Auxiliary generation for prosody

Firstly, let us separate the issue of generating a signal that contains a particular prosodic effect (for example surprise, or accentuation of a particular word) from the issue of deciding how to do this automatically from the text. The issue of the realisation of a particular prosodic form is by no means easy, but it is certainly more tractable than the second issue. In essence it is no different from other parts of the synthesis problem in that we can collect data with this effect, stu how suprasegmental features vary with respect to this effect and so on. 

---