{"id":"W3205904637","doi":"10.1145/3474085.3475318","title":"Towards Realistic Visual Dubbing with Heterogeneous Sources","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Leverage (statistics); Speech recognition; Task (project management); Fidelity; Artificial intelligence; Flexibility (engineering); Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001422011,0.00142909,0.001034685,0.0005996056,0.0003134628,0.0009975187,0.001586463,0.001175288,0.002103639],"category_scores_gemma":[0.005163223,0.0007150716,0.0007917843,0.0004933573,0.0007900884,0.001624352,0.002839604,0.001615944,0.001058811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003866714,"about_ca_system_score_gemma":0.0005271962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001430608,"about_ca_topic_score_gemma":0.002196638,"domain_scores_codex":[0.9990658,0.0003336771,0.00003469803,0.0002823701,0.0001995681,0.00008388852],"domain_scores_gemma":[0.998024,0.001065447,0.0001365815,0.0004748699,0.0002069757,0.00009210233],"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":[0.0008241912,0.0002901733,0.001504268,0.000461895,0.0001648043,0.0005610032,0.0005885068,0.4162604,0.09604663,0.01208999,0.006560596,0.4646476],"study_design_scores_gemma":[0.00002058601,0.00008571053,0.0003312301,0.00001859103,0.00001520525,0.0001160687,0.00006302834,0.9720701,0.01808822,0.007118166,0.00205749,0.00001574777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02097246,0.0002522378,0.9764756,0.00009154811,0.00003252481,0.0000534513,0.0001366301,0.001018268,0.0009672917],"genre_scores_gemma":[0.5811929,0.000390498,0.4079807,0.0003842595,0.0001223534,0.0002592096,0.002014634,0.0005966234,0.007058853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002103639,"threshold_uncertainty_score":0.007520437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01769955542518053,"score_gpt":0.264486470105342,"score_spread":0.2467869146801615,"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."}}