| Publication Type |
Conference Paper |
| Authors |
Iman Mossavat, Oliver Amft, Bert de Vries, Petko Petkov, Bastiaan Kleijn |
| Title |
A Bayesian Hierarchical Mixture Of Experts Approach To Estimate Speech Quality |
| Abstract |
This paper demonstrates the potential of theoretically motivated learning methods in solving the problem of non-intrusive quality estimation for which the state-of-the-art is presented by ITU.563 standard. To construct our estimator, we adopt the speech features from ITU.563, while we use a different mapping of features to form quality estimates. In contrast to ITU.563 which assumes distortion-classes to divide the feature space, our approach divides the feature space based on a clustering which is learned from the data using Bayesian inference. Despite using weaker modeling assumptions, we are still able to achieve comparable accuracy on predicting mean-opinion-scores with ITU.563. Our work suggests Bayesian model-evidence as an alternative metric to correlation-coefficient for determining the necessary number of experts for modeling the data. |
| Date |
2010 |
| Proceedings Title |
QoMEX 2010: Second International Workshop on Quality of Multimedia Experience |
| Publisher |
IEEE Signal Processing Society |
| Pages |
200–205 |
| DOI |
10.1109/QOMEX.2010.5516203 |
| Extra |
Nominated for best student paper award: http://www.qomex2010.org/Bestpapers.html |
| Full Text |
PDF |
