动态剪枝让语音增强模型在低算力设备上更高效
Scalable Speech Enhancement with Dynamic Channel Pruning
- 运行时自动识别并跳过无用卷积通道，实时节省计算量
- 仅用25%通道时减少29.6%乘加操作，音质损失仅0.75%（PESQ）
- 适合资源受限场景下的高性能语音增强部署
语音增强对远程协作环境中的效率提升至关重要。尽管深度学习模型在语音增强任务中表现优异，但其高计算需求使其难以在嵌入式系统中应用。此外，声学条件变化大，而神经网络通常固定计算量。为此，我们首次将动态通道剪枝引入音频领域，并应用于自研卷积架构的语音增强模型。该方法在运行时识别冗余卷积通道，跳过其激活值计算并复用滤波器，从而节省计算资源。训练时仅使用25%通道的情况下，可减少29.6%的乘加操作（MACs），同时仅导致0.75%的PESQ得分下降。结果表明，动态通道剪枝为在资源受限设备上部署更大更强的语音增强模型提供了可行路径。
原文摘要 · Abstract (English)
Speech Enhancement (SE) is essential for improving productivity in remote collaborative environments. Although deep learning models are highly effective at SE, their computational demands make them impractical for embedded systems. Furthermore, acoustic conditions can change significantly in terms of difficulty, whereas neural networks are usually static with regard to the amount of computation performed. To this end, we introduce Dynamic Channel Pruning to the audio domain for the first time and apply it to a custom convolutional architecture for SE. Our approach works by identifying unnecessary convolutional channels at runtime and saving computational resources by not computing the activations for these channels and retrieving their filters. When trained to only use 25% of channels, we save 29.6% of MACs while only causing a 0.75% drop in PESQ. Thus, DynCP offers a promising path toward deploying larger and more powerful SE solutions on resource-constrained devices.
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。