
Hieronimus is a Research Assistant in the Signal Processing for Medical Applications Group at Helmut Schmidt University, where he focuses on improving speech quality and intelligibility in challenging acoustic environments.
He holds a B.Sc. and M.Sc. in Electrical Engineering and Information Technology from the Technical University of Darmstadt, with a specialization in Communication Technology and Sensor Systems. His Bachelor’s thesis was conducted in the Signal Processing Group, where he evaluated speaker models using multiple metrics to ensure reliable performance in speaker verification tasks. His Master’s thesis, completed in the Communication Systems Group with collaboration from MimoSense, focused on designing a system-theoretical approach to compensate for nonlinearities in flexible, printed force sensors.
Since May 2026, Hieronimus has been working on multichannel speech enhancement, aiming to recover clear and intelligible speech from noisy and reverberant recordings. His research explores how deep learning and model-based methods can be combined to suppress background noise, echo, and room reflections—especially in real-world applications such as hearing aids and multimedia devices. The models should not only be robust and accurate but also computationally efficient, ensuring that they are lightweight enough to be deployed on resource-constrained devices.
Letzte Änderung: 6. November 2026