In the Computational Audition group, we are interested in the relation of machine learning and biological systems - with a special focus on the auditory system. Central questions are how sensory input (ranging from simple acoustic stimuli to complex signals such as speech) are processed and represented by the human brain, and how this processing can be transferred to machine learning.
Our main goals are to better understand biological systems and apply our findings to current problems in pattern analysis (for instance, by creating models of computational audition or improving automatic speech recognition).
Follow the links below to learn more about our current projects.
- Dr. Jörn Anemüller: Statistical modelling
- Dr. Bernd T. Meyer: Automatic speech and audio processing
- Prof. Dr. Dr. Birger Kollmeier