{"id":"W4410915170","doi":"10.1007/978-3-031-93806-1_14","title":"FastTalker: Jointly Generating Speech and Conversational Gestures from Text","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Gesture; Speech recognition; Natural language processing; Artificial intelligence; Speech synthesis; Human–computer interaction","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":[0.0007102438,0.002039945,0.001555417,0.0007456679,0.0005381392,0.00148178,0.00230275,0.001523625,0.0302456],"category_scores_gemma":[0.001656054,0.0009927966,0.001015858,0.0005622887,0.0004872158,0.001706674,0.002170843,0.0009198902,0.01090949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003713918,"about_ca_system_score_gemma":0.0004830827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002656442,"about_ca_topic_score_gemma":0.00365139,"domain_scores_codex":[0.9995745,0.00008333703,0.00001920895,0.0001389535,0.000143059,0.00004095283],"domain_scores_gemma":[0.9994414,0.0003581578,0.00001779101,0.00005829133,0.00008091816,0.00004342159],"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":[0.00109819,0.0001368596,0.000499726,0.0005964365,0.0001468849,0.0005306263,0.0004777081,0.01510338,0.1396241,0.004693408,0.04197502,0.7951176],"study_design_scores_gemma":[0.0005267191,0.0005836652,0.00258022,0.0001383974,0.0002194582,0.001280256,0.000458615,0.7082311,0.1903036,0.02358636,0.07188268,0.0002088674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01432222,0.0004789597,0.9066028,0.0001041983,0.0003841172,0.0003226573,0.00225668,0.06864022,0.006888163],"genre_scores_gemma":[0.1194794,0.0004572054,0.8332335,0.0002102337,0.0001767867,0.0008116461,0.007460363,0.009809185,0.02836169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0302456,"threshold_uncertainty_score":0.1011816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01321270625899922,"score_gpt":0.2262320359035712,"score_spread":0.2130193296445719,"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."}}