Carnegie Mellon University
file.pdf (118.61 kB)
Download file

Emotion Identification for Evaluation of Synthesized Emotional Speech

Download (118.61 kB)
journal contribution
posted on 2012-05-01, 00:00 authored by Stefan Steidl, Tim Polzehl, H. Timothy Bunnell, Ying Dou, Prasanna Kumar Muthukumar, Daniel Perry, Kishore Prahallad, Callie Vaughn, Alan Black, Florian MetzeFlorian Metze

In this paper, we propose to evaluate the quality of emotional speech synthesis by means of an automatic emotion identification system. We test this approach using five different parametric speech synthesis systems, ranging from plain non-emotional synthesis to full re-synthesis of pre-recorded speech. We compare the results achieved with the automatic system to those of human perception tests. While preliminary, our results indicate that automatic emotion identification can be used to assess the quality of emotional speech synthesis, potentially replacing time consuming and expensive human perception tests


Publisher Statement

Copyright 2012 ISCA