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

Audio is the one area small labs are winning

amplifypartners.com

Post reply on HN
Print view View original

11–20 of 109 posts

Re: Audio is the one area small labs are winning

#11

Post by derf_ »

tl2do wrote: post #6

[flagged]

Also, while the author complains that there is not a lot of high quality data around [0], you do not need a lot of data to train small models. Depending on the problem you are trying to solve, you can do a lot with single-digit gigabytes of audio data. See, e.g., https://jmvalin.ca/demo/rnnoise/

[0] Which I do agree with, particularly if you need it to be higher quality or labeled in a particular way: the Fisher database mentioned is narrowband and 8-bit mu-law quantized, and while there are timestamps, they are not accurate enough for millisecond-level active speech determination. It is also less than 6000 conversations totaling less than 1000 hours (x2 speakers, but each is silent over half the time, a fact that can also throw a wrench in some standard algorithms, like volume normalization). It is also English-only.

Re: Audio is the one area small labs are winning

#12

Post by tl2do »

garyfirestorm wrote: post #10
tl2do wrote: post #7

Earlier quoted context omitted.

True, but there's a fun irony: the Rebels' X-Wings are powered by GPUs from a company that's... checks relationships ...also supplying the Empire. NVIDIA's basically the galaxy's most successful arms dealer, selling to both sides while convincing everyone they're just "enabling innovation." The real rebels would be training audio models on potato-patched RP2040s. Brave souls, if they exist.

not sure about the irony - you can't really expect rebels to start their own weapons manufacturing lab right from converting ore into steel... these things are often supplied by a large manufacturer (which is often a monopoly) why is it any different for a startup to tap into nvidia's proverbial shovel in order to start digging for gold?

[flagged]

Re: Audio is the one area small labs are winning

#13

Post by tl2do »

derf_ wrote: post #11
tl2do wrote: post #6

[flagged]

Also, while the author complains that there is not a lot of high quality data around [0], you do not need a lot of data to train small models. Depending on the problem you are trying to solve, you can do a lot with single-digit gigabytes of audio data. See, e.g., https://jmvalin.ca/demo/rnnoise/ [0] Which I do agree with, particularly if you need it to be higher quality or labeled in a particular way: the Fisher data…

[flagged]

Re: Audio is the one area small labs are winning

#14

Post by nowittyusername »

Good article and I agree with everything in there. For my own voice agent I decided to make him PTT by default as the problems of the model accurately guessing the end of utterance are just too great. I think it can be solved in the future but, I haven't seen a really good example of it being done with modern day tech including this labs. Fundamentally it all comes down to the fact that different humans have different ways of speaking, and the human listening to them updates their own internal model of the speech pattern. Adjusting their own model after a couple of interactions and arriving at the proper way of speaking with said person. Something very similar will need to be done and at very fast latency's for it to succeed in the audio ml world. But I don't think we have anything like that yet. It seems currently best you can do is tune the model on a generic speech pattern that you expect to fit over a larger percentage of the human population and that's about the best you can do, anyone who falls outside of that will feel the pain of getting interrupted every time.

Re: Audio is the one area small labs are winning

#16

Post by adithyassekhar »

tl2do wrote: post #12
garyfirestorm wrote: post #10

Earlier quoted context omitted.

not sure about the irony - you can't really expect rebels to start their own weapons manufacturing lab right from converting ore into steel... these things are often supplied by a large manufacturer (which is often a monopoly) why is it any different for a startup to tap into nvidia's proverbial shovel in order to start digging for gold?

[flagged]

Your reply has a 0% ai score yet the presence of that "reply to" text is concerning.

Re: Audio is the one area small labs are winning

#17

Post by etherus »

echelon wrote: post #8
dkarp wrote: post #3

There's too much noise at large organizations

They're focused on soaking up big money first. They'll optimize down the stack once they've sucked all the oxygen out of the room. Little players won't be able to grow through the ceiling the giants create.

Why would they do that? Once they have their win-condition, there's no reason to innovate. Only to reduce the costs of existing solutions. I expect that unless voice becomes a parameter which drives competition and first-choice for adoption, it will never become a focus of the frontier orgs. Which is curious to me, as almost the opposite of how I'm reading your comment.
Post reply on HN