arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.17898eess.AScs.SD
收藏

MC-SEMamba:SEMamba 的简单多通道扩展

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

Academia Sinica(中央研究院);National Taiwan University(台湾大学);Seton Hall University(薛顿贺尔大学);University of California Irvine(加州大学欧文分校)

Wen-Yuan Ting, Wenze Ren, Rong Chao, Hsin-Yi Lin, Yu Tsao, Fan-Gang Zeng

AI总结:

本文提出 MC-SEMamba,通过仅增加少量参数将 SEMamba 扩展至多通道语音增强,在 CHiME3 数据集上表现优于基线,且性能随麦克风数量增加而提升。

摘要:

基于 Transformer 的模型因其在序列建模中的卓越性能而日益流行,并影响了语音处理研究。最近,一种极具前景的模型架构 Mamba 因其对长序列的高效建模,作为基于 Transformer 模型的潜在替代方案而出现。特别是,像 SEMamba 这样的模型已经证明了 Mamba 架构在单通道语音增强中的有效性。本文旨在将 SEMamba 适配于多通道应用,且仅增加少量参数。由此产生的系统 MC-SEMamba 在 CHiME3 数据集上取得了与之前几个基线模型相当甚至更优的结果。此外,我们发现将麦克风数量从 1 增加到 6 提升了 MC-SEMamba 的语音增强性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