Novel objective criteria for perceptual separation of two kinds of Distortion in speech enhancement applications

There is an increasing interest in the development of robust quantitative speech quality measures that correlate well with subjective measures. This paper presents two objective criteria-the perceptual signal to audible noise ratio (PSANR) and the perceptual signal to audible distortion ratio (PSADR), to characterize the two kinds of degradation (i.e., residual background noise, speech distortion or both) in speech enhancement applications. For performance evaluation of speech enhancement algorithms it is necessary to determine with accuracy the kind of degradation present in the enhanced signal. Experimental results for speech enhancement using different well-known approaches depict the usefulness of the proposed objective criteria.