Multi-level Exemplar-Based Duration Generation for Expressive Speech Synthesis

The generation of duration of speech units from linguistic information, as one component of a prosody model, is considered to be a requirement for natural sounding speech synthesis. This paper investigates the use of a multi-level exemplar-based model for duration generation for the purposes of expressive speech synthesis. The multi-level exemplar-based model has been proposed in the literature as a cognitive model for the production of duration. The implementation of this model for duration generation for speech synthesis is not straightforward and requires a set of modifications to the model and that the linguistically related units and the context of the target units should be taken into consideration. The work presented in this paper implements this model and presents a solution to these issues through the use of prosodic-syntactic correlated data, full context information of the input example and corpus exemplars.