flow matching

NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speecharxiv.org

NVAlign introduces a post‑training direct‑gradient framework that uses an NV‑aware ASR model as a reward to improve non‑verbal vocalization tag following in continuous autoregressive flow‑matching TTS. Experiments on NVV‑SuperBench and human listening show higher tag‑following accuracy than fine‑tuning and Flow‑GRPO baselines.