Whether ambulance siren, wet road surface or nail in the tyre – external noises around the vehicle deliver important information that its conventional sensors can only detect with difficulty or at a late stage. Intelligent acoustic sensor systems give the car its ears and, in interaction with driver assistance systems, provide important information for driving manoeuvres or for maintenance. In autonomous vehicles, acoustic environment identification is important so that all relevant ambient influences are taken into account.

AI-based acoustic sensor systems for the automotive sector

Under the brand name The Hearing Car, the Oldenburg Branch for Hearing, Speech and Audio Technology HSA of the Fraunhofer Institute for Digital Media Technology IDMT is developing intelligent technologies for acoustic event detection as well as methods and concepts for optimum signal capture on the vehicle. The car’s sense of hearing ensures greater safety, reliability and innovative applications in road traffic.

»The acoustic detection and categorisation of events expands the vehicle’s 'senses'. As part of autonomous driving, it facilitates faster reaction times, smart decision-making for drivers, e.g. on wet tarmac, and predictive maintenance of components before malfunctions or even accidents occur,« explains Danilo Hollosi, Head of Group »Acoustic Event Detection« In addition, communication solutions for speech interaction outside the vehicle see to more comfort and safety, e.g. speech-based opening of doors or for triggering an emergency call.

Showcase event: From which direction is the emergency vehicle approaching?

In close cooperation with car manufacturers and suppliers, Fraunhofer IDMT tests its own sensor technologies and algorithms and collects test data on the test track and on the road. That is why the experts operate their own test vehicle, which visitors to DAGA can experience at scheduled times during the exhibition. Of course, this also includes a live demonstration of The Hearing Car technologies, such as acoustic environment monitoring, source localisation, signal enhancement and speech interaction with the vehicle.

The demonstration of the hearing car will take place daily from 7 to 9 March at 11:30 and 16:00 outside the main entrance of CCH – Congress Center Hamburg. Meet us at DAGA 2023 in Hamburg – we look forward to seeing you! Please register in advance by email: hsa-pr@idmt.fraunhofer.de.

»YourSound« in any situation

The Oldenburg Branch HSA has exciting developments in store for vehicle interiors, which you can try out yourself on its stand. The »YourSound« technology makes it possible to personalise the sound of audio devices quickly and intuitively and enables individual sound experiences in the car. Why? Studies show that people perceive sound individually and want to adjust it accordingly, irrespective of age or hearing ability. With conventional equalisers, personal feel-good sound is difficult to adjust, and it is always only for a specific listening situation. Unique sound personalisation with the help of the »YourSound« technology, which can be integrated into an infotainment system, forms the basis for all future audio reproduction in the vehicle. Once set, users experience an individual and better listening experience, regardless of playback volume and driving situation.

»Click« – Correct engaging of plug connections

Before the vehicle has even left the production line, the researchers from Oldenburg start listening! And at DAGA 2023 they will present an acoustic solution for such manufacturing applications. The motto: Screws were yesterday, today the car is plugged together. However, if a plug connection does not engage properly with the typical »click«, an error message is inevitable. High costs for logistics and complicated reworking – as well as annoyed customers – are often the result of incorrectly engaged connections. The remedy? A »click detector« in the form of an acoustic sensor system for in-line monitoring during assembly. »The special feature of our acoustic solution is that the system can reliably distinguish between many different types of 'click' – even in noisy production environments,« says Hollosi, describing the technology. Depending on customer requirements, both mobile integration of the system, for example at the end of the production line, and stationary integration at the workstation or on the robot arm are possible. 

Hearing, Speech and Audio Technology HSA at Fraunhofer IDMT in Oldenburg

Founded in 2008 by Prof. Dr. Dr. Birger Kollmeier and Dr. Jens-E. Appell, the Fraunhofer Institute for Digital Media Technology IDMT’s Branch for Hearing, Speech and Audio Technology HSA stands for market-oriented research and development with a focus on the following areas:

• Speech and event recognition
• Sound quality and speech intelligibility
• Mobile neurotechnology and systems for networked healthcare

With in-house expertise in the development of hardware and software systems for audio system technology and signal enhancement, over 100 employees at the Oldenburg site are responsible for transferring scientific findings into practical, customer-oriented solutions.

Through scientific cooperation, the institute is closely linked to the Carl von Ossietzky University, Jade University of Applied Sciences, and the University of Applied Sciences Emden/Leer. Fraunhofer IDMT is a partner in the »Hearing4all« cluster of excellence.

The Oldenburg Branch for Hearing, Speech and Audio Technology HSA is funded in the program »Vorab« by the Lower Saxony Ministry of Science and Culture (MWK) and the Volkswagen Foundation for its further development.