Affordable Access

Bayesian Feature Selection for Hearing Aid Personalization

Publication Date
  • Computer Science
  • Musicology
  • Physics


BAYESIAN FEATURE SELECTION FOR HEARING AID PERSONALIZATION Alexander Ypma1, Serkan Ozer2, Erik van der Werf1 and Bert de Vries1'2 1GN ReSound Research, GN ReSound A/S, Horsten 1, 5612 AX Eindhoven 2Signal Processing Systems group, Dept. Electrical Engineering, TU Eindhoven [email protected],{aypma,evdwerf,[email protected] ABSTRACT We formulate hearing aid personalization as a linear regression. Since sample sizes may be low and the number of features may be high we resort to a Bayesian approach for sparse linear regression that can deal with many features, in order to find efficient repre- sentations for on-line usage. We compare to a heuristic feature se- lection approach that we optimized for speed. Results on synthetic data with irrelevant and redundant features indicate that Bayesian backfitting has labelling accuracy comparable to the heuristic ap- proach (for moderate sample sizes), but takes much larger training times. We then determine features for hearing aid personalization by applying the method to hearing aid preference data. 1. HEARING AID PERSONALIZATION Modern digital hearing aids contain advanced signal process- ing algorithms with many parameters. These are set to val- ues that ideally match the needs and preferences of the user. Because of the large dimensionality of the parameter space and unknown determinants of user satisfaction, the fitting procedure becomes a complex task. Some of the user para- meters are personalized by the hearing aid dispenser based on the nature of the hearing loss. Other parameters may be tuned on the basis of models for e.g. loudness perception [1]. But not every individual user preference can be put as a preset into the hearing aid: some particularities of the user may be hard to represent into the algorithm, and the user's typical acoustic environments and preference patterns may be changing. Therefore we should personalize a hearing aid during usage to actual user preferences. The algorithms introduced in [2] are able t

There are no comments yet on this publication. Be the first to share your thoughts.