Unsupervised Self-Adaptive Auditory Attention Decoding: Supplementary Material

In this supplementary material corresponding to the paper `Unsupervised Self-Adaptive Auditory Attention Decoding' by Geirnaert et al. [1], which has also been peer-reviewed together with the original article in [1], we show convergence to a unique fixed point of the fixed-point iteration on the updating model (Equation (16) in the original paper [1]). We hypothesize and show that under three reasonable conditions on the accuracies of the attended and unattended decoder, there exists a unique fixed point to which the fixed-point iteration converges, starting from any (possibly random) decoder.

[1] S. Geirnaert, T. Francart, and A. Bertrand, "Unsupervised Self-Adaptive Auditory Attention Decoding," IEEE Journal of Biomedical and Health Informatics, 2021.