Phone recognition experiments with 2D-DCT spectro-temporal features

Abstract

Localized spectro-temporal analysis is a novel feature extraction strategy in speech recognition, which was inspired by neurophysiological findings. Here we perform phone recognition experiments on features that are extracted from the patches of the critical-band log-energy spectrum by applying the two-dimensional cosine trans-form. We find that in phone recognition experiments the proposed feature set yields results similar to the standard MFCC features under clean conditions, while it provides a significantly smaller performance degradation in noisy conditions. Moreover, we show that the new and the standard features can be readily combined to improve the recognition accuracy still further.