Evaluation of speech quality using digital watermarking

Abstract

Speech quality evaluation is a very important research topic. Mean Opinion Score (MOS) is reliable but the listening test is very expensive, time consuming, and sometimes impractical. The existing objective quality assessment methods require either the original speech or complicated computation model, which makes some applications of quality evaluation impossible. We propose to use digital audio watermarking to evaluate the quality of speech. Our method does not need original signal or computation model. The experimental results show that the method yields accurate quality scores which are very close to the results of PESQ.