Spiking Structured State Space Model for Monaural Speech Enhancement

TL;DR

This paper introduces Spiking-S4, a novel speech enhancement model that combines energy-efficient spiking neural networks with long-range sequence modeling, achieving comparable performance to traditional methods but with reduced computational costs.

Contribution

The paper presents Spiking-S4, a new model that merges SNNs with S4 for efficient long-sequence speech enhancement, addressing computational challenges of existing deep learning approaches.

Findings

Spiking-S4 performs comparably to existing ANN methods on benchmark datasets.

Spiking-S4 uses fewer parameters and FLOPs, indicating higher efficiency.

Evaluation confirms the effectiveness of Spiking-S4 in real-world noisy environments.

Abstract

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).