A Bayesian approach to non-intrusive quality assessment of narrow-band speech is presented. The speech features used to assess quality are the sample mean and variance of band-powers evaluated from the temporal envelope in the channels of an auditory filter-bank. Bayesian multivariate adaptive regression splines (BMARS) is used to map features into quality ratings. The proposed combination of features and regression method leads to a high performance quality assessment algorithm that learns efficiently from a small amount of training data and avoids overfitting. Use of the Bayesian approach also allows the derivation of credible intervals on the model predictions, which provide a quantitative measure of model confidence and can be used to identify the need for complementing the training databases.
Cite as: Petkov, P.N., Mossavat, I.S., Kleijn, W.B. (2009) A Bayesian approach to non-intrusive quality assessment of speech. Proc. Interspeech 2009, 2875-2878, doi: 10.21437/Interspeech.2009-43
@inproceedings{petkov09_interspeech,
author={Petko N. Petkov and Iman S. Mossavat and W. Bastiaan Kleijn},
title={{A Bayesian approach to non-intrusive quality assessment of speech}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={2875--2878},
doi={10.21437/Interspeech.2009-43}
}