Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement
This addresses the problem of high computational complexity in speech enhancement for practical deployment, though it appears incremental as it adapts existing models to a new domain.
The paper tackled speech enhancement by integrating Mamba, a state-space model, with U-Net to overcome the quadratic complexity limitations of transformers, achieving a PESQ score of 3.59 on the VCTK+DEMAND dataset and 3.73 with an additional technique.
In recent speech enhancement (SE) research, transformer and its variants have emerged as the predominant methodologies. However, the quadratic complexity of the self-attention mechanism imposes certain limitations on practical deployment. Mamba, as a novel state-space model (SSM), has gained widespread application in natural language processing and computer vision due to its strong capabilities in modeling long sequences and relatively low computational complexity. In this work, we introduce Mamba-SEUNet, an innovative architecture that integrates Mamba with U-Net for SE tasks. By leveraging bidirectional Mamba to model forward and backward dependencies of speech signals at different resolutions, and incorporating skip connections to capture multi-scale information, our approach achieves state-of-the-art (SOTA) performance. Experimental results on the VCTK+DEMAND dataset indicate that Mamba-SEUNet attains a PESQ score of 3.59, while maintaining low computational complexity. When combined with the Perceptual Contrast Stretching technique, Mamba-SEUNet further improves the PESQ score to 3.73.