Wireless Personal Communications

, Volume 96, Issue 4, pp 5375–5389 | Cite as

Prediction of Speech Quality Based on Resilient Backpropagation Artificial Neural Network

  • Lukas Orcik
  • Miroslav Voznak
  • Jan Rozhon
  • Filip Rezac
  • Jiri Slachta
  • Homero Toral-Cruz
  • Jerry Chun-Wei Lin


The paper presents a system for monitoring and assessment the speech quality in the IP telephony infrastructures using modular probes. The probes are placed at key nodes in the network where aggregating packet loss data. The system dynamically measures speech quality and results are collected on a central server. For data analysis we applied four-state Markov model for modeling the impact of network impairments on speech quality, afterwards, the resilient back propagation (Rprop) algorithm was used to train a neural network. Information about the speech quality are displayed in the form of automatically generated graphs and tables. The proposed solution has been tested with selected codecs and further generalizes the already presented concepts of the speech quality estimation in the IP environment.


Markov models Neural networks Speech quality Network probes 


  1. 1.
    Rezac, F., Voznak, M., & Tomala, K. (2015). Voice Messaging System as a Form of Distribution of an Urgent Information. Wireless Personal Communications, 85(1), 63–76.CrossRefGoogle Scholar
  2. 2.
    ITU-T, Recommendation P.862.1: Mapping function for transforming P.862 raw result scores to MOS-LQO. International Telecommunication Union (2004)Google Scholar
  3. 3.
    Rango, F., Tropea, M., Fazio, P., & Marano, S. (2006). Overview on VoIP: Subjective and objective measurement methods. International Journal of Computer Science and Network Security, 6(1), 140–153.Google Scholar
  4. 4.
    De Rango, F., Fazio, P., Scarcello, F., & Conte, F. (2014). A new distributed application and network layer protocol for VoIP in mobile ad hoc networks. Mobile Computing, IEEE Transactions on, 13(10), 1233–1536.CrossRefGoogle Scholar
  5. 5.
    Frnda, J., Voznak, M., Rozhon, J., & Mehic, M. (2012). Prediction Model of QoS for Triple Play Service. In 21st Telecommunications Forum TELFOR, pp. 733-736. Belgrade.Google Scholar
  6. 6.
    Hecht, J. (2014). All smart, no phone. Spectrum, IEEE, 51(10), 36–41. New York.CrossRefGoogle Scholar
  7. 7.
    Pocta, P., Holub, J., & Mrvova, M. (2009). Impact of different active-speech-ratios on PESQ’s predictions in simulated VoIP environment. Acta Acustica united with Acustica, 95(5), 950–957.CrossRefGoogle Scholar
  8. 8.
    Kadioglu, R., Dalveren, Y., & Kara, A. (2015). Quality of service assessment: A case study on performance benchmarking of cellular network operators in Turkey. Turkish Journal of Electrical Engineering and Computer Sciences, 23(2), 548–559.CrossRefGoogle Scholar
  9. 9.
    Sunder, D.S., & Kushwaha, R.K. (2015). Evaluation of narrow band speech codecs for Ubiquitous Speech Collection and Analysis Systems. In xtitProceedings International Conference on Industrial Instrumentation and Control, ICIC 2015, art. no. 7150718, pp. 93–98Google Scholar
  10. 10.
    Raake, A. (2007). Speech quality of VoIP: Assessment and prediction. Chichester: John Wiley & Sons.Google Scholar
  11. 11.
    Khan, H. A., & Sun, L. (2008). Assessment of speech quality for VoIP applications using PESQ and E-Model. Advances in Communications, Computing, Networks and Security, 7, 263–273.Google Scholar
  12. 12.
    Sun, L., & Ifeachor, E. C. (2006). Voice quality prediction models and their application in VoIP networks. IEEE Transactions on Multimedia, 8(4), 809–820.CrossRefGoogle Scholar
