Comparison of Linear and Nonlinear Methods for Decoding Selective Attention to Speech From Ear-EEG Recordings

Many people with hearing loss struggle to comprehend speech in crowded auditory scenes, even when they are using hearing aids. However, the focus of a listener’s selective attention to speech can be decoded from their electroencephalography (EEG) recordings, raising the prospect of smart EEG-steered hearing aids which restore speech comprehension in adverse acoustic environments. Here, we assess the feasibility of using a novel, ultra-wearable, ear-EEG device to classify the selective attention of normal-hearing listeners who participated in a two-talker competing-speakers experiment. State-of-the-art auditory attention decoding algorithms are compared, including stimulus-reconstruction algorithms based on linear regression as well as non-linear deep neural networks, and canonical correlation analysis (CCA). Meaningful markers of selective auditory attention could be extracted from the ear-EEG signals of all participants, even when those markers are derived from relatively short EEG segments of just 5 s in duration. Algorithms which relate the EEG signals to the rising edges of the speech temporal envelope are more successful than those which make use of the temporal envelope itself. The CCA algorithm achieves the highest mean attention decoding accuracy, although differences between the performances of the three algorithms are both small and not statistically significant when EEG segments of short durations are employed. In summary, our ultra-wearable ear-EEG device offers promising prospects for wearable auditory monitoring.