{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005601904,0.0004786123,0.000521465,0.0006178836,0.0002866276,0.0009001079,0.001779938,0.0003401044,0.00002538244],"category_scores_gemma":[0.0001577288,0.0004397398,0.00009739642,0.0003708071,0.0004781008,0.0004643794,0.001273122,0.0005915884,0.00003558613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001798616,"about_ca_system_score_gemma":0.0007042928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002648848,"about_ca_topic_score_gemma":0.0002296931,"domain_scores_codex":[0.9965044,0.00004455508,0.0005075124,0.001574356,0.0008761705,0.0004929558],"domain_scores_gemma":[0.9976963,0.0007269541,0.0002451096,0.000944698,0.0002110087,0.0001759419],"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":[0.000008149146,0.00002001203,0.0004072472,0.00004948073,0.00003561037,0.0001576978,0.001112638,0.004028332,0.001045118,0.02705791,0.00059922,0.9654786],"study_design_scores_gemma":[0.0008127139,0.0001726713,0.001047788,0.0008558897,0.00002012385,0.0001397958,0.000001105858,0.7576699,0.004868921,0.2276314,0.005467815,0.001311907],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000443275,0.001249034,0.9883008,0.0008918829,0.002752295,0.0003323581,0.00002447679,0.0001393797,0.005866492],"genre_scores_gemma":[0.09620629,0.0000584318,0.8969403,0.003839049,0.001668333,0.00001148337,0.00003962279,0.00002997714,0.0012065],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9641667,"threshold_uncertainty_score":0.9998055,"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."}}