Prosody and synthesis techniques

In the remainder of this chapter we shall concentrate on prosody prediction, the term given to the task of generating the prosodic form from the text. In Chapter 9 we complete the task by considering the issue of prosody synthesis, the job of generating phonetic or acoustic information from the prosodic form. As we shall see, the degree to which prosody needs to be specified depends very much on the synthesis technique employed 

---

We now turn to unit selection synthesis which is the dominant synthesis technique in text-to-speech today. Unit selection is the natural extension of second generation concatenative systems, and deals with the issues of how to manage large numbers of units, how to extend prosody beyond just FO and timing control, and how to alleviate the distortions caused by signal processing. 

First generation techniques usually require a quite detailed, low-level description of what is to be spoken. For purposes of explanation, we will take this to be a phonetic representation for the verbal component, along with a time for each phone, and an FO contour for the whole sentence. The phones will have been generated by a combination of lexical lookup, LTS rules and post-lexical processing (see Chapter 8), while the timing and FO contour will have been generated by a classical prosody algorithm of the type described in Chapter 9. It is often convenient to place this information in a new stmcture called a synthesis specification. Hence the specification is the input to the synthesiser and the waveform is the output. 

Second generation techniques are characterised by a hybrid approach of using data to determine the behaviour of the verbal or phonetic part of synthesis, and an explicit model plus signal processing to generate the correct prosody. 

---