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.