{"id":"W4393147067","doi":"10.1609/aaai.v38i16.29747","title":"UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Context (archaeology); Computer science; Linguistics; Psychology; Speech recognition; Natural language processing; Biology; Paleontology","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":[0.000526918,0.0003046528,0.0003395642,0.0002722133,0.0002531993,0.0008168356,0.001444326,0.0001486765,0.0001173493],"category_scores_gemma":[0.0005317345,0.0002061075,0.00009362605,0.001121574,0.0003222753,0.0004477258,0.0004574464,0.0004737813,0.0001689086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005390786,"about_ca_system_score_gemma":0.0001258435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003815036,"about_ca_topic_score_gemma":0.00003505336,"domain_scores_codex":[0.9977708,0.0000285796,0.0004893464,0.0007689729,0.0005587109,0.0003835601],"domain_scores_gemma":[0.9982868,0.000448619,0.0001652128,0.0003442533,0.0005564708,0.0001986599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007033168,0.0000512528,0.00006538776,0.00004210929,0.00001983655,0.000003938871,0.001368468,7.873173e-7,0.006165853,0.5994475,0.0001104918,0.392654],"study_design_scores_gemma":[0.00009685914,0.0007895549,0.0002399521,0.004976886,0.00005810654,0.0001035478,0.005844194,0.09282404,0.6740576,0.2174419,0.002706679,0.0008606582],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5645785,0.0003017414,0.3666732,0.04289483,0.001150185,0.002202727,0.0000338077,0.0009758578,0.02118911],"genre_scores_gemma":[0.9887695,0.00007832235,0.009905331,0.0007757467,0.00006332347,0.00004552826,3.951932e-7,0.00002171396,0.0003400943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6678917,"threshold_uncertainty_score":0.8404821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06781807521491127,"score_gpt":0.2937481810081966,"score_spread":0.2259301057932853,"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."}}