News for hackers. Stuff that matters.

A comment on Using AI to compress audio files for quick and easy sharing.

Re:Using AI to compress audio files for quick and easy sharing by guggle on Monday October 31, 2022 @02:07AM (#33402542)
> we are the first to make it work for 48 kHz sampled stereo audio (i.e., CD quality)

"CD quality" is 44.1khz over 16bit.

> We achieve an approximate 10x compression rate compared with MP3 at 64 kbps, without a loss of quality.

but then later:

> The key to lossy compression is to identify changes that will not be perceivable by humans

[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by augustuspolius on Monday October 31, 2022 @02:32AM (#33402647)
It's quite amazing how they can build something so ingenious and yet make such a glaring mistake in the announcement post (48 kHz CD quality).

On your second point: they probably meant that there is no loss in perceived quality, of course it's a lossy algorithm.

6kbps sound demo is really impressive! Initially I was turned off by aliasing artifacts (hiss) but to be fair 6kbps is a really really low bitrate.

[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by guggle on Monday October 31, 2022 @02:46AM (#33402707)
It is impressive, but it's also not something I would want to use for music listening. I guess the "10x" goal makes for an impressive chart, but I'd like to know what are the more realistic goals and gains.
[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by augustuspolius on Monday October 31, 2022 @03:03AM (#33402786)
The interesting part to me was that they used specifically a 64kbps example, not a higher bitrate that would be more appropriate for music listening. Just speculating, but if they managed to get 10x higher compression rate compared to 64kbps MP3, could they achieve an even higher compression rate when compared to 320kbps MP3? If the algorithm is so good that it can compress audio down to 6kbps with just a few artifacts, would it sound almost good at 12kbps? 24kbps?

Between this effort and the recently announced Google-led multi-channel/immersive audio codec initiative, I am pretty excited about the future of audio streaming and distribution.

[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by beardyw on Monday October 31, 2022 @03:26AM (#33402911)
> they used specifically a 64kbps example, not a higher bitrate that would be more appropriate for music listening.

... but only if you are a bat.

[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by genewitch on Monday October 31, 2022 @08:30PM (#33415384)
Bitrate as it pertains to the size is the purpose of all of this.
[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by brokenmachine on Thursday November 03, 2022 @12:49AM (#33447139)
>recently announced Google-led multi-channel/immersive audio codec initiative

Link?

[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by bongobingo1 on Monday October 31, 2022 @05:15AM (#33403494)
> not something I would want to use for music listening

The flute in particular suffers quite a lot and the triangle disappears completely!

[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by Workaccount2 on Monday October 31, 2022 @10:42AM (#33406418)
It is something you would want though if you are hosting content with audio consumed by people who aren't paying attention to audio quality.
[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by Dwedit on Monday October 31, 2022 @01:35PM (#33409450)
Because writeups are done at the last second, rather than as part of the project.
[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by bscphil on Monday October 31, 2022 @03:14AM (#33402849)
> While such techniques have been explored before for speech, we are the first to make it work for 48 kHz sampled stereo audio (i.e., CD quality), which is the standard for music distribution.

Reading this extremely charitably, I think the contrast is supposed to be to speech which is normally uses much smaller sample rates. E.g. AMR-WB samples at 16 kHz. Speex, back in the day, supported up to 32 kHz.

Full quality digitally distributed audio is often encoded at 48 kHz (e.g. Opus - the default audio codec on YouTube and many other sources), so I think "CD quality" is just supposed to emphasize that it's full-band rather than wide band or narrow band.

[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by earthnail on Monday October 31, 2022 @03:22AM (#33402881)
Since there is no perceptual difference to humans between 44.1 and 48 kHz, the statement about CD quality is perfectly fine - even more so as they operate on the higher sample rate.

Most research in that field operates at 16kHz. Enough for most speech applications, not enough for CD quality. In general, CD quality in this field means a high enough sample rate that you can play all audible frequencies.

[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by rzzzt on Monday October 31, 2022 @05:20AM (#33403526)
They didn't specify bit depth either.

I understand all of this reads like pointless pedantry, but a) it feels good indulging in it b) certain word combinations (such as "CD quality") have meanings backed by broad consensus, please use them responsibly so readers do not have to overexert their loose interpretation muscle.

If they mean wide band, say wide band, noone will bat an eye.

[ Parent | on HN ]
Re:Using AI to compress audio files for quick and easy sharing by ihatepython on Monday October 31, 2022 @05:30AM (#33403583)
No, CD quality means 44.1 kHz 16-bit. DVD quality would be 48 kHz. Higher sample rate does not necessary mean higher quality
[ Parent | on HN ]