Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed Attention and Knowledge Distillation, a framework that adapts pretrained AR-TTS models to operate with constant computational and memory complexity. WAND separates the attention mechanism into two: persistent global attention over conditioning tokens and local sliding-window attention over generated tokens. To stabilize fine-tuning, we employ a curriculum learning strategy that progressively tightens the attention window. We further utilize knowledge distillation from a full-attention teacher to recover high-fidelity synthesis quality with high data efficiency. Evaluated on three modern AR-TTS models, WAND preserves the original quality while achieving up to 66.2% KV cache memory reduction and length-invariant, near-constant per-step latency.
@article{arxiv.2604.08558,
title = {WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models},
author = {Hanna Lee and Tan Dat Nguyen and Jaehoon Kang and Kyuhong Shim},
journal= {arXiv preprint arXiv:2604.08558},
year = {2026}
}