Voice Quality in VoIP Networks Based on Random Neural Networks

The growth of Internet has led to the development of many new applications and technologies. Voice over Internet Protocol (VoIP) is one of the fastest growing applications. Calculating the quality of calls has been a complex task. The ITU E-Model gives a framework to measure quality of VoIP calls but the MOS element is a subjective measure. In this paper, we discuss a novel method using Random Neural Network (RNN) to accurately predict the perceived quality of voice and more importantly to perform this on real-time traffic to overcome the drawbacks of available methods. The novelty of this model is that RNN model provides a non-intrusive method to accurately predict and monitor perceived voice quality for both listening and conversational voice. This method has learning capabilities and this makes it possible for it to adapt to any network changes without human interference. Our novel model uses three input variables (neurons) delay, jitter, and packet loss and the codec used was G711.a. Results show a good degree of accuracy in calculating Mean Option Score (MOS), compared to Perceptual Evaluation of Speech Quality (PESQ) algorithm. WAN emulation software WANem was used to generate different samples for testing and training the RNN.