Abstract
The use of hearing aids will increase in the coming years due to demographic change. One open problem that remains to be solved by a new generation of hearing aids is the cocktail party problem. A possible solution is electroencephalography-based auditory attention decoding. This has been the subject of several studies in recent years, which have in common that they use the same preprocessing methods in most cases. In this work, in order to achieve an advantage, the use of a scattering transform is proposed as an alternative to these preprocessing methods. The two-layer scattering transform is compared with a regular filterbank, the synchrosqueezing short-time Fourier transform and the common preprocessing. To demonstrate the performance, the known and the proposed preprocessing methods are compared for different classification tasks on two widely used datasets, provided by the KU Leuven (KUL) and the Technical University of Denmark (DTU). Both established and new neural-network-based models, CNNs, LSTMs, and recent Transformer/graph-based models are used for classification. Various evaluation strategies were compared, with a focus on the task of classifying speakers who are unknown from the training. We show that the two-layer scattering transform can significantly improve the performance for subject-related conditions, especially on the KUL dataset. However, on the DTU dataset, this only applies to some of the models, or when larger amounts of training data are provided, as in 10-fold cross-validation. This suggests that the scattering transform is capable of extracting additional relevant information.
Abstract (translated)
未来的几年里，助听器的使用量将会因为人口结构的变化而增加。新一代助听器仍需解决的一个开放性问题就是“鸡尾酒会问题”。一种可能的解决方案是基于脑电图（EEG）的听觉注意力解码方法，近年来对此进行了多项研究，它们通常采用相同的预处理方法。在这项工作中，为了获得优势，提出使用散射变换作为这些预处理方法的一种替代方案。两层散射变换与常规滤波器组、同步挤压短时傅里叶变换和常用预处理方法进行了比较。 为了展示性能，本文将已知的和提出的预处理方法在两个广泛使用的数据集上进行不同分类任务的对比，这两个数据集分别由鲁汶大学（KU Leuven, KUL）和丹麦技术大学（Technical University of Denmark, DTU）提供。用于分类的任务包括了传统的卷积神经网络（CNNs）、长短时记忆模型（LSTMs）以及最近提出的基于Transformer或图的方法。 比较了各种评估策略，重点是在测试集中包含训练集之外说话者的情况下进行分类任务的性能。研究结果显示，两层散射变换在与受试者相关的条件下显著提高了性能，特别是在KUL数据集上表现突出。然而，在DTU数据集上，只有某些模型或者在提供大量训练数据（例如10倍交叉验证）时才会表现出这一优势。这表明，散射变换能够提取出更多的相关信息。
URL
https://arxiv.org/abs/2602.23003
