Emotion Identification for Evaluation of Synthesized Emotional Speech

Steidl S, Polzehl T, Bunnell HT, Dou Y, Muthukumar PK, Perry D, Prahallad KS, Vaughn C, Black AW, Metze F (2012)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2012

Original Authors: Steidl Stefan, Polzehl Tim, Bunnell H. Timothy, Dou Ying, Kumar Muthukumar Prasanna, Perry Daniel, Prahallad Kishore, Vaughn Callie, Black Alan W., Metze Florian

Conference Proceedings Title: Proc. Speech Prosody 2012

Event location: Shanghai CN

URI: http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2012/Steidl12-EIF.pdf

Abstract

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 test.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Steidl, S., Polzehl, T., Bunnell, H.T., Dou, Y., Muthukumar, P.K., Perry, D.,... Metze, F. (2012). Emotion Identification for Evaluation of Synthesized Emotional Speech. In Speech Prosody Special Interest Group (Eds.), Proc. Speech Prosody 2012. Shanghai, CN.

MLA:

Steidl, Stefan, et al. "Emotion Identification for Evaluation of Synthesized Emotional Speech." Proceedings of the Speech Prosody 2012, Shanghai Ed. Speech Prosody Special Interest Group, 2012.

BibTeX: Download