ESTIMATION OF RADIO SIGNAL QUALITY DEGRADATION BY MEANS OF NEURAL NETWORK AND NON-PARAMETRIC REGRESSION MODEL


Cite item

Full Text

Abstract

In this paper we present an approach which allows us to avoid expansive and time consuming subjective assessments of audio quality degradation caused by different nature distortions while transmitting and receiving of stereo audio signal through the radio channel. This approach is based on the basic version of PEAQ (Perceptual Evaluation of Audio Quality) originally developed mainly for audio codec estimation. The MOV (Model Output Variables) vector of the PEAQ method is mapped to the audio quality degradation scale using two different models: neural networks and non-parametric regression. The results of two independent approaches are compared.

About the authors

S Zablotskiy

T Muller

W Minker

References

  1. ITU-R Recommendation BS.1387, Method for Objective Measurements of Perceived Audio Quality, Dec. 1998.
  2. Kabal P. An Examination and Interpretation of ITU-R BS.1387: Perceptual Evaluation of Audio Quality // Department of Electrical & Computer Engineering, McGill University, Canada, 2002.
  3. Anderson J. A. An Introduction to Neural Network, The MIT Press, 1995.
  4. Nadaraya E. On estimating regression, Theory of Probability and its Applications. 1964. Vol. 10. P. 186-190.
  5. Hagan M. T. Neural Network Design (Electrical Engineering). PWS Pub. Co. 1995.
  6. Goldberg D. E. Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Professional. 1989.
  7. Holland J. H. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. The MIT Press. 1992.
  8. Haupt R. L. Practical Genetic Algorithms, Wiley-Interscience. 1997.
  9. Wand M., Jones M. Kernel Smoothing. New York : Chapman and Hall. 1995.

Supplementary files

Supplementary Files
Action
1. JATS XML

Copyright (c) 2010 Zablotskiy S., Muller T., Minker W.

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies