用高斯混合模型构建纯净语音先验，提升降噪效果且无需录音
G-MaP-SE: Guided Speech Enhancement via GMM-Based Prior Matching
- 用高斯混合模型建立纯净语音嵌入先验，对抗噪声干扰
- 在两个数据集上优于噪声条件输入，接近理想纯净条件性能
- 推理时无需录制参考音频，适合实际场景应用
使用说话人嵌入作为条件可增强语音降噪效果，但多数方法需干净的注册音频，或依赖从噪声语音中提取的嵌入，后者在噪声和域偏移下不稳定。本文提出G-MaP-SE框架，通过高斯混合模型（GMM）构建纯净语音嵌入先验，并将噪声条件嵌入与该先验匹配以进行优化。匹配后的先验嵌入通过轻量级门控融合模块注入时频增强主干网络。在VoiceBank+DEMAND和DNS Challenge 2020数据集上的实验表明，所提先验匹配方法持续优于噪声条件输入，显著缩小与理想纯净条件上界之间的差距，且推理时无需注册音频。代码、音频样本及模型检查点已公开。
原文摘要 · Abstract (English)
Using speaker embeddings as conditioning can strengthen speech enhancement, but most methods either require clean enrollment audio or rely on embeddings extracted from noisy speech, which are fragile under noise and domain shift. We propose G-MaP-SE, a guided enhancement framework that builds a clean-speech embedding prior with a Gaussian Mixture Model (GMM) and refines a noisy conditioning embedding by matching it to this prior. The matched prior embedding is then injected into a time-frequency enhancement backbone via a lightweight gated fusion module. Experiments on VoiceBank+DEMAND and DNS Challenge 2020 datasets show that the proposed prior matching consistently outperforms noisy conditioning and substantially narrows the gap to an oracle clean-conditioning upper bound, while requiring no enrollment audio at inference time. The code, audio samples, and checkpoint are available.
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。