemma":[0.001073389,0.0001362628,0.0001453247,0.001015601,0.00008439102,0.0004707624,0.0004839892,0.0003152281,0.0002162524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001868041,"about_ca_system_score_gemma":0.0001451774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003745694,"about_ca_topic_score_gemma":0.000004239607,"domain_scores_codex":[0.9982079,0.00001845902,0.0005590857,0.0003309869,0.0005562542,0.0003273475],"domain_scores_gemma":[0.9978582,0.0002001837,0.0003706813,0.0002991488,0.001166495,0.0001053289],"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":[0.0002075062,0.00007182764,0.0004942792,0.00001793613,0.0001108308,0.0002947275,0.0002253805,0.00008585022,0.2050649,0.003853953,0.005778504,0.7837943],"study_design_scores_gemma":[0.0006242272,0.0003638425,0.0001409444,0.00009390997,0.000005574655,0.0003698582,0.0001422104,0.0006171866,0.9238337,0.04009324,0.03357654,0.0001387922],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5341864,0.00006816676,0.4323524,0.03021704,0.002298436,0.0001942858,0.000006658061,0.0003185687,0.0003580385],"genre_scores_gemma":[0.7956652,0.00007413237,0.2028391,0.0006891958,0.0003644809,0.000006970185,0.000002618371,0.00001575364,0.000342549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7836555,"threshold_uncertainty_score":0.5556637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01663494020198911,"score_gpt":0.3090252094865346,"score_spread":0.2923902692845454,"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."}}