MC-SEMamba: A Simple Multi-channel Extension of SEMamba

TL;DR

This paper introduces MC-SEMamba, a multi-channel extension of SEMamba, which efficiently enhances speech by leveraging multiple microphones, achieving superior results with minimal parameter increase compared to single-channel models.

Contribution

The paper adapts SEMamba for multi-channel speech enhancement, demonstrating improved performance with more microphones and minimal additional parameters.

Findings

MC-SEMamba outperforms previous baselines on CHiME3 dataset.

Increasing microphones from 1 to 6 improves speech enhancement.

Minimal parameter increase for multi-channel adaptation.

Abstract

Transformer-based models have become increasingly popular and have impacted speech-processing research owing to their exceptional performance in sequence modeling. Recently, a promising model architecture, Mamba, has emerged as a potential alternative to transformer-based models because of its efficient modeling of long sequences. In particular, models like SEMamba have demonstrated the effectiveness of the Mamba architecture in single-channel speech enhancement. This paper aims to adapt SEMamba for multi-channel applications with only a small increase in parameters. The resulting system, MC-SEMamba, achieved results on the CHiME3 dataset that were comparable or even superior to several previous baseline models. Additionally, we found that increasing the number of microphones from 1 to 6 improved the speech enhancement performance of MC-SEMamba.