---
id: 20260805-T0-10
title: "DLLM-TTS：新的离散扩散语言模型，实现更快更高效的语音合成"
title_en: "DLLM-TTS: Block Discrete Diffusion Model Speeds Up High-Quality Speech Synthesis"
url: https://ai.daily.yangsir.net/daily/20260805-T0-10
issue_date: 2026-08-05
publish_date: 2026-08-04T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2608.00011
---

# DLLM-TTS：新的离散扩散语言模型，实现更快更高效的语音合成

一篇新论文提出了DLLM-TTS，一种基于块离散扩散语言模型的语音合成系统。现有系统在质量与速度间面临取舍：自回归模型音质高但速度慢且依赖大规模数据；非自回归模型速度快但质量不足。DLLM-TTS试图兼顾两者，通过创新的块级离散扩散方法提升合成速度，同时保持高清晰度，为实时或低延迟语音应用提供了新可能。

## English Version

**DLLM-TTS: Block Discrete Diffusion Model Speeds Up High-Quality Speech Synthesis**

A new paper introduces DLLM-TTS, a text-to-speech system based on a block discrete diffusion language model. Current systems face a trade-off between quality and speed: autoregressive models offer high intelligibility but are slow and data-hungry, while non-autoregressive models are fast but sacrifice quality. DLLM-TTS aims to get the best of both worlds, using a novel block-level discrete diffusion approach to increase synthesis speed while maintaining high fidelity, offering new possibilities for real-time or low-latency speech applications.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2608.00011)

**详情页**：https://ai.daily.yangsir.net/daily/20260805-T0-10

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*