Share Email Print
cover

Proceedings Paper

Predictive model for determining the quality of a call
Author(s): M. Voznak; J. Rozhon; P. Partila; J. Safarik; M. Mikulec; M. Mehic
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper the predictive model for speech quality estimation is described. This model allows its user to gain the information about the speech quality in VoIP networks without the need of performing the actual call and the consecutive time consuming sound file evaluation. This rapidly increases usability of the speech quality measurement especially in high load networks, where the actual processing of all calls is rendered difficult or even impossible. This model can reach its results that are highly conformant with the PESQ algorithm only based on the network state parameters that are easily obtainable by the commonly used software tools. Experiments were carried out to investigate whether different languages (English, Czech) have an effect on perceived voice quality for the same network conditions and the language factor was incorporated directly into the model.

Paper Details

Date Published: 22 May 2014
PDF: 9 pages
Proc. SPIE 9118, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XII, 91180Y (22 May 2014); doi: 10.1117/12.2050661
Show Author Affiliations
M. Voznak, VŠB-Technical Univ. of Ostrava (Czech Republic)
J. Rozhon, VŠB-Technical Univ. of Ostrava (Czech Republic)
P. Partila, VŠB-Technical Univ. of Ostrava (Czech Republic)
J. Safarik, VŠB-Technical Univ. of Ostrava (Czech Republic)
M. Mikulec, VŠB-Technical Univ. of Ostrava (Czech Republic)
M. Mehic, VŠB-Technical Univ. of Ostrava (Czech Republic)


Published in SPIE Proceedings Vol. 9118:
Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XII
Harold H. Szu; Liyi Dai, Editor(s)

© SPIE. Terms of Use
Back to Top