ISCA Archive Eurospeech 1993
ISCA Archive Eurospeech 1993

Using context to specify intonation in speech synthesis

Scott Prevost, Mark Steedman

A generator based on Combinatory Categorial Grammar using a simple and domain-independent discourse model can be used to direct synthesis of intonation contours for responses to data-base queries, conveying distinctions of contrast and emphasis determined by the discourse model and the state of the knowledge-base.