Modelling F_0 Dynamics in Unit Selection Based Speech Synthesis

摘要

In the common unit selection implementations, F_0 continuity is measured as one of concatenation cost features with the expectation that smooth units transition (regarding speech melody) is ensured when the difference of F_0 is low enough. This measure generally uses a static F_0 value computed at the units boundary. In the present paper we show, however, that the use of static F_0 values is not enough for smooth speech units concatenation, and that a dynamic nature of the F_0 contour must be taken into account. Two schemes of dynamic F_0 handling are presented, and speech generated by both schemes is compared by means of listening tests on specially selected phrases which are known to carry unnatural artefacts. Advantages and disadvantages of the individual schemes are also discussed.