LANGUAGE AND SPEECH GENERATION

The paper describes a system that produces spoken monologues derived f rom information in a database. The sentences of these monologues are g enerated from templates of syntactic structures, which may contain ope n slots in which other elements, usually noun phrases, can be inserted . It is shown how these sentences string together to form a coherent m essage. This message has to be pronounced correctly, which means, amon g other things, that it has to be prosodically acceptable. The paper i ndicates how linguistic information is used to arrive at an acceptable prosodic structure, which, in turn, feeds into a module which takes c are of the phonetic realization of the monologue.