Objective analysis of emotional speech for English and Slovenian Interface emotional speech databases

Vladimir Hozjan (Faculty of Electrical Engineering and Computer Science Institute of Electronics University of Maribor Smetanova17, SI - 2000 Maribor, Slovenia)

Zdravko Kacic (Faculty of Electrical Engineering and Computer Science Institute of Electronics University of Maribor Smetanova17, SI - 2000 Maribor, Slovenia)

SO9: Emotional & Specific Databases

In this paper we propose a new approach for analysis of emotional speech prosody features. The aim of the analysis is definition of emotional features that characterise emotions. Analysis was performed on emotional speech databases that were recorded in the framework of the project "Multimodal Analysis/Synthesis System for Human Interaction to Virtual and Augmented Environments" (Interface). The new approach determines emotional features in three steps. In the first step the low-level features were determined, second step includes definition of high-level features and in the last step the emotional features were determined. Emotional features for native English and native Slovenian speakers were analysed. A comparison of emotional features between English male and female speaker, English male and Slovenian male as well as English female and Slovenian female speaker was performed. New approach for analysis of emotional features enables consistent and objective analysis. It enables comparison of emotional features between different speakers and at the same time searches for new correlates of emotions in speech.

Emotions, Prosody, Database analysis, Emotional features, Emotional database

175.pdf