Unveiling weak auditory evoked potentials using data-driven filtering

Abstract

Auditory evoked potentials (AEPs) are commonly used to objectively evaluate sound perception in humans. Close to the hearing threshold and for low frequencies, efficient filtering of AEP from other brain activities is of major concern due to weak potentials and the requirement of long averaging times. Filtered AEP data are well-interpretable and useful, especially in medical and psychological diagnostics. Here, we present two data-driven approaches for efficient AEP filtering. First, neural networks of different architectures trained for EEG denoising are used to extract weak late-response AEP for low-frequency and infrasonic stimuli. During the design of the networks, we leveraged knowledge of the specific characteristics of the expected AEP data. Second, a singular value decomposition (SVD) of EEG data is evaluated, attempting to create classifiers for the presence of weak late-response AEP modes. We anticipate that the evaluation of AEP with data-driven methods can support researchers and scientists, for example, with real-time evaluation and diagnosis of acoustic-induced discomfort.