AI headphones let you listen to one person in a crowd by one glance
1–5 of 5 posts
Re: AI headphones let you listen to one person in a crowd by one glance
#2I just went to get my hearing checked for the first time, and it's fine, the doctor said my responses are great for someone my age.
But in a noisy environment - not even that noisy, just kind of any noise at all - I'm functionally deaf. My child was telling me something while rubbing two balloons together and I had to get her to put them down before I could parse what she was saying.
I know there's obvious privacy issues with this thing, but man, it would be great to be able to pop in a pair of earbuds and be able to hold a conversation with someone while cars are driving nearby.
Re: AI headphones let you listen to one person in a crowd by one glance
#3The non-AI version is better: Using multiple microphones, you can use time-of-flight to isolate multiple voices in a crowd, and separate them into distinct, clear audio tracks.
Re: AI headphones let you listen to one person in a crowd by one glance
#4I just went to get my hearing checked for the first time, and it's fine , the doctor said my responses are great for someone my age. But in a noisy environment - not even that noisy, just kind of any noise at all - I'm functionally deaf. My child was telling me something while rubbing two balloons together and I had to get her to put them down before I could parse what she was saying. I know there's obvious privacy i…
I'm similar - I feel as though how quiet or high-pitched someone can physically hear must be a largely separate matter from how well their brain can separate out and process speech.
If all the processing is on-board, I don't think there'd be privacy issues beyond noise-cancelling headphones.
Re: AI headphones let you listen to one person in a crowd by one glance
#5The non-AI version is better: Using multiple microphones, you can use time-of-flight to isolate multiple voices in a crowd, and separate them into distinct, clear audio tracks.
This does make use of multiple microphones and timing between sound waves arriving. To my understanding, the machine learning part allows it to work even as the speaker/wearer move relative to each other, such as if you turn your head.