Lucerne/Stäfa ZH – In a project by Lucerne University of Applied Sciences and Arts and the company Sonova, mobile robots are measuring how sound behaves in rooms. The experts want to use this to create the data basis for new algorithms that can simulate the propagation of sound. This should help to improve hearing aids.
Lucerne University of Applied Sciences andArts (HSLU) and hearing aid manufacturer Sonova are working together to gain a better understanding of sound propagation in a room. According to a press release, a student project is collecting data in various rooms and situations. Sonova contributes its knowledge of hearing acoustics, audio technology, signal processing and electroacoustics. HSLU contributes its expertise in robotics, software development, room acoustics and audio signal analysis and processing. The project is funded by the Innosuisse innovation agency.
"If these detailed measurements are carried out manually by people, they are extremely time-consuming," says HSLU acoustics expert Prof. Dr. Armin Taghipour. That's why he and his team have developed mobile robots that do this autonomously. Unlike before, the robots can independently measure both the volume of background noise and the room acoustics.
The data material generated in this way will serve as the basis for algorithms that can simulate different room situations and furnishings using machine learning. "Because the most important prerequisite for machine learning to work is large amounts of data," explains Hannes Wüthrich, Project Manager at Sonova.
Unlike written texts or images, where it is usually possible to fall back on existing data sets, acoustic data would first have to be generated. The ultimate aim of this project is to improve the quality of hearing aids in large rooms or with loud background noise, for example, and thus make communication easier for people with hearing loss. ce/mm