DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis
Continuous-latent Autoregressive Diffusion Transformer (AR-DiT) models have demonstrated immense potential in zero-shot speech generation. However, they still suffer from limited decoding stability when synthesizing long utterances or complex linguistic structures. This instability primarily stems from a restricted his...
Zi-Yu Zhang, Tian-Lun Zuo, Han-Zhao Li et al.
· 0 citations