Preprint
Sep 2026
Taming Long-form Text-to-Speech
Localized Attention-Constrained Inference (LACI), an inference-only method to detect TTS errors in near real-time, roll back to the error onset and regenerate with temporary guardrails, adding negligible computational overhead to demonstrate the efficacy of LACI on voice cloning reliability.
Rong-Xiang Wang, Berkin Durmus, Aysegul Orhon et al.
· 0 citations