A discourse model of affect for text-to-speech synthesis

Abstract

This paper introduces a model of affect to improve prosody in text-to-speech synthesis. It operates on the discourse level of text to predict the underlying linguistic factors that contribute towards emotional appraisal, rather than any particular surface emotion itself. The architecture of the model is described and its performance is evaluated on three levels—its predictive accuracy on text, its effect on natural speech and its effect on synthesised speech.