Voice Quality Evaluation of a Call Using Fuzzy Logic

Voice will remain a fundamental communication media that cut across people of all walks of life. It is therefore important to make it very affordable. VoIP has been increasingly popular in recent times due to its affordability, however, poor reliability and voice quality remain important factors that limit the widespread adoption of VoIP systems. Good voice quality is a key factor for users transiting from the Public Switched Telephone Network (PSTN) to VoIP networks. It has been shown that line echo is one of the key factors that deteriorate voice quality in VoIP systems. Several non-real-time algorithms have been developed in literature to estimate various aspects of voice quality in VoIP systems. But there is no real-time algorithm that estimates the echo content of a VoIP conversation, which could enable the operator take some corrective actions to improve the quality while the call is in progress. In this paper, the authors propose a real-time fuzzy algorithm to estimate the strength of the line echo component of the voice quality in VoIP networks. The results obtained shows that the algorithm is able to track and estimate echo content of a live VoIP traffic in real-time. This algorithm could be embedded in VoIP systems to enable operators monitors calls in real-time.