THIS CONTENT IS BROUGHT TO YOU BY SINTEF - read more
Why is it difficult for AI to distinguish between the sound of excavators and seagulls?
A new AI-based sound metre can manage to do this.
Do you want to know how much noise there is at a construction site?
Then you want to measure the sound of the excavator or the hammer drill, but you don’t want to measure seagulls, traffic noise, or a helicopter flying by.
A new sound measurement service can now do just that. With the help of artificial intelligence – and that is by no means a given, says Femke B. Gelderblom, a senior researcher at SINTEF.
Sound is confusing for AI
“Sound and artificial intelligence research is still quite an immature field when compared to what AI can do with images or text," says Gelderblom.
Audio is apparently very difficult, even though it is an easy concept for us humans to understand.
"Explaining that a certain sound comes from the same source as a similar sound, albeit from a greater distance, can quickly confuse an AI model,” she says.
But Gelderblom and her colleagues at SINTEF have figured it out. They collaborated on a research project with Norsonic, a Norwegian company that makes equipment for measuring sounds and vibrations.
The result is a completely new product: NoiseTag.
“It’s exciting to be able to do research on topics that turn into real products,” she says.
No more seagull cries
“The challenge up to now has been that people who go through the data have to listen to each individual recording to remove the measurement data that's not relevant to the project,” says Karl Henrik Ejdfors at Norsonic.
Seagull cries at a harbour are a typical example.
"Instead of listening to seagull cries and helicopters, we train a model on these sounds and identify which sounds should be included and which should not be included in the project. Then the model automatically filters and removes those parts of the measurements,” he says.
A new microphone hears everything
Norsonic produces measuring equipment, including for ports and construction sites.
The microphones are calibrated and standardised to meet Norwegian legal requirements for noise measurement, including in the construction industry. But the microphones pick up all the sounds at the location.
When they monitor noise, they often want to know what is relevant and what isn't. A construction project is, for example, very often located next to a major road.
"The road is noisy, but that doesn’t mean the construction project shouldn’t be built because all the sources of noise make the construction site too noisy. That’s when you need to know what noise comes from the road, and what noise is from the construction project itself,” says Gelderblom.
AI doesn’t learn as quickly as we do
Research has made it possible to create models that are specific to each individual customer. This allows the noise each customer wants to measure to be isolated.
“Humans can learn this quite quickly. I recognise what I hear. Machines can also learn to do this, but it’s not as easy for them,” says Gelderblom.
This is due to things such as the surroundings and distance affecting the sound. The sound from the source changes before it reaches you. The sound can also vary even if your ear perceives it as the same type of source.
For example: one excavator may have a different engine speed than another.
For you and me, it's easy to hear that both sounds are from an excavator, but for a machine that's listening, they are two different sounds, and it has to learn that both are being produced by an excavator.
NoiseTag has just been launched.
“Typical of artificial intelligence is that it gets smarter the more we use it and the more data comes in. We’re hoping that our device will get better as more people use it,” says Gelderblom.
———
Read the Norwegian version of this article on forskning.no
More content from SINTEF:
-
Vibrations in the ground can provide clean energy
-
This special solar cell system produces both electricity and heat
-
Electric car batteries in the cold: "Almost like honey"
-
This solution could cut aviation emissions by up to 30 per cent
-
The ports of the future can float on water
-
It's tough to be a nurse: Many also have to clean and do kitchen work
