In context: Most new headphones come with some form of noise cancellation. How it works is random. Apple’s AirPods are pretty good. Cheaper brands like Earfun are mediocre. But none seem to cancel external noise 100%.
Engineers from the University of Washington have developed a set of headphones that achieve near-complete noise cancellation through machine learning. The headphones, dubbed ClearBuds, were recently demonstrated at the Association for Computing Machinery’s International Conference on Mobile Systems, Applications and Services. Besides the obvious application in audio wearables, the AI cancellation technique could be used in home speakers and to help robots track their location.
A short video (below) shows the headphones silencing a vacuum cleaner and even another person’s voice. The method effectively isolates the speaker’s voice without any sound interference. Other methods tested still allow part of the background noise to pass. Of course, a practical demo would be more convincing.
archyde news
Like other noise canceling technologies, ClearBuds uses two microphones to capture speaker and external sounds. However, the way it processes signals is entirely different.
Maruchi KimPhD candidate at the Paul G. Allen School of Computer Science and Engineering at UoW, Explain that each earbud creates two synchronized high-resolution audio streams containing data about the direction of each captured sound. This technique allows the AI to create a spatial audio profile of the environment and isolate the speaker’s voice and noise sources more precisely than bidirectional mics.
“Because the speaker’s voice is close and about the same distance from both headphones, the neural network was trained to focus only on their speech and filter out background sounds, including other voices. ”, said the co-author of the study. Ishaan Chatterjee Explain. “This method is largely similar to how your ears work. They use the time difference between the sounds in your left and right ears to determine the direction the sound is coming from.”
Most high-quality earbuds have mics on each earbud, but Allen says only one is actively sending audio for processing at any given time. With ClearBuds, each earbud constantly sends simultaneous audio streams. This method required scientists to develop a specialized Bluetooth network protocol for headphones that synchronizes the two streams within 70 microseconds of each other.
Although the ClearBuds are a bit larger than some of the more popular compact headphones available, the AI processing still needs to be done by a connected device that can run the AI. The team is working to make the neural network algorithms more efficient so that the processing can happen on the headphones.
The researchers did not mention a marketing plan. However, once their work is fully completed, manufacturing a commercial product or licensing the technology is highly likely.