Phase AutoCorrelation (PAC) derived Robust Speech Features

In this paper, we introduce a new class of noise robust acoustic features derived from a new measure of autocorrelation, and explicitly exploiting the phase variation of the speech signal frame over time. This family of features, referred to as Phase AutoCorrelation'' (PAC) features, include PAC spectrum and PAC MFCC, among others. In regular autocorrelation based features, the correlation between two signal segments (signal vectors), separated by a particular time interval $k$, is calculated as a dot product of these two vectors. In our proposed PAC approach, the angle between the two vectors is used as a measure of correlation. Since dot product is usually more affected by noise than the angle, it is expected that PAC-features will be more robust to noise. This is indeed significantly confirmed by the experimental results presented in this paper. The experiments were conducted on the Numbers 95 database, on which stationary'' (car) and ``non-stationary'' (factory) Noisex 92 noises were added with varying SNR. In most of the cases, without any specific tuning, PAC-MFCC features perform better.