LX8DvZFL
The problem with hearing loss is that you can't hear. In most cases, there's a loss of high-frequency hearing, you can't hear sibilants and thus can't parse the speech.
Speech-in-noise is a specific situation that HAs do not handle well. It's less of an issue with un-aided hearing thanks to the shape of our ears.
> The ideal hearing aid will amplify those frequencies at which speech is present, while suppressing frequencies that contain background noise
Every modern hearing aid does this already.
> a pretty dumb set of heuristics to figure out which is which
Dumb? Billions of dollars are waiting for the person who can make noise reduction work really really well. It's surprisingly difficult, even with unlimited computation power.
> they'll try to estimate how far the source of the noise is
This is 100% fiction. No HA on the planet calculates distance-to-noise.
You can spot the HAs that do because they require three microphones not in a straight line. Probably a triangle.
You might be thinking of beamforming, where the HA calculates the direction of the sound and can optionally focus amplification on sounds coming from that direction. Typically, sounds behind the listener are amplified less than sounds coming from in front of the listener. This is a useful refinement done by every modern HA.
> wind sounds or rustling paper also gets amplified
That is unfortunate. There is significant research going into recognising speech patterns so that the HA can make these decisions better. Unfortunately, none have shown useful results yet.
> huge opportunity here to apply deep learning
To do what, exactly? Why DL? How do you propose to run DL on a 1MHz CPU with 16kb of RAM and a battery the size of a bee's genitals?
> It's a challenging hardware problem
The hardware has been known and fixed for 20 years. What would you change? Software is where all of the improvements have come from for a very long time.
> deep learning part of it has largely been solved
Cite me a paper and we can make billions.
The reality is that you have basically no pitch perception. 16 frequency bands across, say, the four octaves that music is interesting? You're lucky to discriminate half-octaves let alone semitones.
Temporal aspects of music come through alright. I suppose you could be a drummer.
The tech is easy and well-known. Being able to legally sell the product without getting sued? That's hard.
- mics
- DSPs
- drivers (speakers)
- custom wireless chipset
- batteries
i.e. all of the stuff that you need to build a regular HA. The differences are that:
- they have shorter battery life (but a lower capacity battery)
- built in larger quantities
- not 'medical grade'
Telecoil doesn't add significantly to the cost, but it does use a bit of internal volume. They are incredibly useful and are not going away anytime soon.
It's not like you need the 2017 model of HA; for most people the 2000 model would be just fine, and (for the company) the costs of IC development and regulatory have long been recovered. ASICs are expensive to produce, but not that expensive that it adds thousands to the COGS.
The real reason is simple market forces: people will pay a lot of money for healthcare. Insurance coverage in the target market determines much of the price.
Current material refers to 'bodyworn' for babies and toddlers who tend to lose BTEs. You get the same BTE, but it's strapped more firmly to the body.
If you're paying out of pocket, I strongly recommend that you check out eBay. Second-hand gear is quite cheap.