Text-to-speech synthesis, including text processing, and waveform generation by concatenation of diphones.
Introduction to this part of the course
What this part of the course will cover, and a first look at some of the different techniques available for synthesising speech.
The front end
We need to process the input text, first to identify the words, then to decide how they should be said.
Waveform generation
From the linguistic specification produced by the front end, we can now generate a speech waveform.
