Experimental brain-controlled hearing aid can pick out voices in a crowd


Study that through surgery enhanced the ability of epileptic patients to pick voices out in a noisy crowd:
Obviously, won’t be very practical unless a non-surgical approach can be devised.

Readable Popular Account:

Original Research Paper:

Selection of Other Articles Listed in Google News Covering Same:

Edit_Update: The gist of what a normal brain does to enhance a particular voice that current external HA’s cannot do and what the implant in epilectic patients undergoing surgery attempts to mimic (quoted from StatNews article-1st link)

" Mesgarani started his mining in the brain. He and his graduate adviser discovered in 2012 that when people converse, the listener’s brain waves echo the acoustic features of the speaker’s voice, turning up its perceived volume and filtering out extraneous voices.

That ability comes from the brain’s secondary auditory cortexes, one behind each ear. They amplify one voice over others by the simple means of paying attention, in a process called top-down control. (“Top” means an executive function such as conscious attention; “down” means a sensory function, in this case hearing.) The sound of a familiar voice, a familiar word (one’s name), an emotionally resonant word ( divorce ) or tone, or other attention-grabber causes this region to increase the perceived volume of what grabs its attention.

The brain-controlled hearing aid first separates the audio signals of different speakers. It then determines the spectrogram, or voiceprint, of each, meaning how a voice’s volume and frequency vary with time. Next, it detects the brain waves in a listener’s auditory cortex (via an implanted 16-by-16 electrode array), which indicate what voice the listener is paying attention to. Finally, the system searches for that particular voice and amplifies it, and only it. When the listener’s attention turns to a different voice, the system quiets the first one and dials up the volume on the new one."

1 Like

Hearing aids that read your brain will know who you want to hear [MIT]

Interesting and hopeful. It’s difficult to imagine a non-surgical analogue of this unless it’s a helmet plugged into a battery backpack. It seems more likely that a medical treatment will arrive first. At the moment you have candidate drugs for synaptopathy from Otonomy and Decibel Therapeutics at the pre-clinical stage. Then you have candidate drugs for hair cell regeneration from Frequency Therapeutics and the Regain consortium. There are some indications that regenerating hair cells will have a beneficial effect on the ribbon synapses. Loss of connections in the ribbon synapses that connect the hair cells to the auditory nerve pathways to the brain are thought to be a major cause of problems with hearing in noise. My understanding anyway.



Being at age 73, it’s probably not too likely in my lifetime that a miracle fix is going to come along. I’m more interested in what’s going on out of intellectual curiosity. I didn’t read the original research article (yet) but I wonder what sort of computational power is required, too? (that’s where the battery backpack comes in, right?!!). Perhaps some alternative setup is a possible. Auditory algorithms that can filter out individual voices as suggested in the article, directional localization of the sources of those voices, and then rather than monitor auditory cortical activity with scalp electrodes or whatever, the equivalent of Google Glasses or Hololenses that detects that you’re gazing at person X and so you must want to hear person X’s voice, so that gets selectively served up (no implants or scalp eletrodes required). And we thought HA’s are expensive now …



Here is another link



What these guys in Mannheim doing is also interesting. A contact lens for the ear and an implant:


This is very close to completion - apparently clinical trials starting soon or already underway in a clinic in Germany and they plan on selling the aid next year.



or focus with your Google glasses on someone you want to hear. Tap your watch. Repeat. System holds the last three voices you tapped on and ups the gain on them and only them. Something like that?

1 Like