Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A DIY Audio Induction Loop for the Hard of Hearing

spectrum.ieee.org

Post reply on HN
Print view View original

1–10 of 12 posts

Re: A DIY Audio Induction Loop for the Hard of Hearing

#2

Post by jws »

That takes care of half of the problem.

You will be a complete hero if you write up how to do "blind signal separation" with an economical microphone array. Such a device can be ceiling mounted and use copious heaps of mathematics to locate speaking people and isolate just their voice, attenuating other room noise and echos.

There are likely affordable hardware candidates, the $55 ESP32-Lyra-TD development board with 3 microphones or the MATRIX Voice with 8 at $75. Both have special hardware for the signal processing.

Re: A DIY Audio Induction Loop for the Hard of Hearing

#3

Post by deadlyllama »

In my recent experience in churches in New Zealand, newer hearing aids either don't have T-coils, or the audiologist has to turn them on (and hasn't), or the hearing aid owner does but doesn't know how.

10-20 years ago everyone had a T-coil and loop systems were a great option. Now they're not.

Re: A DIY Audio Induction Loop for the Hard of Hearing

#4

Post by ampdepolymerase »

jws wrote: post #2

That takes care of half of the problem. You will be a complete hero if you write up how to do "blind signal separation" with an economical microphone array. Such a device can be ceiling mounted and use copious heaps of mathematics to locate speaking people and isolate just their voice, attenuating other room noise and echos. There are likely affordable hardware candidates, the $55 ESP32-Lyra-TD development board with…

You will almost certainly need a neural accelerator for this, neural networks are currently the only known effective solution for cocktail party problems.

Re: A DIY Audio Induction Loop for the Hard of Hearing

#5

Post by dieselerator » 

  What I am about to write here is similar to third hand information.
  I do not have first hand experience.

  I looked into putting an audio loop into a venue.  I asked an audiologist
  about the prevalence of T-coil equipped hearing aids.  She told me most
  users prefer small and rechargeable.  There is not much space in the unit
  and rechargeable would likely be selected.  So, the T-coil does not get
  included.  She thought T-coil units were common in Europe.

  There are special amplifiers to drive the audio loop.  The makers don't
  tell us much about them.  I think we would call those transconductance
  amplifiers.  Reading the subject article is encouraging.  Perhaps we
  will just try this after the virus is not such a threat.

Re: A DIY Audio Induction Loop for the Hard of Hearing

#6

Post by nitrogen »

ampdepolymerase wrote: post #4
jws wrote: post #2

That takes care of half of the problem. You will be a complete hero if you write up how to do "blind signal separation" with an economical microphone array. Such a device can be ceiling mounted and use copious heaps of mathematics to locate speaking people and isolate just their voice, attenuating other room noise and echos. There are likely affordable hardware candidates, the $55 ESP32-Lyra-TD development board with…

You will almost certainly need a neural accelerator for this, neural networks are currently the only known effective solution for cocktail party problems.

If you have many microphones then you are probably just beamforming, which is pure math.

Re: A DIY Audio Induction Loop for the Hard of Hearing

#7

Post by dmitrygr »

ampdepolymerase wrote: post #4
jws wrote: post #2

That takes care of half of the problem. You will be a complete hero if you write up how to do "blind signal separation" with an economical microphone array. Such a device can be ceiling mounted and use copious heaps of mathematics to locate speaking people and isolate just their voice, attenuating other room noise and echos. There are likely affordable hardware candidates, the $55 ESP32-Lyra-TD development board with…

You will almost certainly need a neural accelerator for this, neural networks are currently the only known effective solution for cocktail party problems.

How did the world arrive to this, that we think that NNs solve everything? Beamforming requires zero NNs and works wonderfully (it is all math).

Re: A DIY Audio Induction Loop for the Hard of Hearing

#8

Post by m463 »

nitrogen wrote: post #6
ampdepolymerase wrote: post #4

Earlier quoted context omitted.

You will almost certainly need a neural accelerator for this, neural networks are currently the only known effective solution for cocktail party problems.

If you have many microphones then you are probably just beamforming, which is pure math.

Some of these neural network things can track the speaker's face. So not necessary, but it might might make things more interesting.
Post reply on HN