Euromasters summer school 2005

Tutorial 6: Speech synthesis using Festival - short version

Rob Clark, Korin Richmond and Simon King, University of Edinburgh, UK

This is a short introduction to the Festival 2.0 text-to-speech (TTS) system. Festival is a complete toolkit for TTS and is the most widely used system in speech synthesis research around the world. This is a hands on tutorial that covers the basics of using Festival and the background required to develop new voices for Festival.

Using Festival

We start be looking at running Festival from the users point of view, and see how Festival can be used in a number of different environments, from interactive turorial sessions to a backend server in for other language applications.

We then take a closer look at Festival's internals, to see what the synthesis process involves and to discover how Festival stores different types of data. We look at ways in which this data can be accessed and manipulated (e.g. to drive a talking head).

Building Festival Voices

We look at the different synthesis engines available in Festival and discover how voices using each technique differ. We look at what is involved in building voices of different types and what they may be suitable for.

Back to registration page

Location of tutorial files

Notes

• Instructions web page
• Slides 1
• Slides 2
• You need to disable the KDE sound server, see here