Speech enhancement seeks to extract clean speech from noisy signals. Traditional deep learning methods face two challenges: efficiently using information in long speech sequences and high computational costs. To address these, we introduce the Spiking Structured State Space Model (Spiking-S4). This approach merges the energy efficiency of Spiking Neural Networks (SNN) with the long-range sequence modeling capabilities of Structured State Space Models (S4), offering a compelling solution. Evaluation on the DNS Challenge and VoiceBank+Demand Datasets confirms that Spiking-S4 rivals existing Artificial Neural Network (ANN) methods but with fewer computational resources, as evidenced by reduced parameters and Floating Point Operations (FLOPs).

翻译：语音增强旨在从含噪信号中提取纯净语音。传统深度学习方法面临两大挑战：长语音序列中信息的高效利用与高昂的计算成本。为解决这些问题，我们提出了基于脉冲的结构化状态空间模型（Spiking-S4）。该方法融合了脉冲神经网络（SNN）的能效优势与结构化状态空间模型（S4）的长距离序列建模能力，提供了一种引人注目的解决方案。在DNS挑战赛与VoiceBank+Demand数据集上的评估证实，Spiking-S4在计算资源更少的情况下（如参数数量与浮点运算次数（FLOPs）的减少所示）可与现有的人工神经网络（ANN）方法相媲美。