The group Speech Technology and Hearing Aids was founded by School VI of Medicine and Health Sciences in the context of the Cluster of Excellence Hearing4all in the Department of Medical Physics and Acoustics in 2021.

The new group delivers excellent research and education for better speech reception in adverse acoustic conditions. This includes applications of speech communication with mobile devices in ambient noise, hands-free communication systems with harsh acoustic feedback, and spatial hearing with binaural hearing aids. To this end, the research will rely on methods of signal processing, machine learning, and acoustic modeling.

Currently, our themes include the algorithmic optimization of speech and audio communication for hybrid video conferences with local group and single remote participants in one and the same meeting. This configuration currently proves considerable technical difficulties and therefore challenges the research. On the other hand, the hybrid conference bears huge potential for home-schooling and remote office concepts.

The challenges for speech signal processing then include the consistent fusion of speech on a local acoustic sensor network, the acoustic echo cancellation of a far-end speaker at the local end, and the spatial sound production for remote participants.