Cognitive Signal Processing Group

Research Areas

Robust systems and algorithms for automatic speech and pattern recognition:

Our group's activities are focused on achieving optimal information integration in  machine perception. We are working on a tighter coupling of machine learning and statistical signal processing, aiming at a closer interaction of graph algorithms, probabilistic modelling and deep learning.

On the applications side, we are using audiovisual input for highly robust speech recognition, reliable and interpretable human-machine interaction, and for video-based speech quality enhancement.

Signal processing and machine learning are also used as tools for technical diagnostics and automatic fault monitoring.


Situation-aware human-machine interaction:

We are developing systems that support human users during difficult tasks as well as in learning new skills.

One area of focus is multi-modal and situated interaction, which we address in collaboration with Honda Research Institute Europe. Situated interaction is important whereever human and machine are to solve tasks cooperatively in a shared environment, such as in driver assistance systems:


see M. Heckmann, N. Steinhardt, D. Orth, B. Bolder, M. Dunn, D. Kolossa: "CORA, a Prototype for a Cooperative Speech-Based On-Demand Intersection Assistant," accepted for publication, Proc. 11th Int. ACM SIGCHI Conference on Automotive UI, Utrecht, NL, Sept. 2019.


Pattern Recognition for Communication and Technical Diagnostics

While originally developed for robust speech recognition, the idea of using time-variant reliability information is also valuable for pattern analysis and recognition in general.

In collaboration with institutional and industrial partners, we are currently working on extending the idea of uncertainty-of-observation techniques both to more reliable data transmission and to the fault diagnosis of complex technical systems.


Teaching Experience: Lectures, Student Projects, Programming Courses (Matlab, Simulink) of DSP, Speech Recognition, Microprocessor Architecture

Specialties: Speech Processing, Acoustic and Audiovisual Speech Recognition, Machine Learning, Deep Learning, Signal Processing, Microprocessor Systems, Control System Design




Foto Robots