A Discourse Model of Affect for Text-to-Speech Synthesis
Abstract
This paper introduces a model of affect to improve
prosody in text-to-speech synthesis. It operates on the discourse
level of text to predict the underlying linguistic factors that contribute
towards emotional appraisal, rather than any particular
surface emotion itself. The architecture of the model is described
and its performance is evaluated on three levels—its predictive
accuracy on text, its effect on natural speech and its effect on
synthesised speech.
URI
https://researchspace.csir.co.za/dspace/bitstream/handle/10204/7272/Schlunz_2013.pdf?sequence=1http://hdl.handle.net/10394/26511
Collections
- Faculty of Engineering [1129]