Noise-robust speech recognition based on difference of power spectrum

A new noise-robust speech recognition method is presented based on the difference in the power spectrum. The idea is to remove the additive noise by filtering in the power spectrum domain. Feature extraction is carried out in two steps: (i) the short-time power spectrum of the speech signal is allowed to pass through a filter bank, and (ii) the differences in the filter outputs are calculated. Theoretical analysis and experimental results show that using the proposed features can significantly improve the recogniser´s performance in a noisy environment