Robust Feature Extraction Using Spectral Peaks of the Filtered Higher Lag Autocorrelation Sequence of the Speech Signal

This paper presents a new feature set for noisy speech recognition in autocorrelation domain. The autocorrelation domain is well-known for its pole preserving and noise separation properties. Therefore, in this paper we use the autocorrelation domain as an appropriate candidate for robust feature extraction. In our approach, initially, the lower lags of the noisy speech autocorrelation sequence are discarded and then, the effect of noise is further suppressed using a high pass filter in autocorrelation domain. Finally, the speech feature set is found using the spectral peaks of this filtered autocorrelation sequence We tested our features on the Aurora 2 noisy isolated-word task and found that it led to noticeable improvements over other autocorrelation-based and differential spectral-based methods implemented previously