  13. 13.
    Fazio, P., De Rango, F., & Selvaggi, I. (2010). A novel bandwidth reservation algorithm based on neural networks path prediction in wireless environments. In Proceedings International Symposium on Perf. Evaluation of Computer and Telecommunication Systems (SPECTS 10), Ottawa.Google Scholar
  14. 14.
    De Rango, F., Tropea, M., Santamaria, A. F., & Marano, S. (2007). An enhanced QoS CBT multicast routing protocol based on Genetic Algorithm in a hybrid HAPSatellite system. Computer Communications, 30(16), 3126–3143.CrossRefGoogle Scholar
  15. 15.
    Meky, M., & Saadawi, T. (1997). Prediction of speech quality usingradial basis functions neural networks. In Proceedings of Second IEEE Symposium on Computers and Communications, Alexandria, pp.174–178.Google Scholar
  16. 16.
    Mrvova, M., & Pocta, P. (2013). Quality estimation of synthesized speech transmitted over IP channel using genetic programming approach. In Proceedings International Conference on Digital Technologies (DT), Zilina, pp. 39–43.Google Scholar
  17. 17.
    Rozhon, J., Rezac, F., Slachta, J., & Voznak, M. (2014). Monitoring of speech quality in full-mesh networks. Communications in Computer and Information Science, 431, 157–166.CrossRefGoogle Scholar
  18. 18.
    OpenWRT-Wireless Freedom,
  19. 19.
    Summerfield, M. (2013) Python in Practice: Create Better Programs Using Concurrency, Libraries, and Patterns, 1st edition. Addison-Wesley Professional, IndianaGoogle Scholar
  20. 20.
    Barret, D. J., Silverman, R. E., & Byrnes, R. G. (2005). SSH, The secure shell: The definitive guide (2nd ed.). Sebastopol: O’Reilly Media.Google Scholar
  21. 21.
    Paramiko - SSH2 Protocol for Python,
  22. 22.
    Klucik, S., Chromy, E., & Baronak, I. (2015). Model to Increase the Number of Output States of a Random Variable Using a Histogram Based PDF. Wireless Personal Communications, 85(1), 137–149.CrossRefGoogle Scholar
  23. 23.
    Burget, R., Komosny, D., & Ganeshan, K. (2012). Topology aware feedback transmission for real-time control protocol. Journal of Network and Computer Applications, 35(2), 723–730.CrossRefGoogle Scholar
  24. 24.
    Igel, C., & Husken, M. (2000). Improving the Rprop Learning Algorithm. In Proc. of the Second International Symposium on Neural Computation, NC2000, ICSC Academic Press, 115–121.Google Scholar
  25. 25.
    Elliot, D. (1993). A Better Activation Function for Artificial Neural Networks. ISR Technical Report TR 93-8, University of Maryland.Google Scholar
  26. 26.
    Friedman, T., Caceres, R., & Clark, A. (2003). RTP Control ProtocolExtended Reports (RTCP XR). IETF Network Working Group, RFC 3611.Google Scholar
  27. 27.
    Clark, A. (2001). Modeling the Effects of Burst Packet Loss and Recency on Subjective Voice Quality. Colombia: IPtel Workshop.Google Scholar
  28. 28.
    Voznak, M., Rezac, F., & Rozhon, J. (2013). Speech quality assessment using computational E-model and its implementation. International Journal of Mathematics and Computers in Simulation, 7(3), 277–285.Google Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Lukas Orcik
    • 1
  • Miroslav Voznak
    • 1
  • Jan Rozhon
    • 1
  • Filip Rezac
    • 1
  • Jiri Slachta
    • 1
  • Homero Toral-Cruz
    • 2
  • Jerry Chun-Wei Lin
    • 3
  1. 1.VSB-Technical University of OstravaOstravaCzech Republic
  2. 2.University of Quintana RooChetumalMexico
  3. 3.School of Computer Science and TechnologyHarbin Institute of Technology Shenzhen Graduate SchoolShenzhenChina

Personalised recommendations