A Robust Feature Normalization Algorithm for Automatic Speech Recognition

Abstract

In this paper, we present an effective feature normalization algorithm to improve the robustness of automatic speech recognition systems. At front-end, minimum mean square error log-spectral amplitude estimation speech enhancement is adopted to suppress noise from noisy speech. Then, at back-end, the histogram equalization feature normalization is used to deal with the residual mismatch between enhanced speech and clean speech. We have evaluated recognition performance under noisy environments using NOISEX-92 database and recorded speech signals in continuous speech recognition task. Experimental results show that our approach exhibits considerable improvements in the degraded environment.