Evaluation of a system for F0 contour prediction for european portuguese

Abstract

This paper presents the evaluation of a system for speech F0 contour prediction for European Portuguese using the Fujisaki model. It is composed of two command-generating sub-systems, the phrase command sub-system and the accent command sub-system. The parameters for evaluating the ability of each sub-system are described. A comparison is made between original and predicted F0 contours. Finally, the results of a perceptual test are discussed.