Post-processing of EEG-based Auditory Attention Decoding Decisions via Hidden Markov Models

TL;DR

This paper introduces a hidden Markov model to enhance EEG-based auditory attention decoding, significantly improving accuracy and responsiveness in both real-time and offline scenarios by modeling attention stability.

Contribution

The novel integration of a hidden Markov model with existing AAD algorithms to better capture attention dynamics and improve decoding performance.

Findings

HMM significantly improves AAD accuracy in real-time and offline settings.

HMM outperforms existing postprocessing methods in accuracy and responsiveness.

Performance depends on window length, switching frequency, and initial AAD accuracy.

Abstract

Auditory attention decoding (AAD) algorithms exploit brain signals, such as electroencephalography (EEG), to identify which speaker a listener is focusing on in a multi-speaker environment. While state-of-the-art AAD algorithms can identify the attended speaker on short time windows, their predictions are often too inaccurate for practical use. In this work, we propose augmenting AAD with a hidden Markov model (HMM) that models the temporal structure of attention. More specifically, the HMM relies on the fact that a subject is much less likely to switch attention than to keep attending the same speaker at any moment in time. We show how a HMM can significantly improve existing AAD algorithms in both causal (real-time) and non-causal (offline) settings. We further demonstrate that HMMs outperform existing postprocessing approaches in both accuracy and responsiveness, and explore how various factors such as window length, switching frequency, and AAD accuracy influence overall performance. The proposed method is computationally efficient, intuitive to use and applicable in both real-time and offline settings.