Modelling pitch accents for concept-to-speech synthesis.
Clark, Robert A J
MetadataShow full item record
This paper addresses the problem of generating a full range of appropriate intonation contours for concept-to-speech synthesis systems where there is a specific requirement to produce different semantic meanings and contrasts through intonation. We show improvements through the appropriate use of prosodic structure and by improving the way in which individual accent shapes are modelled.