Comparison of linear and nonlinear methods for decoding selective attention to speech from ear-EEG recordings

Abstract

Many people with hearing loss struggle to comprehend speech in crowded auditory scenes, even when they are using hearing aids. It has recently been demonstrated that 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 (such as the cocktail party). To this end, we here 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. Eighteen participants took part in a diotic listening task, whereby they were asked to attend to one narrator whilst ignoring the other. Encoding models were estimated from the recorded signals, and these confirmed that the device has the ability to capture auditory responses that are consistent with those reported in high-density EEG studies. Several state-of-the-art auditory attention decoding algorithms were next 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 18 participants, even when those markers were derived from relatively short EEG segments of just five seconds in duration. Algorithms which related the EEG signals to the rising edges of the speech temporal envelope (onset envelope) were more successful than those which made use of the temporal envelope itself. The CCA algorithm achieved the highest mean attention decoding accuracy, although differences between the performances of the three algorithms were both small and not statistically significant when EEG segments of short durations were employed.