Exploitation of spectral variance to improve robustness in speech recognition

Abstract

With the aim of improving noise robustness of speech recognition an approach that exploits the variance information in spectral sub-bands is presented. The variance based features are used in combination with the normally used Mel-frequency cepstral coefficients (MFCC), and experimental results show that the combined features outperform MFCC alone, perceptual linear prediction features and entropy based features.