ABSTRACT
Subjective quality evaluation, for instance, involves comparisons of original and processed speech signals by a group of listeners who are asked to rate the quality of speech along a predetermined scale. Objective evaluation involves a mathematical comparison of the original and processed speech signals. This chapter provides an overview of the various listening tests/procedures that have been used to evaluate speech enhancement algorithms in terms of quality and intelligibility. Although historically some of these procedures have been used to evaluate speech-coding algorithms, these methods have also been used to quantify the performance of speech enhancement algorithms. Quality is highly subjective in nature and it is difficult to evaluate reliably. This is partly because individual listeners have different internal standards of what constitutes “good” or “poor” quality, resulting in large variability in rating scores among listeners. Intelligibility is an important attribute of the speech signal that needs to be preserved at all costs by speech enhancement algorithms.
