MC-SEMamba: A Simple Multi-channel Extension of SEMamba
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.
Cite
@article{arxiv.2409.17898,
title = {MC-SEMamba: A Simple Multi-channel Extension of SEMamba},
author = {Wen-Yuan Ting and Wenze Ren and Rong Chao and Hsin-Yi Lin and Yu Tsao and Fan-Gang Zeng},
journal= {arXiv preprint arXiv:2409.17898},
year = {2024}
}