Articulatory features for expressive speech synthesis
Alan W. Black, H. Timothy Bunnell, Ying Dou, Prasanna Kumar Muthukumar, Florian Metze, Daniel J. Perry, Tim Polzehl, Kishore Prahallad, Stefan Steidl, Callie Vaughn · 2012
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.