{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000312092,0.0004713788,0.0002024073,0.0003215855,0.000113651,0.0004072531,0.000276585,0.0003249571,0.003347678],"category_scores_gemma":[0.001635281,0.0001293201,0.0002235485,0.0001507162,0.0002461364,0.0004750279,0.000439867,0.0003738428,0.0005691994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008682053,"about_ca_system_score_gemma":0.0001297799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002348436,"about_ca_topic_score_gemma":0.0003563656,"domain_scores_codex":[0.999858,0.00002959382,0.00001659018,0.00003206031,0.00004811542,0.00001559309],"domain_scores_gemma":[0.9993966,0.0002974033,0.00005322814,0.00007984922,0.0001315186,0.00004143653],"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":[0.000316948,0.00009190913,0.0004758523,0.0002129709,0.000011862,0.0001483763,0.0001023173,0.002112463,0.9423221,0.0004805354,0.0002976856,0.05342697],"study_design_scores_gemma":[0.00004966223,0.001111962,0.007865658,0.00003107048,0.0000511606,0.000544506,0.0001041044,0.02828211,0.9574602,0.0003678168,0.004098875,0.00003297732],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6876065,0.0006375097,0.30463,0.0001362415,0.0001645433,0.0003011719,0.0005445897,0.001512795,0.00446693],"genre_scores_gemma":[0.8086301,0.0004798068,0.1865517,0.0001196158,0.0000486987,0.0002438465,0.0004922712,0.0002604411,0.003173502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003347678,"threshold_uncertainty_score":0.01119906,"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."}}