Voice cloning technology poses significant privacy threats by enabling unauthorized speech synthesis from limited audio samples. Existing defenses based on imperceptible adversarial perturbations are vulnerable to common audio preprocessing such as denoising and compression. We propose SceneGuard, a training-time voice protection method that applies scene-consistent audible background noise to speech recordings. Unlike imperceptible perturbations, SceneGuard leverages naturally occurring acoustic scenes (e.g., airport, street, park) to create protective noise that is contextually appropriate and robust to countermeasures. We evaluate SceneGuard on text-to-speech training attacks, demonstrating 5.5% speaker similarity degradation with extremely high statistical significance (p < 10^{-15}, Cohen's d = 2.18) while preserving 98.6% speech intelligibility (STOI = 0.986). Robustness evaluation shows that SceneGuard maintains or enhances protection under five common countermeasures including MP3 compression, spectral subtraction, lowpass filtering, and downsampling. Our results suggest that audible, scene-consistent noise provides a more robust alternative to imperceptible perturbations for training-time voice protection. The source code are available at: https://github.com/richael-sang/SceneGuard.

翻译：语音克隆技术能够通过有限的音频样本实现未经授权的语音合成，从而构成严重的隐私威胁。现有基于不可感知对抗扰动的防御方法易受去噪、压缩等常见音频预处理的影响。本文提出SceneGuard，一种训练时语音保护方法，通过在语音录音中添加场景一致的可听背景噪声。与不可感知的扰动不同，SceneGuard利用自然存在的声学场景（如机场、街道、公园）生成上下文适配且对抗措施鲁棒的保护性噪声。我们在文本到语音训练攻击场景下评估SceneGuard，结果显示该方法在保持98.6%语音可懂度（STOI = 0.986）的同时，使说话人相似度显著降低5.5%（统计极显著性：p < 10^{-15}，Cohen's d = 2.18）。鲁棒性评估表明，SceneGuard在MP3压缩、谱减法、低通滤波及降采样等五种常见对抗措施下均能维持或增强保护效果。研究结果表明，可听且场景一致的噪声为训练时语音保护提供了比不可感知扰动更具鲁棒性的替代方案。源代码已发布于：https://github.com/richael-sang/SceneGuard。