Gábor Olaszy

Learn More
This paper gives an overview of the design and development of an experimental restricted domain corpus-based unit selection text-to-speech (TTS) system for Hungarian. The experimental system generates weather forecasts in Hungarian. 5260 sentences were recorded creating a speech corpus containing 11 hours of continuous speech. A Hungarian speech recognizer(More)
Prosody generation relates to the composition of the detailed time structure of continuous speech and the realisation of the fundamental frequency and intensity structure, embedded in it. In our model a complex function set is described for the three prosody components for read speech. Each of the three prosody components is modelled separately by a(More)