After successful completion of the course, students
are able to understand and implement basic algorithms and designs of
Cognitive User Interfaces (CUI). The students will also get an overview of
existing CUIs and learn about their pros and cons.

• Introduction to CUIs
• Human cognition and perception models for CUIs
• Hidden-Markov-models (Training, Adaptation, Recognition, Synthesis)
• Acoustic speech synthesis with unit selection, Hidden Markov Models (HMM), Deep Neural Networks (DNN), Wavenet, hybrid models
• Acoustic speech recognition
• Visual speech synthesis
• Multimodal and spoken dialog systems

Didactics:

The exercise consists of a theoretical and practical part where we will develop a speech synthesizer. For the practical part you have to work in a group of 3-5 students and record a speaker from the group and train a statistical synthesizer with the recordings and let it talk. The recordings will be made in a professional recording room.

Lecture based on slides, work out examples in the exercises,
train an acoustic model in the exercises in a group.

ECTS-Breakdown:
20 h Lecture + Exercise
23 h Preparation of exercise
30 h Preparation for exam
2 h written exam
------
75 h total = 3 ECTS

Written exam, work out examples on the blackboard,
hand in of an acoustic model and generated samples of a speech synthesizer
in a group.