Syllabus
1. Theoretical bases of speech recognition, essential principles (HMM, neural networks, DTW, language modelling).
2. Application of these principles in available software tools.
3. Types of speech synthesis and their characteristics.
4. Closer examination of concatenative synthesis (used speech units, their coding and methods of combining).
5. Modelling prosody (especially with regard to the Czech language).
6. Practical introduction to speech synthesis using available software tools.
7. The significance of speech technology for phonetic research.
Annotation
The course introduces theoretical and practical aspects of speech technology, with the focus on speech synthesis and recognition. It examines the state of this applied research area from both the phonetic and technical viewpoint.