SSR-Speech：迈向稳定、安全且鲁棒的零样本文本语音编辑与合成
SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
AI总结：
SSR-Speech提出基于Transformer解码器与无分类器引导的神经编解码器自回归模型，结合水印Encodec和原始未编辑片段重建，在零样本语音编辑与合成中实现稳定、安全、鲁棒的最先进性能。
摘要：
本文提出SSR-Speech，一种神经编解码器自回归模型，旨在实现稳定、安全且鲁棒的零样本文本语音编辑与文本到语音合成。SSR-Speech基于Transformer解码器构建，并引入无分类器引导以增强生成过程的稳定性。提出一种水印Encodec，将帧级水印嵌入语音中被编辑的区域，从而能够检测出哪些部分被编辑。此外，波形重建利用原始未编辑语音片段，相比Encodec模型提供了更优的恢复效果。该方法在RealEdit语音编辑任务和LibriTTS文本到语音任务中取得了最先进性能，超越以往方法。SSR-Speech在多跨度语音编辑方面表现优异，并对背景声音展现出显著的鲁棒性。源代码和演示已发布。
英文摘要：
In this paper, we introduce SSR-Speech, a neural codec autoregressive model designed for stable, safe, and robust zero-shot textbased speech editing and text-to-speech synthesis. SSR-Speech is built on a Transformer decoder and incorporates classifier-free guidance to enhance the stability of the generation process. A watermark Encodec is proposed to embed frame-level watermarks into the edited regions of the speech so that which parts were edited can be detected. In addition, the waveform reconstruction leverages the original unedited speech segments, providing superior recovery compared to the Encodec model. Our approach achieves state-of-the-art performance in the RealEdit speech editing task and the LibriTTS text-to-speech task, surpassing previous methods. Furthermore, SSR-Speech excels in multi-span speech editing and also demonstrates remarkable robustness to background sounds. The source code and demos are released.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
