{"id":"W3083173864","doi":"10.1145/3414685.3417838","title":"Speech gesture generation from the trimodal context of text, audio, and speaker identity","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":304,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Gesture; Computer science; Context (archaeology); Speech recognition; Identity (music); Gesture recognition; Embedding; Artificial intelligence; Human–computer interaction; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001113825,0.0001053734,0.0001219521,0.00005400896,0.0002380723,0.0001076293,0.0003779838,0.00007924251,0.00006019362],"category_scores_gemma":[0.00002895455,0.00008392122,0.00008997693,0.0003844797,0.00007202724,0.0005721811,0.00001171936,0.0002621461,0.00002116853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008011839,"about_ca_system_score_gemma":0.00002699493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001322315,"about_ca_topic_score_gemma":0.0003836105,"domain_scores_codex":[0.9991348,0.00007858187,0.0001938761,0.0002593037,0.0002376591,0.000095716],"domain_scores_gemma":[0.9992775,0.0001389607,0.00007945963,0.0003543605,0.00008380925,0.00006596145],"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":[0.00016435,0.0007792162,0.001858873,0.00005775587,0.0006285093,0.00003464394,0.01301825,0.0003801332,0.0593201,0.0792077,0.01196798,0.8325825],"study_design_scores_gemma":[0.01105352,0.002614568,0.2072544,0.0002732846,0.001076615,0.0001401565,0.003093204,0.1274558,0.3758621,0.1758919,0.09241147,0.002872902],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.259746,0.0001430084,0.7240928,0.01537789,0.0002650264,0.0001747099,0.00005013846,0.00007450586,0.00007589295],"genre_scores_gemma":[0.9922714,0.0002735652,0.003161001,0.004125252,0.0001263572,0.000007199218,0.00001005908,0.000006694121,0.00001843813],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8297096,"threshold_uncertainty_score":0.3422208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0463744464987958,"score_gpt":0.253126340540515,"score_spread":0.2067518940417192,"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."}}