Research

We focus on human-centered technologies and applications based on biosignals, such as the acquisition, recognition, and interpretation of speech, muscle activity, and brain activity.

The core themes of our work are:

Speech
Brain
Human behavior modeling

Most of our experiments are conducted in our biosignals lab. The biosignals lab consists of an interaction space that allows us to merge real and virtual interactions. It is equipped with a variety of sensory devices to capture biosignals resulting from human behavior—such as speech, movement, gaze, muscle activity, and brain activity—under controlled and less constrained, open-space conditions.

Fields of research

Silent Speech Communication

The Cognitive Systems Laboratory at the University of Bremen is working on innovative Silent Speech Interfaces, which allow humans to communicate with each other by speaking silently.

Systems for People with dementia

At the Cognitive Systems Lab, we are developing a number of systems aimed at people with dementia.

Brain activity Modeling

At the Cognitive Systems Lab we are using Near-Infrared Spectroscopy for innovative User Interfaces.

Automatic speech Recognition

Speech is the most important natural human communication form. Thus, speech recognition is the most natural interface for app.

Human Activity Recognition

At the Cognitive Systems Lab, we investigate various research areas of multimodal human activity recognition, including software development and dataset acquisition, segmentation and annotation, feature extraction, feature dimensionality study, human activity modeling, iterative training and parameter tuning, real-time recognition system, among others.

Artifact Classification during Biosignal Acquisition

This research investigates biosignal acquisition artifacts frequently occurring in experiments due to human negligence or environmental influences, such as electrode detachment, misuse of electrodes, unanticipated magnetic field interference, and signal distortion by human movements, which are not easily noticeable by experimenters or software during acquisition but can be discovered by ML in real-time.

Gesture Recognition

At the Cognitive Systems Lab we use Ineartial Measurement Units (IMUs), as well as Electromyography (EMG) to recognize gestures for innovative user interfaces.

Updated by: koehne

RSS

Print page