Improving text-to-speech synthesisMark Tatham, Eric Lewis, Improving text-to-speech synthesis. Proceedings of the Institute of Acoustics, 18 (9). ISBN 1 873082 94 0, pp. 35–42. November 1996. No electronic version available.
Naturalness in human speech is dependent on a number of factors and the extent to which a text-to-speech synthesis system can account for these factors in its underlying model will be a measure of its success in the market place. As well as the obvious factors of rhythm and intonation there is the more difficult question of modelling the variability in human speech. This paper discusses how SPRUCE, a high level text-to-speech synthesis system, incorporates several different types of variability.