ETSI - TR 102 948
Speech and multimedia Transmission Quality (STQ); Quality Assessment of Synthesized Speech
|Publication Date:||1 December 2012|
The present document provides information about the impact of specific types of packet loss and coding on speech quality predictions provided by ITU-T Recommendations P.862 [i.6], P.863 [i.39] and P.563 [i.9] models, when both naturally-produced and synthesized speech are used. The variability of the predictions with respect to the type of signal (naturally-produced or synthesized) and the loss conditions was evaluated. Moreover, the accuracy of predictions provided by the investigated models was assessed by comparing these predictions with subjective assessments.
The results indicate one implication for designers of speech communication systems.
It has to be emphasized that none of the instrumental algorithms investigated here (P.862, P.863 and P.563) were validated for synthesized speech. The presented analysis is a use case which is out-of-scope for these algorithms.