Spiking Structured State Space Model for Monaural Speech Enhancement
This work addresses computational efficiency in speech enhancement for applications like audio processing, though it is incremental as it combines existing SNN and S4 techniques.
The paper tackled speech enhancement by introducing the Spiking Structured State Space Model (Spiking-S4) to address inefficiencies in long sequence modeling and high computational costs, achieving competitive performance with existing methods while reducing parameters and FLOPs on datasets like DNS Challenge and VoiceBank+Demand.
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).