This work aims to study a scalable state-space model (SSM), Mamba, for the
speech enhancement (SE) task. We exploit a Mamba-based regression model to
characterize speech signals and build an SE system upon Mamba, termed SEMamba.
We explore the properties of Mamba by integrating it as the core model in both
basic and advanced SE systems, along with utilizing signal-level distances as
well as metric-oriented loss functions. SEMamba demonstrates promising results
and attains a PESQ score of 3.55 on the VoiceBank-DEMAND dataset. When combined
with the perceptual contrast stretching technique, the proposed SEMamba yields
a new state-of-the-art PESQ score of 3.69.

研究了一种可扩展的状态空间模型（SSM）Mamba，用于语音增强（SE）任务，利用基于 Mamba 的回归模型来表征语音信号，并在 Mamba 上构建了一个 SE 系统，命名为 SEMamba，在基本和高级 SE 系统中集成了 Mamba 的属性，并利用信号级距离和基于度量的损失函数。SEMamba 表现出有希望的结果，并在 VoiceBank-DEMAND 数据集上获得了 3.55 的 PESQ 分数。当与感知对比拉伸技术结合使用时，所提出的 SEMamba 获得了 3.69 的最新的 PESQ 分数。

融入曼巴进行语音增强的研究

An Investigation of Incorporating Mamba for Speech Enhancement

Speech enhancement (SE) performance has improved considerably owing to the
use of deep learning models as a base function. Herein, we propose a perceptual
contrast stretching (PCS) approach to further improve SE performance. The PCS
is derived based on the critical band importance function and is applied to
modify the targets of the SE model. Specifically, the contrast of target
features is stretched based on perceptual importance, thereby improving the
overall SE performance. Compared with post-processing-based implementations,
incorporating PCS into the training phase preserves performance and reduces
online computation. Notably, PCS can be combined with different SE model
architectures and training criteria. Furthermore, PCS does not affect the
causality or convergence of SE model training. Experimental results on the
VoiceBank-DEMAND dataset show that the proposed method can achieve
state-of-the-art performance on both causal (PESQ score = 3.07) and noncausal
(PESQ score = 3.35) SE tasks.

本文提出了一种基于感知对比度拉伸 (PCS) 的方法来改善音频信号增强 (SE) 的性能，该方法通过对基于感知重要性的关键带重要性函数的目标特征的对比度进行拉伸，从而提高整体性能，并且可以与不同的 SE 模型架构和训练标准相结合，并且 PCS 不影响 SE 模型训练的因果性或收敛性，并可在 VoiceBank-DEMAND 数据集上实现最先进的性能。