English(EN) DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis

DiTAR+ 框架增强自回归扩散语音合成稳定性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了 DiTAR+，一个双重优化框架，以提高自回归扩散语音合成模型的稳定性和准确性。该框架通过引入扩张上下文采样（Dilated Context Sampling）来扩展模型的感受野，并通过分层声学掩码（Hierarchical Acoustic Masking）来更好地将语义对齐与声学重建解耦，从而解决了长语音中的发音错误和语义幻觉等问题。实验表明，DiTAR+ 显著降低了词错误率并提高了说话人相似度，在具有挑战性的语言任务和扩展音频生成方面优于现有基线。 AI

影响提高了 AI 驱动的语音合成的鲁棒性和准确性，尤其是在处理长而复杂的语音时。

排序理由这是一篇详细介绍语音合成新技术框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍语音合成新技术框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Ziyu Zhang, Tianlun Zuo, Hanzhao Li, Haoyu Zhang, Lei Xie · 2026-09-15 04:00

DiTAR+: 鲁棒自回归扩散语音合成的双重优化

arXiv:2609.13909v1 Announce Type: cross Abstract: 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 utterance…

本文如何被排名

报道来源 [1]

DiTAR+: 鲁棒自回归扩散语音合成的双重优化

相关实体

相关话题