Employing the neural networks to parametrically assess the quality of a voice call

The paper deals with the modelling of the network effects on the quality of speech in the Voice over IP networks. The main purpose of the ideas presented here is to achieve high-precision estimation of the speech quality in the environment in which the classical approaches of speech quality determination fail. To achieve such a high precision a modular neural network model is used to map the effects of a packet loss on the speech quality based on the PESQ (Perceptual Evaluation of the Speech Quality) reference. To incorporate the temporal effects, the Emodel is partially utilized as well. This way a universal tool capable of harnessing the information about the speech quality for stress testing and monitoring of the local infrastructure has been developed enabling the telephony infrastructure administrators to evThe paper deals with the modelling of the network effects on the quality of speech in the Voice over IP networks. The main purpose of the ideas presented here is to achieve highprecision estimation of the speech quality in the environment in which the classical approaches of speech quality determination fail. To achieve such a high precision a modular neural network model is used to map the effects of a packet loss on the speech quality based on the PESQ (Perceptual Evaluation of the Speech Quality) reference. To incorporate the temporal effects, the Emodel is partially utilized as well. This way a universal tool capable of harnessing the information about the speech quality for stress testing and monitoring of the local infrastructure has been developed enabling the telephony infrastructure administrators to evaluate the performance and stability of the systems in their hands. Moreover, a high-performance simulation environment has been developed.aluate the performance and stability of the systems in their hands. Moreover, a high-performance simulation environment has been developed.