SCOOT: Synthesis Toolkits
Merlin
Merlin is a toolkit for building Deep Neural Network models for statistical parametric speech synthesis developed at CSTR Edinburgh by a team led by Simon King. It must be used in combination with a front-end text processor (e.g., Festival) and a vocoder (e.g., STRAIGHT or WORLD).
Merlin comes with recipes to show you how to build state-of-the art systems.
Merlin is free software, distributed under an Apache License Version 2.0, allowing unrestricted commercial and non-commercial use alike.
This video tutorial for Merlin is from Simon King
Festival
Festival, developed at CMU (Alan Black) and CSTR Edinburgh (Simon King) ‘offers a general framework for building speech synthesis systems as well as including examples of various modules. ‘ It is multilingual and there are online demos .
Festvox
from the CMU speech group ‘aims to make the building of new synthetic voices more systemic and better documented, making it possible for anyone to build a new voice. There are close connections to Festival. Festvox offers
- Documentation, including scripts explaining the background and specifics for building new voices for speech synthesis in new and supported languages.
- Specific scripts to build new voices in supported languages, such as US and UK English.
- Aids to building synthetic voices for limited domains
- Example speech databases to help building new voices.
- Links, demos and a repository for new voices.’