Lecture Sprachsynthese / Speech Synthesis

(Here you will find binding study regulations and module handbooks. )

© TU Dresden / STKS

In the lecture Sprachsynthese we deal with the artificial generation of speech signals from text ("text-to-speech"), as we encounter it today in more and more applications. We start with the pre-processing of text, such as text normalization and the generation of sound sequences. We then look at methods for describing and generating prosody, in particular speech melody. On this basis, we deal with various methods for generating the actual speech signal. These include classical methods such as formant synthesis and concatenation synthesis, but also articulatory speech synthesis (simulation models of the vocal tract, vocal folds and acoustics) and the latest methods of neural synthesis.

If required, the lecture can be held in English or supported by English-language materials.

The lecture is suitable for

Also suitable for students of other technical disciplines.

Recommended knowledge: Systemtheorie I and II, Signalverarbeitung, Signalanalye and Mustererkennung

The lecture is always offered in the winter semester.

Please register for participation and for further information in the corresponding Opal course.

Lecture Sprachsynthese in the learning platform OPAL