Automated speech quality monitoring tool based on perceptual evaluation

Abstract

The paper deals with a speech quality monitoring tool which we have developed in accordance with PESQ (Perceptual Evaluation of Speech Quality) and is automatically running and calculating the MOS (Mean Opinion Score). Results are stored into database and used in a research project investigating how meteorological conditions influence the speech quality in a GSM network. The meteorological station, which is located in our university campus provides information about a temperature, a humidity, a dew point, a rain, a wind speed and an atmospheric pressure. The developed tool generates a call every five minutes through GSM network, a reference sample is transmitted and finally the MOS is calculated in PESQ model. The human ear performs a time-frequency transformation and in PESQ this is modelled by a short term FFT with a Hann window. The final PESQ score is a linear combination of the average disturbance value and the average asymmetrical disturbance value. The aim of our research project is to investigate a correlation between the speech quality in GSM and meteorological data. The paper describes our tool which automatically generates and calculates the MOS in GSM network.