Hacker News Reader

Comment by pontus | Hacker News Reader

With all the advances in tech, why does it seem that hearing aids are still from the 80s?

I guess ultimately you're limited by your interface to the brain (something maybe neuralink could address?), but even still shouldn't there be some "magic" machine learning stuff going on in this space? Not at all an expert in audio processing, but I would imagine that we could do a decent job distinguishing voices from background noise, automatically thresholding sound in different environments, and possibly modulating sounds into different frequency bands when there are e.g. multiple speakers.

For all I know, stuff like this is already going on.

View on HN

My mother, who's fully deaf in one year and mostly deaf in the other, has heavily depended on strong and expensive hearing aids her whole life.

Over the years her hearing aids have improved in battery life, gotten smaller, and improved in things like filtering background noise. Every new hearing aid would start by sounding distorted and weird but her brain adapts to the new sounds after a couple of weeks.

The single largest life improvement I've seen for her was about 10 year ago when she could finally get a hearing aid with bluetooth. Suddenly she didn't have to decide between the "whistling" (feedback) or not hearing to talk on the phone. We got her an iPad and she stopped watching TV almost entirely and now watches YouTube and Netflix. And she can do her yoga over Skype.

Her biggest challenge, at this point, isn't a hearing aid problem but a bluetooh one. Her iPhone inconstantly switches between her hearing aid and her Volkswagen (pre-CarPlay).

I agree hearing aids are stuck in the past, but I'm also convinced most of the problems are lower hanging fruit than a neuralink :).

If she likes watching on a TV, the Apple TV can talk to bluetooth audio devices. Have never tried it, but it would probably be able to talk to the hearing aids directly.

Both https://audatic.ai/ and https://whisper.ai/ are taking the ML approach for speech enhancement, and the large companies are starting to get on board. It's the future!

These days they are fairly sophisticated; my hearing aids will automatically switch between several different programs depending on the environment. (It doesn't work how I'd like it to, though, so I have a program that I manually set for music.) There is also a phone app for adjusting settings, though it's limited and buggy.

It's difficult to evaluate hearing aids because they are proprietary. Reading about the features in a brochure for a hearing aid is like reading the features for a TV set or stereo. Who knows what those trademarked terms really mean when it comes to how the code works?

Would be cool to create an open standard and perhaps even open source the development. If nothing else, I would imagine that there are quite a few hearing impaired engineers and scientists out there that would gladly work on something like this if it meant that they themselves could benefit from the improvements.

I agree! We're working on this at AudioFocus (YC S19). You can see an old demo here: https://www.audiofocus.io/demo

There are a lot of challenges with putting this in a hearing aid: low latency inference (10ms), small power budget, consistent performance, fault tolerance, etc. Still a fair amount of R&D to be done, but change is coming.

Is it too difficult to ask for one that distributes the processes between phone/external device, rims of glasses and in the ear speaker. It will go a long way in addressing the issue of stigma and enabling more people to use it early.

A big hurdle for doing this is latency, every time you hop from one device to another you're adding at least ~10ms of latency if it's over anything like bluetooth. There might a clever way to do it, it's something I'm thinking about but it's too early to say.

For now it looks like it's going to be a behind-the-ear hearing aid. Maybe in 5-10 years it could fit in your ear canal.

How many microphones do you need to do this filtering? I wear hearing aids myself and if you can do it that that level on a real hearing aid that would be amazing.

In this demo there is only one microphone on the phone. But we're working on stereo (2) microphones now. That will help make it more reliable, lower latency, and give you spatial awareness (awareness of the direction of sound).

Glad you're excited about it!

Reply on news.ycombinator.com