Naturalness in a high-level synthetic speech systemM. A. A. Tatham, E. Lewis, Naturalness in a high-level synthetic speech system. Proceedings of the 4th European Conference on Speech Communication. ISSN 1018-4074, pp. 1815–1818. September 1995. No electronic version available.
Naturalness in synthetic speech is to a large extent determined by how well the system models the variability in human speech. Good models of variability are now emerging, and this paper describes how variability of several different types is incorporated into SPRUCE - a high level text-to-speech synthesis system. The synthesiser is carefully engineered to the requirements of a recent computational model of speech production. The resulting voice output illustrates the usefulness of well-motivated theory in speech synthesiser design.