Predicting Preference Judgments of Individual Normal and Hearing-Impaired Listeners With Gaussian Processes

Abstract—A probabilistic kernel approach to pairwise preference learning based on Gaussian processes is applied to predict preference judgments for sound quality degradation mechanisms that might be present in a hearing aid. Subjective sound quality comparisons for 14 normal-hearing and 18 hearing-impaired subjects were used for evaluating the predictive performance. Stimuli were sentences subjected to three kinds of distortion (additive noise, peak clipping, and center clipping) with eight levels of degradation for each distortion type. The kernel approach gives a significant improvement in preference predictions of hearing-impaired subjects by individualizing the learning process. A significant difference is shown between normal-hearing and hearing-impaired subjects, because of nonlinearities in the perception of hearing-impaired subjects. In particular, hearingimpaired subjects have significant nonlinear preference judgments when making pairwise comparisons between peak clipped...

• Type: Journal
• Year: 2011
• Where: TASLP
• Authors: Perry Groot, Tom Heskes, Tjeerd Dijkstra, James M. Kates
• Keywords: Hearing-impaired Subjects, Kernel Approach, Probabilistic Kernel Approach, Software Engineering, TASLP 2011