Learning Outcomes
Students gain
- Understanding of the most important principles of human-computer interaction.
- Basic knowledge of multimodality and multimodal interacttion.
- Basic knowledge of the gestural interaction.
- Basic knowledge of speech production and perception.
- Basic knowledge of speech recognition, acoustic feature extraction, and sequence modeling.
- Basic knowledge of audio-visual and multimodal speech recognition.
- Basic knowledge of machine learning and data mining.
- Basic knowledge of machine translation and dialogue systems.
- Presentation and knowledge transfer skills.
Students will be able to
- use the learned knowledge for designing exemplary human-computer interfaces
Content
IV „Computer-supported Interaction“:
This course gives an overview over statistical methods and their application on speech recognition, extraction of metadata (identity, age, gender, speech), audio-visual speech recognition, multi-lingual speech recognition, speech translation, multimodal interfaces: applications and technology (multimodal fusion und fission), Information Retrieval, Beamforming and microphon-arrays.
Description of Teaching and Learning Methods
Lecture part: Lecture with practical presentations.
Seminar part: Practical and theoretical presentations by students (optional).