Discourse prominence patterns

When sentences are spoken in discourses or dialogues, additional patterns can occur. One commonly cited affect is the difference in prominence levels between given and new information. This idea says that when a word is first used in a discourse, it will often be quite strong, but on second and subsequent mentions it is actually weaker, so we might have  

We can identify a second type of discourse prominence effect which we shall term emphasis. This occiu-s when a speaker wants to draw attention to a particular word  

This however also extends into affective purposes, where for example the speaker knows that the hstener will understand, but still uses extra emphasis. This could occur for example when the speaker wishes to express frustration or imply that the listener is stupid and therefore has to have everything spoken slowly or clearly. 

---

Of all the prosodic phenomena we have examined intonational tune is the most heavily related to augmentative and particularly affective content. In situations where these effects are absent, we can say to a first approximation that all utterances have in fact the same intonational tune the only differences occur as to where the pitch accents and boundary tones which make up this tune are positioned. Hence we can almost argue that for discourse neutral synthesis, there simply isn t any intonational tune prediction to be done. In other words, the real task is to predict a suitable FO contour that e q)resses the prominence and phrasing patterns and encodes the suprasegmental, rather than true prosodic patterns of the utteranee. 

While we can describe prominence and phrasing in quite abstract high level terms, this is significantly harder with intonation as all theories to a greater or lesser extent make exphcit references to FO patterns, levels and dynamics. Given this, and the fact that for the most part we are generating discourse neutral suprasegmental intonation, we will leave the entire topic of intonation until Chapter 9. 

This chapter is concerned with the issue of synthesising aconstic representations of prosody. The input to the algorithms described here varies but in general takes the form of the phrasing, stress, prominence and discourse patterns which we introduced in Chapter 6. Hence the complete process of synthesis of proso can be seen as one whereby we first extract a prosodic form representation from the text, as described in Chapter 6, and then synthesize an acoustic representation of this form, as described here. 

---