DarkStream实现实时语音匿名，低延迟下保护说话人隐私。
DarkStream: real-time speech anonymization with low latency
- 采用因果波形编码+短前瞻缓冲+注意力层，兼顾低延迟与内容保真。
- 直接生成波形，避免中间转换，推理速度更快；在攻击场景下EER接近50%。
- 适合需要实时隐私保护的通信系统，如会议、客服等场景。
我们提出DarkStream，一种用于实时语音匿名的流式语音合成模型。为在严格延迟约束下提升内容编码能力，DarkStream结合因果波形编码器、短前瞻缓冲区和基于Transformer的上下文层。为进一步降低推理时间，模型通过神经声码器直接生成波形，省去中间梅尔频谱图转换。最后，通过将GAN生成的伪说话人嵌入注入内容编码器的语言特征中，实现说话人身份匿名化。评估显示，该模型在懒惰知情攻击场景下达到近50%的说话人验证错误率（接近随机水平），同时保持可接受的语言可懂度（词错误率低于9%）。通过平衡低延迟、强隐私保护与最小可懂度损失，DarkStream为隐私保护型实时语音通信提供了实用解决方案。
原文摘要 · Abstract (English)
We propose DarkStream, a streaming speech synthesis model for real-time speaker anonymization. To improve content encoding under strict latency constraints, DarkStream combines a causal waveform encoder, a short lookahead buffer, and transformer-based contextual layers. To further reduce inference time, the model generates waveforms directly via a neural vocoder, thus removing intermediate mel-spectrogram conversions. Finally, DarkStream anonymizes speaker identity by injecting a GAN-generated pseudo-speaker embedding into linguistic features from the content encoder. Evaluations show our model achieves strong anonymization, yielding close to 50% speaker verification EER (near-chance performance) on the lazy-informed attack scenario, while maintaining acceptable linguistic intelligibility (WER within 9%). By balancing low-latency, robust privacy, and minimal intelligibility degradation, DarkStream provides a practical solution for privacy-preserving real-time speech communication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。