SOURCE-LINKED INTELLIGENCE

DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

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 historical receptive field and an acoustic inertia dependency within the diffusion decoder, which causes the model to ignore semantic conditions. To address these challenges, we propose DiTAR+, a dual-optimization framework. First, we introduce Dilated Context Sampling to expand the

Read original source ↗ Open in workspace

recordType

paper

region

Global