The goal of this course is to become familiar with speech recognition methods and applications. Additionally, to learn to understand the structure of a typical speech recognition system and to know how to construct one in practice.
- Preprocessing and feature extraction for speech
- Phoneme models
- Lexicon and language models
- Recognition and retrieval of continuous speech
This course includes a mandatory project. The teams are created in the first lecture, so it is important to be present! If you want to join the course, but are not able to be present in the first lecture send an email to the course staff before the first lecture (firstname.lastname@example.org)