List of Tables

1. La performance de RN pour apprendre le problème et sa réaction aux exemples non-vus.
2. Le coefficient de corrélation de quelques mesures objectives existantes de la qualité de la parole avec MOS.
3. Le coefficient de corrélation de quelques mesures objectives existantes de la qualité de la parole avec MOS en considérant les paramètres de codage et de réseau.
4. Les coefficients de corrélation d'EMBSD, de MNB et d'E-model avec MOS en considérant les paramètres de réseau.
5. Comparaison entre GD, LM, LM2 et AM-LM pour le premier problème .
6. Comparaison entre GD, LM, LM1 et LM2 pour le deuxièmes problème.
7. Standard video resolution formats.
8. ITU 5-point quality scale
9. ITU 9-point quality scale
10. Number of hops and one-way delay statistics between the peers (Site) and Rennes (ENST-B) one.
11. The quality databases for both Arabic and Spanish languages to train and test the NN.
12. Performance of the NN to learn the problem and react to non-seen examples.
13. Correlation coefficient of some existing objective speech quality measures with MOS. Results are taken from the literature. Only the encoding impairments are considered.
14. Correlation coefficient of some existing objective speech quality measures with MOS for both network and encoding impairments.
15. Correlation coefficient of EMBSD, MNB and E-model with MOS for VoIP impairments. Source is [57].
16. A portion of the scoring sheet distributed to each subject.
17. The quality database to train and test the NN (before being normalized)
18. Some entries from the ENSTB trace.
19. Some entries from the training database after being normalized between 0 ...1.
20. Comparison between GD, LM, LM2 and AM-LM for the first problem.
21. Comparison between GD, LM, LM1 and LM2 for the second problem.