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

Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

spectrum.ieee.org

Post reply on HN
Print view View original

11–20 of 60 posts

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#11

Post by Smaug123 »

tobtoh wrote: post #6

> The greatest frustration among potential users is that a hearing aid cannot distinguish between, for example, a voice and the sound of a passing car if those sounds occur at the same time. The device cranks up the volume on both, creating an incoherent din. It may be a simplification of the article that I'm misinterpreting, but as someone who got a hearing aid in early 2016, that's not how (modern) hearing aids wor…

> That blows my mind ... a bit like how do you know the color green is green. Maybe it's purple, but you have been told by someone else that it's green.

You may be interested in the "the map is not the territory" idea. "Green" is not a property of an object but of an observer, though "emits light at wavelength N" is a property of an object.

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#12

Post by rasur »

sdrothrock wrote: post #4
csours wrote: post #2

Tech starts 1/3 the way down the article (ctrl+f "clean speech") > My lab was the first, in 2001, to design such a filter, which labels sound streams as dominated by either speech or noise. With this filter, we would later develop a machine-learning program that separates speech from other sounds based on a few distinguishing features, such as amplitude (loudness), harmonic structure (the particular arrangement of to…

As someone with a cochlear implant who lives with the consequences of overly clever programmers who thought they'd "help" by filtering out noise and volume and whatever else... I really wish they wouldn't. This is a technology that makes me so angry some days that I sometimes wonder if it was worth getting implanted, even though I know it was.

This is something I do wonder about, in this context. I don't have a CI myself, but my 6 year old son does, and I am somewhat concerned that he is-or-might be experiencing partial sound "blindness" (meaning: sure speech processing is adequate but there are surely some things that are processed away). I have a fair amount of experience in music/sound-recording environments and it makes me somewhat sad for him that he's still "missing out" (although obviously this is outweighed by the fact that he can actually hear and communicate now, but I'm sure you get what I mean).

I'd get into the area myself, if I was in anyway useful with DSP code or C++..

May I ask, were your hearing issues (leading to the CI) a recent thing, or long-term? My main interest here is about using machine learning to assist people who do not know sign-language to understand signers rather than to "improve" the actual hearing process (because - personally - my S/L skills are abysmal).

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#13

Post by eb0la »

chas wrote: post #7

This approach surprised me. Why are they doing feature extraction and then feeding that into a DNN? It seems much more straightforward to have the input of the network be noisy samples and the output be clean samples a la super resolution[0] in images. They probably wouldn't want to use fully-connected layers in that instance, but I don't see any fundamental barriers if they have enough computational power to run a n…

This is the paper they submitted: http://web.cse.ohio-state.edu/~dwang/papers/CWYWH.jasa16.pdf

I'm not an expert in the hearing field, but makes sense for me: they probably know that some filters work (and are actually used) for hearing, and feeding that preprocessed data would save them training and hyperparameter tuning time.

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#14

Post by austinjp »

Smaug123 wrote: post #11
tobtoh wrote: post #6

> The greatest frustration among potential users is that a hearing aid cannot distinguish between, for example, a voice and the sound of a passing car if those sounds occur at the same time. The device cranks up the volume on both, creating an incoherent din. It may be a simplification of the article that I'm misinterpreting, but as someone who got a hearing aid in early 2016, that's not how (modern) hearing aids wor…

> That blows my mind ... a bit like how do you know the color green is green. Maybe it's purple, but you have been told by someone else that it's green. You may be interested in the "the map is not the territory" idea. "Green" is not a property of an object but of an observer, though "emits light at wavelength N" is a property of an object.

Also qualia and the knowledge argument:

https://en.m.wikipedia.org/wiki/Knowledge_argument

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#15

Post by Smaug123 »

austinjp wrote: post #14
Smaug123 wrote: post #11

Earlier quoted context omitted.

> That blows my mind ... a bit like how do you know the color green is green. Maybe it's purple, but you have been told by someone else that it's green. You may be interested in the "the map is not the territory" idea. "Green" is not a property of an object but of an observer, though "emits light at wavelength N" is a property of an object.

Also qualia and the knowledge argument: https://en.m.wikipedia.org/wiki/Knowledge_argument

Though I don't understand why it's in principle impossible for Mary to deduce what colour feels like to a standard human. Just because humans are not smart enough to model a being's internal state completely, given just the total physical information, doesn't mean it's impossible.

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#16

Post by epalmer »

tobtoh wrote: post #6

> The greatest frustration among potential users is that a hearing aid cannot distinguish between, for example, a voice and the sound of a passing car if those sounds occur at the same time. The device cranks up the volume on both, creating an incoherent din. It may be a simplification of the article that I'm misinterpreting, but as someone who got a hearing aid in early 2016, that's not how (modern) hearing aids wor…

>Hearing aids have changed my quality of life (at age 40).

