In the context of: Most new headphones come with some form of noise cancellation. How it works randomly. AirPods from Apple are very good. Cheaper brands like Earfun are modest. But none of them seem to cancel out outside noise 100%.
Engineers from the University of Washington have advanced A set of headphones that achieve near-total noise cancellation through machine learning. The headphones, dubbed ClearBuds, were recently shown at the Society for Computing Machinery’s International Conference on Mobile Systems, Applications, and Services. Besides the obvious application in audio, wearable devices, AI canceling technology can be used in home speakers and to help robots track their locations.
A short video (below) shows the headphones silencing the vacuum cleaner and even someone else’s voice. The method effectively isolates the speaker sound without any audio interference. Other methods tested still allow a portion of the background noise to pass through. Of course, a hands-on demonstration will be more convincing.
Like other noise-cancelling technologies, ClearBuds uses two microphones to pick up outside noises and headphones. However, the way you process the signals is completely different.
Maruchi KimPhD candidate in the Paul G. Allen College of Computer Science and Engineering at UoW, explain Each earbud creates two simultaneous high-fidelity audio streams that contain data about the direction of each captured sound. This technology allows AI to create a spatial audio profile of the environment and isolate the speaker’s voice and noise sources more accurately than two-way microphones.
“Because the speaker’s voice is close to and approximately the same distance from both speakers, the neural network was trained to focus only on their speech and filter out background sounds, including other sounds,” said the study co-author. Ishaan Chatterjee explains. “This method is very similar to how your ears work. They use the time difference between the sounds in your left and right ears to determine which direction the sound is coming from.”
Most high-end earbuds have microphones on each earpiece, but Allen says only one sends out active audio for processing at any one time. With ClearBuds, each earbud sends continuously synchronized audio streams. This method required the scientists to develop a specialized Bluetooth network protocol for the headphones that synchronized the two streams within 70 microseconds of each other.
Although the ClearBuds are slightly larger than some of the more popular built-in headphones available, AI processing still needs to be done by a connected device that can run AI. The team is working on making neural network algorithms more efficient so that processing can be done on headphones.
The researchers did not mention a marketing plan. However, once their work is fully completed, they are very likely to manufacture a commercial product or license the technology.
“Evil thinker. Music scholar. Hipster-friendly communicator. Bacon geek. Amateur internet enthusiast. Introvert.”