用更快的网络结构让语音增强模型更小更省电。
Fast-ULCNet: A fast and ultra low complexity network for single-channel speech enhancement
- 用FastGRNN替换原模型的GRU层，降低计算开销。
- 在长音频上修复状态漂移问题，保持效果稳定。
- 模型体积减半，延迟降低34%，适合嵌入式设备。
单通道语音增强算法常用于资源受限的嵌入式设备，低延迟和低复杂度设计愈发重要。近年来，研究者提出了多种解决方案，其中ULCNet是该领域的先进方法之一。本文提出对ULCNet的改进：用FastGRNN替代其GRU层，以降低计算延迟和复杂度。此外，本文揭示了FastGRNN在长音频推理中因内部状态漂移导致性能下降的实证现象，并提出一种基于可训练互补滤波器的新方法来缓解该问题。所提出的Fast-ULCNet模型在语音增强任务上表现与最先进的原始ULCNet相当，同时模型大小减少超过一半，平均延迟降低34%。
原文摘要 · Abstract (English)
Single-channel speech enhancement algorithms are often used in resource-constrained embedded devices, where low latency and low complexity designs gain more importance. In recent years, researchers have proposed a wide variety of novel solutions to this problem. In particular, a recent deep learning model named ULCNet is among the state-of-the-art approaches in this domain. This paper proposes an adaptation of ULCNet, by replacing its GRU layers with FastGRNNs, to reduce both computational latency and complexity. Furthermore, this paper shows empirical evidence on the performance decay of FastGRNNs in long audio signals during inference due to internal state drifting, and proposes a novel approach based on a trainable complementary filter to mitigate it. The resulting model, Fast-ULCNet, performs on par with the state-of-the-art original ULCNet architecture on a speech enhancement task, while reducing its model size by more than half and decreasing its latency by 34% on average.
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。