Publication detail

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

VOZŇÁK, M. ROZHON, J. MIKULEC, M. ŘEZÁČ, F. KOMOSNÝ, D. CHUN-WEI LIN, J. FOURNIER-VIGER, P.

Original Title

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

English Title

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

Type

conference paper

Language

en

Original Abstract

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 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.

English abstract

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 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.

Keywords

Delay; E-model; Jitter; Neural Networks; Packet Loss; PESQ

Released

16.09.2016

ISBN

9781510824232

Book

Proceedings of the 2016 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS)

Pages from

1

Pages to

5

Pages count

5

BibTex


@inproceedings{BUT141087,
  author="Miroslav {Vozňák} and Jan {Rozhon} and Martin {Mikulec} and Filip {Řezáč} and Dan {Komosný} and Jerry {Chun-Wei Lin} and Philippe {Fournier-Viger}",
  title="Employing the neural networks to parametrically assess the quality of a voice call",
  annote="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 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.",
  booktitle="Proceedings of the 2016 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS)",
  chapter="141087",
  howpublished="online",
  year="2016",
  month="september",
  pages="1--5",
  type="conference paper"
}