Having trouble hearing in a crowded room? The new “cone of silence” can help

Having trouble hearing in a crowded room?  The new

Written by Matthew Hudson

Even in a room full of loud conversations, our brains can use one voice to focus on something called the cocktail party effect. But it gets louder – or as you get older it is harder to do. Now, researchers may have figured out how to fix it using a machine learning technique called Silence and the Cone of Silence.

Computer scientists have trained a neural network that roughly mimics the wiring in the brain and recognizes and separates the voices of many people speaking in a room. The network measured how long it took for the microphones to sound in the center of the room.

When researchers tested their system with loud background noise, they found that the silence cone had two voices. Within 3.7 ° of their sources, they reported on neural information processing systems at an online-only conference this month. This is comparable to a sensitivity of only 11,500 over the previous sophisticated technology. When the researchers trained their new system in additional voices, they managed the same trick with eight voices – a sensitivity of 6.3 – even if no more than four were heard at the same time.

Such a system could one day be used for hearing aids, surveillance systems, hands-free kits or laptops. New technology, this is also possible. Keep track of moving voices. By splitting and facilitating your Zoom calls. The background noise is soothing. From vacuum cleaners to lozenges.