System for prosodic modification of corpus synthetized Slovak speech

In this article, a design of an improvement of a TTS system for Slovak speech synthesis is desribed. The improvement consists of a new type of parametric corpus storing, that allows prosodic modification of the speech in real-time processing. This approach is based on a HNM (harmonic plus noise) model that represents speech signals as a sum of a harmonic and a noise part. The decomposition of speech signal into these two parts enables more natural sounding modifications of the signal. The parametric representation of speech provides a straightforward way of changing prosodic features of the speech. Our algorithm is based on the parametric storing approach, where the speech is stored not as usual by PCM coding, but as sinusoidal parameters of HNM model.