The present research aims at a partial model for synthesized text into
nation, restricted to utterances consisting of a single intonation phr
ase. Intonational characteristics of short utterances in different pos
itions within a paragraph are investigated. The effects of position in
the paragraph on sentence prosody are mainly located in the beginning
of the utterance. A model is formulated to capture the main findings.
The model is then perceptually evaluated. The results indicate that t
he model can be used to improve the naturalness of rule-based intonati
on in a system for automatic text-to-speech conversion.