Speech Quality Evaluation: A New Application of Digital Watermarking

Speech quality evaluation is an important research topic. The traditional way for speech quality evaluation is using subjective tests. They are reliable, but very expensive, time consuming, and cannot be used in certain applications such as online monitoring. Objective models, based on human perception, were developed to predict the results of subjective tests. The existing objective methods require either the original speech or complicated computation model, which makes some applications of quality evaluation impossible. In this paper, we propose a novel speech quality evaluation method using digital watermarking. Our algorithm evaluates the speech quality without the need of reference speech or any computational model. The watermark is embedded in the discrete wavelet domain or temporal domain of a speech signal by using quantization technique. This algorithm can evaluate perceptual quality of speech that is distorted by Gaussian noise, MP3 compression, low-pass filtering, and packet loss. The experimental results show that the method yields accurate quality scores which are very close to the results of the perceptual evaluation of speech quality