FestVox: Building Synthetic Voices
This project is designed to provide the tools, scripts and documentation to allow people to build synthetic voices for use with general speech applications. Support for English and other languages is provided. Voices produced by these methods run within Edinburgh University's Festival Speech Synthesis System. We are also developing a small, fast synthesis engine suitable for these voices called Flite. This project involves a number of aspects of speech synthesis research, including prosodic modeling, unit select synthesis, statistical parametric synthesis, diphone synthesis, text analysis, lexicon representation and limited domain synthesis. It also provides a forum for research and development of automatic labeling tools and synthesis evaluation tools. Recent work investigates processing languages without written forms, and stylistic variation including emotion, casual and specific speaker styles.