Czech Emotional Prosody in the Mirror of Speech Synthesis

Contemporary speech synthesisers still provide a fairly monotonous and tedious output when used for longer Czech texts. One of the ways how to make these texts more lively is the synthesis of emotionally coloured speech. In the present paper we focus on the modelling of real-speech-based emotions in synthetic speech and the subsequent assessment of emotionally coloured utterances in listening tests with the aim of determining the role that individual prosodic parameters play in the identification of each emotion.