Smart hearing aids tailored to the individual needs of the user: Hearing Acoustics researchers at the Collaborative Research Center (CRC) have been working towards this goal for the past four years. Now the German Research Foundation (DFG) has expanded funding for the project. Directed by Prof. Dr. Volker Hohmann, an audition researcher at the University of Oldenburg, the CRC will receive up to 8.1 million euros for a second phase of funding that will run from 2022 to 2026. With the official title “Hearing Acoustics : Perceptual Principles, Algorithms “. and Applications “(HAPPAA), the CRC is focusing on the development of hearing aids and hearing aid systems that use artificial intelligence (AI) to automatically adjust to different environments, making these devices more adaptable. to the specific needs of individual users.
In addition to the University of Oldenburg, the Jade University of Applied Sciences, the Fraunhofer Institute for Digital Media Technology IDMT, the Hörzentrum Oldenburg gGmbH, the RWTH University of Aachen and the Technical University of Munich, all leading institutions in the field of auditory research, they are involved in this large-scale project that has a total duration of twelve years.
In our aging society, it is becoming more and more urgent to develop hearing aids and other communication speakers that work effectively in harsh acoustic environments and really help people in their daily lives. Oldenburg Hearing Research is doing an excellent job and is widely recognized both nationally and internationally. The German Research Foundation’s renewed funding commitment underscores this in an impressive way. “
Prof. Dr. Ralph Bruder, President of the University of Oldenburg
When humans interact with their acoustic environment
The Hearing Acoustics Collaborative Research Center brings together a variety of disciplines, including acoustics, psychoacoustics, audiology, engineering sciences, and physical modeling. The first funding period focused on the interactions between people with hearing impairments and their acoustic environment. “In real life, the hearing situation changes constantly because people react to voices and sounds. For example, they turn their head towards the sound source, or move their gaze in that direction. This is called ‘acoustic communication loop’.” , he says. Hohmann. This dynamic loop had received little attention in auditory acoustics in the past, he notes.
In recent years, the team has managed to incorporate the hearing aid into this loop of acoustic communication. “We have developed a first prototype of the so-called ‘immersive hearing aid’ that constantly assesses the acoustic situation and identifies which sound source a test person is directing their attention to at a given time,” explains Hohmann. The device determines the direction of the test person’s gaze and head movements, and then adjusts the signal processing to ensure that the target sound source can be heard optimally by the test person. The current prototype can be used in both field and laboratory experiments.
Among other factors, the new perceptual models developed by the research team for use in different auditory situations have paved the way for this success. “These models predict how a test person will perceive an audible signal in a given situation, whether or not they will be able to follow a conversation in a noisy environment, for example,” explains Hohmann. Simulation of hearing with and without hearing impairment in different hearing situations involving background noise and reverberation is essential for the development and evaluation of innovative methods for signal processing in hearing aids, he emphasizes.
Test algorithms directly to the ear
Another important result of the first funding period is the “hearpiece”, a special, especially high-quality headset for research purposes. Placed in the ear and with several built-in microphones and small speakers, the device can amplify the sound in exactly the same way as a hearing aid. Researchers can use it to test new algorithms for signal processing directly into the ear, for example. The special feature here is that the headset is acoustically transparent, which means that listening with this device corresponds to normal hearing with an open ear. “Thanks to interdisciplinary collaboration within the CRC we were able to combine acoustic and signal processing methods, and as a result, we have made considerable progress,” says Hohmann.
The team has also developed an interactive and audiovisual virtual reality installation in the laboratory to conduct auditory experiments with test subjects under controlled conditions. With this technology, real-life situations can be simulated more realistically than was possible before. To that end, the team created several complex audiovisual scenarios in which testers can “immerse themselves,” such as a virtual restaurant, a subway station, and a living room. These scenarios, along with related data, have been made available free of charge to research labs around the world so that they can conduct their own auditory experiments.
Active noise control
In the second funding period that will begin now, the CRC team plans to refine and merge its perception models, algorithms and applications. One of the goals is to develop algorithms for hearing aids and immersive hearing aids that can actively control noise depending on the acoustic scenario. To do this, researchers use cutting-edge AI methods that they developed themselves. The long-term goal is for each hearing aid to constantly learn and improve when it comes to predicting which settings are optimal for the respective user in a specific situation. People with hearing impairments should be able to enter the necessary comments themselves via their smartphone. “However, we still have a lot of work to do before we reach that goal,” Hohmann notes.
The team is also working to establish international standards for complex acoustic scenarios in auditory research and audiology in order to facilitate and improve the exchange between different laboratories. In addition, the CRC aims to develop new auditory-acoustic tests in virtual environments that allow researchers to better identify differences in individual perception. This should make it possible to design diagnostic and rehabilitation measures for hearing aids that are optimally adapted to individual needs.
The Collaborative Research Center complements the research conducted by the Cluster of Excellence Hearing4all, which is also led by researchers from the University of Oldenburg. In addition, it actively supports doctoral projects for early-stage scientists with its own integrated research training group.