Predicting speech intelligibility from a selective attention decoding paradigm in cochlear implant users

Abstract

Abstract Objectives. Electroencephalography (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. Approach. CI 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 ( ρ A SIR ) or the unattended ρ U SIR   speech stream at each SIR was computed. Additionally, we computed the difference correlation coefficient at the same ( ρ Diff =   ρ A SIR − ρ U SIR ) and opposite SIR ( ρ DiffOpp =   ρ A SIR − ρ U − SIR ) . ρ Diff compares the attended and unattended correlation coefficient to speech sources presented at different presentation levels depending on SIR. In contrast, ρ DiffOpp compares the attended and unattended correlation coefficients to speech sources presented at the same presentation level irrespective of SIR. Main results. Selective attention decoding in CI users is possible even if both speech streams are presented monaurally. A significant effect of SIR on ρ A SIR , ρ Diff and ρ DiffOpp, but not on ρ U SIR , was observed. Finally, the results show a significant correlation between speech understanding performance and ρ A SIR as well as with ρ U SIR across subjects. Moreover, ρ DiffOpp which is less affected by the CI artifact, also demonstrated a significant correlation with speech understanding. Significance. Selective 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. These results are important for future development of objective speech understanding measures for CI users.