Auditory attention decoding from Ear-EEG signals: A dataset with dynamic attention switching and rigorous cross-validation

Recent promising results in auditory attention decoding (AAD) using scalp electroencephalography (EEG) have motivated the exploration of cEEGrid, a flexible and portable ear-EEG system. While prior cEEGrid-based studies have confirmed the feasibility of AAD, they often neglect the dynamic nature of attentional states in real-world contexts. To address this gap, a novel cEEGrid dataset featuring three concurrent speakers distributed across three of five distinct spatial locations is introduced. The novel dataset is designed to probe attentional tracking and switching mimicking realistic scenarios. Nested leave-one-out validation—an approach more rigorous than conventional single-loop leave-one-out validation—is employed to reduce biases stemming from EEG’s intricate temporal dynamics. Several rule-based models are evaluated: Wiener filter (WF) and canonical component analysis (CCA). With a 30-second decision window and individualized hyperparameters, WF and CCA models achieve decoding accuracies of 41.5% and 41.4%, respectively. Tuning hyperparameters on all subjects resulted in a decoding accuracy of 43.8% achieved by WF model. These results indicate that dynamic three-speaker cEEGrid AAD remains a challenging benchmark, with current linear models achieving statistically significant but practically limited performance. Additionally, higher decoding accuracies are observed for electrodes positioned at the upper cEEGrid layout and near the listener’s right ear. These findings underscore the utility of dynamic, ecologically valid paradigms and rigorous validation in advancing AAD research with cEEGrid.