ARTICULATORY FEATURES FOR EXPRESSIVE SPEECH SYNTHESIS

This paper describes some of the results from the project entitled "New Parameterization for Emotional Speech Synthesis" held at the Summer 2011 JHU CLSP workshop. We describe experiments on how to use articulatory features as a meaningful intermediate representation for speech synthesis. This parameterization not only allows us to reproduce natural sounding speech but also allows us to generate stylistically varying speech. We show methods for deriving articulatory features from speech, predicting articulatory features from text and reconstructing natural sounding speech from the predicted articulatory features. The methods were tested on clean speech databases in English and German, as well as databases of emotionally and personality varying speech. The resulting speech was evaluated both objectively, using techniques normally used for emotion identification, and subjectively, using crowd-sourcing.