Perceived speech quality prediction for voice over IP-based networks

Perceived speech quality is the key metric for QoS for VoIP applications. The primary aims of the study reported in the paper are to carry out a fundamental investigation of the impact of packet loss and talkers on perceived speech quality using an objective method to provide the basis for developing an artificial neural network (ANN) model to predict speech quality for VoIP. The impact of packet loss (e.g. loss burstiness, loss patterns and packet size) and different talkers on speech quality was investigated for three modern codecs (G.729, G.723.1 and AMR) using the new ITU PESQ algorithm. Results show that packet loss burstiness, loss locations/patterns and the gender of talkers have an impact on perceived speech quality. Packet size has, in general, no obvious influence on perceived speech quality for the same network conditions, but the deviation in speech quality depends on packet size and codec. Based on the investigation, we used talkspurt-based conditional and unconditional packet loss rates (instead of network packet loss rates because they are perceptually more relevant), codec type and the gender of the talker (extracted from decoder) as inputs to an ANN model to predict speech quality directly from network parameters. Results show that high prediction accuracy was obtained from the ANN model (correlation coefficients for the test and validation datasets were 0.952 and 0.946 respectively). This work should help to develop efficient, nonintrusive QoS monitoring and control strategies for VoIP applications.