Skip to Content

A Sense of Hearing Could Make Cars Safer and More Reliable

Startup OtoSense makes software that can listen for sirens or engine trouble.
Espen Friberg

Most car owners know what it’s like to hear a new clink or grinding noise coming from the engine and wonder how costly the fix will be.

Startup OtoSense is working with major automakers on software that could give cars their own sense of hearing to diagnose themselves before any problem gets too expensive. The technology could also help human-driven and automated vehicles stay safe, for example by listening for emergency sirens or sounds indicating road surface quality.

OtoSense has developed machine-learning software that can be trained to identify specific noises, including subtle changes in an engine or a vehicle’s brakes. French automaker PSA Group, owner of brands including Citroen and Peugeot, is testing a version of the software trained using thousands of sounds from its different vehicle models.

Under a project dubbed AudioHound, OtoSense has developed a prototype tablet app that a technician or even car owner could use to record audio for automated diagnosis, says Guillaume Catusseau, who works on vehicle noise in PSA’s R&D department.

Espen Friberg

Tests have shown that the system can identify unwanted noises from the engine, HVAC system, wheels, and other components. It makes the correct diagnosis 95 percent of the time. Catusseau says PSA is now considering how what he dubs a “bionic ear” could be deployed to speed up repairs and make customers happier. “Buzz, squeak, or rattle is a great concern for car owners,” he says. “The customer will perceive the vehicle as being of low quality, [and] this can affect repurchase intent.”

Sebastian Christian, CEO of OtoSense, says the software could be built into vehicles so they can automatically flag potential problems that electronic sensors can’t. Leading U.S. automakers are also testing OtoSense’s technology to see how a sense of hearing can help vehicles understand their environment. (Christian declines to identify them publicly, citing nondisclosure agreements.)

One idea the startup has tested involves adding accelerometers to a vehicle’s windshield to effectively turn it into a giant microphone. Christian says that the physical properties of windshields make this design good at detecting sirens and the direction they come from.

That could help a self-driving vehicle stay safe, and allow a human-driven car to inform its driver where to look out for an emergency vehicle. (Google previously disclosed that microphones that detect sirens were part of the bundle of sensors on its self-driving vehicles, which are now being developed by a separate company, Waymo.)

Audio sensors could also let a vehicle understand the nature of the road surface, for example how icy or snowy it is, says Christian. His company works with chip maker Analog Devices to embed the software needed to understand sound into low-cost processors.

Automakers have made sensors such as cameras and radar commonplace in high-end vehicles to support cruise control and safety features. Rajesh Rajamani, a professor at the University of Minnesota who works on novel applications for sensors, says the low cost of audio hardware suggests the technology could make it to market quickly if the current R&D proves it to be useful.

“You can spread a lot of microphones around a car without it becoming very expensive, and compared to vision, sound is much less computationally intensive to analyze,” he says.

Indeed, the potential power of low-cost sound analysis means OtoSense isn’t the only company trying to use it to help machinery stay healthy. For example, Augury, another startup, is using the same basic approach to spot problems in HVAC systems (see “This Gadget Can Tell What’s Wrong with Your Air Conditioner by Listening to It”).

Keep Reading

Most Popular

Scientists are finding signals of long covid in blood. They could lead to new treatments.

Faults in a certain part of the immune system might be at the root of some long covid cases, new research suggests.

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.