Robust phoneme recognition for a speech therapy environment

Abstract

Traditional speech therapy approaches for speech sound disorders have a lot of advantages to gain from computerbased therapy systems. With speech recognition techniques the motivation elements of these systems can be automated in order to get an interactive environment that motivates the therapy attendee towards better performances. Here we propose a robust phoneme recognition solution for an interactive environment for speech therapy. We compare the results of hierarchical and flat classification, with naive Bayes, support vector machines andkernel density estimation on linear predictive coding coefficients and Mel-frequency cepstral coefficients.