A Discourse Model of Affect for Text-to-Speech Synthesis
Loading...
Date
Authors
Schlunz, Georg I.
Barnard, Etienne
Researcher ID
Supervisors
Journal Title
Journal ISSN
Volume Title
Publisher
Pattern Recognition Association of South Africa and Mechatronics International Conference
Record Identifier
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.
Sustainable Development Goals
Description
Keywords
Citation
Georg Schlunz and Etienne Barnard, “A Discourse Model of Affect for Text-to-Speech Synthesis”, in Proc. Annual Symp. Pattern Recognition Association of South Africa (PRASA), pp 91-98, Johannesburg, South Africa, 2013. [http://engineering.nwu.ac.za/multilingual-speech-technologies-must/publications]