Improved noise reduction in audio signals using spectral resolution enhancement with time-domain signal extrapolation

Abstract

In this paper, we present significant improvement to frame-by-frame noise reduction methods which are based on spectral domain processing. This work mainly focuses on the analysis stage of the noise reduction process. It is common knowledge that better performance is obtained by increasing the spectral resolution. However, effective spectral resolution depends directly on the number of samples in the processing frame. This leads to the well-known tradeoff between spectral and temporal resolution. Our approach is to use a novel discrete signal extrapolation method to prolong the given signal frame, resulting in increased spectral resolution without losing any temporal quality. The improvement in the noise reduction is tested with objective and subjective evaluations. The effect of the human auditory system is taken into account in the objective measures. Subjective tests are performed to determine the quality improvement in a perceptual sense.