PREDICTING SPEECH INTELLIGIBILITY FROM A SELECTIVE ATTENTION DECODING PARADIGM IN COCHLEAR IMPLANT USERS

1. ABSTRACT ObjectivesElectroencephalography (EEG) can be used to decode selective attention in cochlear implant (CI) users. This work investigates if selective attention to an attended speech source in the presence of a concurrent speech source can predict speech understanding in CI users. ApproachCI users were instructed to attend to one out of two speech streams while EEG was recorded. Both speech streams were presented to the same ear and at different signal to interference ratios (SIRs). Speech envelope reconstruction of the to-be-attended speech from EEG was obtained by training decoders using regularized least squares. The correlation coefficient between the reconstructed and the attended (ρASIR) and between the reconstructed and the unattended (ρUSIR) speech stream at each SIR was computed. Main ResultsSelective attention decoding in CI users is possible even if both speech streams are presented monaurally. A significant effect of SIR on the correlation coefficient to the attended signal ρASIR, as well as on the difference correlation coefficients ρASIR – ρUSIR and ρASIR – ρUSIR was observed, but not on the unattended correlation coefficient ρUSIR. Finally, the results show a significant correlation between speech understanding performance and the correlation coefficients ρASIR–ρUSIR or ?ρUSIR across subjects. Moreover, the difference correlation coefficient ρASIR – ρU?SIR, which is less affected by the CI electrical artifact, presented a correlation trend with speech understanding performance. SignificanceSelective attention decoding in CI users is possible, however care needs to be taken with the CI artifact and the speech material used to train the decoders. Even if only a small correlation trend between selective attention decoding and speech understanding was observed, these results are important for future development of objective speech understanding measures for CI users.