{"id":"W4407251405","doi":"10.2139/ssrn.5128348","title":"Fasttalker: An Unified Framework for Generating Speech and Conversational Gestures from Text","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Gesture; Computer science; Speech recognition; Linguistics; Communication; Natural language processing; Psychology; Artificial intelligence; Philosophy","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":[0.001577297,0.002742122,0.001978593,0.00184501,0.0009571056,0.003570553,0.004062543,0.002189895,0.03399615],"category_scores_gemma":[0.00438096,0.001714944,0.002054627,0.001081393,0.0008054785,0.003055548,0.00337852,0.002046378,0.01583986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006714087,"about_ca_system_score_gemma":0.001110773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004375235,"about_ca_topic_score_gemma":0.005632802,"domain_scores_codex":[0.9989342,0.0001842775,0.00008995591,0.0003285076,0.0003526534,0.0001105306],"domain_scores_gemma":[0.9988272,0.00054563,0.00006820729,0.000238354,0.0002285906,0.00009199711],"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":[0.001787425,0.0002017858,0.001259947,0.001528847,0.0003020218,0.0009038048,0.001433916,0.02794464,0.08041042,0.03482211,0.08702283,0.7623823],"study_design_scores_gemma":[0.000337043,0.0003125924,0.001580451,0.0002442545,0.0002259541,0.001036628,0.0003574005,0.6608251,0.1219285,0.05494073,0.1578576,0.0003537151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001113242,0.0001017434,0.9239188,0.00003078972,0.0000752187,0.0001464723,0.001554815,0.07199778,0.001061161],"genre_scores_gemma":[0.05309095,0.0003478003,0.9085312,0.0001630505,0.0001296975,0.000881483,0.009194097,0.018424,0.009237599],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03399615,"threshold_uncertainty_score":0.1137284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01667713250356856,"score_gpt":0.2719421316703564,"score_spread":0.2552649991667879,"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."}}