Scoring sleep stages in polysomnography recordings is a time-consuming task
plagued by significant inter-rater variability. Therefore, it stands to benefit
from the application of machine learning algorithms. While many algorithms have
been proposed for this purpose, certain critical architectural decisions have
not received systematic exploration. In this study, we meticulously investigate
these design choices within the broad category of encoder-predictor
architectures. We identify robust architectures applicable to both time series
and spectrogram input representations. These architectures incorporate
structured state space models as integral components, leading to statistically
significant advancements in performance on the extensive SHHS dataset. These
improvements are assessed through both statistical and systematic error
estimations. We anticipate that the architectural insights gained from this
study will not only prove valuable for future research in sleep staging but
also hold relevance for other time series annotation tasks.

通过研究编码器 - 预测器体系结构的设计选择，我们找到了适用于时间序列和频谱图输入表示的可靠体系结构，其中结构化状态空间模型作为其组成部分，从而在广泛的 SHHS 数据集上显著提高了性能，这些改进通过统计和系统误差估计进行了评估。我们预计，从本研究获得的体系结构见解不仅对于未来的睡眠分期研究有价值，而且对其他时间序列注释任务也具有相关性。

S4Sleep: 深度学习基于睡眠阶段分类模型的设计空间阐明

S4Sleep: Elucidating the design space of deep-learning-based sleep stage  classification models

Speech enhancement seeks to extract clean speech from noisy signals.
Traditional deep learning methods face two challenges: efficiently using
information in long speech sequences and high computational costs. To address
these, we introduce the Spiking Structured State Space Model (Spiking-S4). This
approach merges the energy efficiency of Spiking Neural Networks (SNN) with the
long-range sequence modeling capabilities of Structured State Space Models
(S4), offering a compelling solution. Evaluation on the DNS Challenge and
VoiceBank+Demand Datasets confirms that Spiking-S4 rivals existing Artificial
Neural Network (ANN) methods but with fewer computational resources, as
evidenced by reduced parameters and Floating Point Operations (FLOPs).

使用 Spiking Structured State Space Model（Spiking-S4）可以高效地从长时间语音序列中提取干净的语音，该方法将 Spiking Neural Networks（SNN）的能效与 Structured State Space Models（S4）的长程序列建模能力相结合，具有较少的计算资源要求，与现有的人工神经网络（ANN）方法相媲美。