I've had mine for 6 months. I'm 63 now. They have changed my life as well. I still have some tinniness but the tech has been adjusting the curve and other factors each time I visit her and this last time a few weeks ago the sound quality got much better.

There are still places where they don't work or get overwhelmed by background noise, like at a live baskeball game or football game but I can live with that. I'm now missing only a few pieces of most conversations and music sounds better as well. I also have audio dyslexia so that accounts for some inability to perceive parts of some conversations. The HA don't help with that.

One place they work for me that has some background noise is in my car. I listen to tech podscasts during my commute and most times don't have any issues unless the podcast has problems with too much dynamic range. My car (a Honda Civic) is a 2014 model and does a decent job blocking some road noise.

I was very resistant to getting hearing aids until I read about "Hearing Loss Linked to Accelerated Brain Tissue Loss" [1] and that did it. I'm trying to take reasonable steps in diet, exercise, and with nutrients to prevent or delay dementia. Like most of us here on HN I make a living with my brain and my quality of life would be impacted if I can't think through complexity and problem solving.

At thanksgiving I was talking to my father-in-law about my hearing aids and he also was resistant. He got his first pair a month ago and is extremely happy. He is 81 years old.

My doctor sells hearing aids but actually recommended that I use one of the big box store's services. With a 12 month warranty you can't really go wrong and the prices was about half of what my doctor could sell them for.

[1] http://www.hopkinsmedicine.org/news/media/releases/hearing_l...

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#17

Post by epalmer »

chx wrote: post #9
tobtoh wrote: post #6

> The greatest frustration among potential users is that a hearing aid cannot distinguish between, for example, a voice and the sound of a passing car if those sounds occur at the same time. The device cranks up the volume on both, creating an incoherent din. It may be a simplification of the article that I'm misinterpreting, but as someone who got a hearing aid in early 2016, that's not how (modern) hearing aids wor…

I probably need a hearing aid but I am very reluctant to go for a testing because the last time I had one (very long ago and very far away from Canada, I admit) I thought it was incredibly imprecise: they asked me to press a button when I could hear a sound and I was absolutely unsure whether I heard really something already or just imagined. Is it still so very subjective?

You might want to reconsider. http://www.hopkinsmedicine.org/news/media/releases/hearing_l...

Its been great for me. I've had mine for 6 months. They are not perfect but they are a big improvement. See my other comment above.

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#18

Post by stefs »

tobtoh wrote: post #6

> The greatest frustration among potential users is that a hearing aid cannot distinguish between, for example, a voice and the sound of a passing car if those sounds occur at the same time. The device cranks up the volume on both, creating an incoherent din. It may be a simplification of the article that I'm misinterpreting, but as someone who got a hearing aid in early 2016, that's not how (modern) hearing aids wor…

i'm 35 and i've got HAs for 20 years now. my hearing loss is quite severe (without aides i don't understand face to face conversation without the other person being close to shouting).

modern devices employ another trick: they "compress" frequencies you're hearing less into a spectrum that's not as damaged (this is mostly done if your hearing loss affects the frequencies used for speech).

the side effect is that music i knew from before my hearing loss got so severe sounds strange now, but the aides also got a "music" mode.

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#19

Post by petra »

Is deep learning useful for noise-cancellation headphones/earphones? It's extremely hard to design great noise cancelling, only a very few do it, and hence the prices are very high. If deep learning can reduce costs and increase competition here, i think this sector could really grow.

Re: Deep Learning enables hearing aid wearers to pick out a voice in a crowded room

#20

Post by sdrothrock »

rasur wrote: post #12
sdrothrock wrote: post #4

Earlier quoted context omitted.

As someone with a cochlear implant who lives with the consequences of overly clever programmers who thought they'd "help" by filtering out noise and volume and whatever else... I really wish they wouldn't. This is a technology that makes me so angry some days that I sometimes wonder if it was worth getting implanted, even though I know it was.

This is something I do wonder about, in this context. I don't have a CI myself, but my 6 year old son does, and I am somewhat concerned that he is-or-might be experiencing partial sound "blindness" (meaning: sure speech processing is adequate but there are surely some things that are processed away). I have a fair amount of experience in music/sound-recording environments and it makes me somewhat sad for him that he'…

Long term; I have progressive sensorineural hearing loss that was noticed when I was about two and had reached "profound" levels by the time I was about ten. Implanted in my left ear at 16.

I actually made the decision to be a part of the normal public school system and never learned sign language, partially out of stubbornness, so I can't really help with SL-related questions, though I'd be more than glad to answer hearing/CI-related questions.

Post reply on HN