Parametrization of a Slovak speech database for mobile platform speech synthesis

One of the main topics in the area of user-friendly human machine interface is speech synthesis. The paper deals with the application of harmonic plus noise model (HNM) for preparation of compressed speech database in a format that is that is useful for easy prosodic modification of the synthesized speech. The HNM approach of speech representation allows us to reduce significantly the database of speech segments for a concatenative or diphone speech synthesis, too.