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

41–50 of 109 posts

Re: Audio is the one area small labs are winning

#41

Post by nextaccountic »

hadlock wrote: post #30

Can someone reccomend to me: a service that will generate a loopable engine drone for a "WWII Plane Japan Kawasaki Ki-61"? It doesn't have to be perfect, just convincing in a hollywood blockbuster context, and not just a warmed over clone of a Merlin engine sound. Turns out Suno will make whatever background music I need, but I want a "unique sound effect on demand" service. I'm not convinced voice AI stuff is sustai…

you mean you want some ai product that generates sound effects from a textual prompt? elevenlabs has a model specifically for that

https://elevenlabs.io/sound-effects

Re: Audio is the one area small labs are winning

#42

Post by isoprophlex »

yalok wrote: post #37
isoprophlex wrote: post #35

Earlier quoted context omitted.

I refuse to believe that none of these people ever heard of Nyquist, and that noone was able to come up with "ayyy lmao let's put a low pass on this before downsampling". Edit: 2 day old account posting stuff that doesn't pass the sniff test. Hmmmm... baited by a bot?

in ~30 years of my work in DSP domain, I've seen insane amount of ways to do signal processing wrong even for simplest things like passing a buffer and doing resampling. The last example I've seen in one large company, done by a developer lacking audio/DSP experience: they used ffmpeg's resampling lib, but, after every 10ms audio frame processed by resampler, they'd invoke flush(), just for the sake of convenience of…

Haha wow, I guess that gives a very noticeable 100 Hz comb-like effect... noone cared to do a quick sanity check on that output?!

Re: Audio is the one area small labs are winning

#43

Post by troyvit »

nubg wrote: post #19
tl2do wrote: post #6

[flagged]

[flagged]

What's the point of saying that without backing it up? Either you think it's so obvious it doesn't need backing up (in which case you don't need to say it), or ...?

The reason it matters is that soon, any time somebody sees a comment they don't like or think is stupid, they'll just say, "eh a bot said that," and totally dilute the rest of the discussion, even if the comment was real.

Re: Audio is the one area small labs are winning

#46

Post by friendzis »

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…

Wrt data, it's not like there is a shortage of transcribed audio in the form of music sheets, lyrics and subtitles.

If one asks ~~nice~~ expensive enough they can even get isolated multitracks or teleprompter feeds together with the audiovisual tracks. Heck, if they wanted they could set up dedicated transcription teams for the plethora of podcasts with the costs somewhere in the rounding error range. But you can't siphon that off of torrents and paying for training material goes against the core ethics of the big players.

Too bad you can't really scrape tiktok/instagram reels with subtitles... Oh no, oh no, oh no no no no

Re: Audio is the one area small labs are winning

#48

Post by friendzis »

troyvit wrote: post #43
nubg wrote: post #19

Earlier quoted context omitted.

[flagged]

What's the point of saying that without backing it up? Either you think it's so obvious it doesn't need backing up (in which case you don't need to say it), or ...? The reason it matters is that soon, any time somebody sees a comment they don't like or think is stupid, they'll just say, "eh a bot said that," and totally dilute the rest of the discussion, even if the comment was real.

We are *quickly* approaching a Tuesday where "bot detected, opinion rejected" is going to be a default assumption.
Post reply on HN