In voice and video communication, quality usually states whether the experience is a good or bad one.
A mean opinion score (MOS) provides a numerical indication of the quality of transmission, in the range of 1 to 5.
PESQ: Perceptual Evaluation of Speech Quality
- PESQ is an objective method of measuring speech quality.
- It predicts subjective MOS scores by comparing speech recordings that transmitted through the network under test with original versions of these speech recordings (Processed Speech Files) that were input to the network under test ( Reference Speech Files).
- PESQ returns a score from 4.5 to -0.5, with higher scores indicating better quality.
The PESQ algorithm doesn’t provide a comprehensive evaluation of the transmission quality. It Only measures the effects of one-way speech distortion and noise of speech quality.
- So the effects of loudness loss, delay, side-tone and echo aren’t reflected in the PESQ scores.
It’s Possible to have high PESQ scores, yet poor quality of the connection overall.
Accuracy of PESQ algorithm must be determines by comparing PESQ with MOS scores.
PESQ does not attempt to define what ‘quality’ is; the purpose of the PESQ algorithm is to objectively predict the subjective mean opinion scores listening setup.