Data-driven spatial filtering for improved measurement of cortical tracking of multiple representations of speech.

OBJECTIVE: Measurement of the cortical tracking of continuous speech from electroencephalography (EEG) recordings using a forward model is an important tool in auditory neuroscience. Usually the stimulus is represented by its temporal envelope. Recently, the phonetic representation of speech was successfully introduced in English. We aim to show that the EEG prediction from phoneme-related speech features is possible in Dutch. The method requires a manual channel selection based on visual inspection or prior knowledge to obtain a summary measure of cortical tracking. We evaluate a method to (1) remove non-stimulus-related activity from the EEG signals to be predicted, and (2) automatically select the channels of interest. APPROACH: Eighteen participants listened to a Flemish story, while their EEG was recorded. Subject-specific and grand-average temporal response functions were determined between the EEG activity in different frequency bands and several stimulus features: the envelope, spectrogram, phonemes, phonetic features or a combination. The temporal response functions were used to predict EEG from the stimulus, and the predicted was compared with the recorded EEG, yielding a measure of cortical tracking of stimulus features. A spatial filter was calculated based on the generalized eigenvalue decomposition (GEVD), and the effect on EEG prediction accuracy was determined. MAIN RESULTS: A model including both low- and high-level speech representations was able to better predict the brain responses to the speech than a model only including low-level features. The inclusion of a GEVD-based spatial filter in the model increased the prediction accuracy of cortical responses to each speech feature at both single-subject (270% improvement) and group-level (310%). SIGNIFICANCE: We showed that the inclusion of acoustical and phonetic speech information and the addition of a data-driven spatial filter allow improved modelling of the relationship between the speech and its brain responses and offer an automatic channel selection.

Predicting individual speech intelligibility from the cortical tracking of acoustic- and phonetic-level speech representations.

OBJECTIVE: To objectively measure speech intelligibility of individual subjects from the EEG, based on cortical tracking of different representations of speech: low-level acoustical, higher-level discrete, or a combination. To compare each model's prediction of the speech reception threshold (SRT) for each individual with the behaviorally measured SRT. METHODS: Nineteen participants listened to Flemish Matrix sentences presented at different signal-to-noise ratios (SNRs), corresponding to different levels of speech understanding. For different EEG frequency bands (delta, theta, alpha, beta or low-gamma), a model was built to predict the EEG signal from various speech representations: envelope, spectrogram, phonemes, phonetic features or a combination of phonetic Features and Spectrogram (FS). The same model was used for all subjects. The model predictions were then compared to the actual EEG of each subject for the different SNRs, and the prediction accuracy in function of SNR was used to predict the SRT. RESULTS: The model based on the FS speech representation and the theta EEG band yielded the best SRT predictions, with a difference between the behavioral and objective SRT below 1 decibel for 53% and below 2 decibels for 89% of the subjects. CONCLUSION: A model including low- and higher-level speech features allows to predict the speech reception threshold from the EEG of people listening to natural speech. It has potential applications in diagnostics of the auditory system.