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

Google open-sources the Lyra audio codec

opensource.googleblog.com

Post reply on HN
Print view View original

51–60 of 145 posts

Re: Google open-sources the Lyra audio codec

#51

Post by danaliv »

ncmncm wrote: post #47
te0006 wrote: post #41

"Please note that there is a closed-source kernel used for math operations that is linked via a shared object called libsparse_inference.so. We provide the libsparse_inference.so library to be linked, but are unable to provide source for it. This is the reason that a specific toolchain/compiler is required.* - README

[update: proprietary .so] They should re-implement the needed bits of libsparse_inference before releasing this thing. Otherwise it's just a distraction. Probably they should get it building with something other than Bazel, too.

It's not a kernel module, it's a compute kernel. Nothing to do with operating systems. They provide versions for android-arm64 and linux-x86_64.

The fine README says it builds and runs on Ubuntu 20.04.

Re: Google open-sources the Lyra audio codec

#52

Post by ncmncm »

A more useful system would take Opus-compressed data as input and feature-extract that, presumably faster than this thing. Bonus for not requiring a proprietary library like libsparse_inference.so.

Also, instead of encoding independent 40ms segments, it should be much better to encode 10ms segments given the previous 30ms.

Re: Google open-sources the Lyra audio codec

#54

Post by nyanpasu64 »

bobthechef wrote: post #39
dqv wrote: post #26

Earlier quoted context omitted.

This already happens with existing compression algorithms. Certain vowel sounds get collapsed, so someone will say, for example, "66" and it will come out on the other side as "6". Very annoying because you can't exactly coach a layperson on how to talk "the right way" to not trigger this vowel collapse.

> you can't exactly coach a layperson on how to talk "the right way" to not trigger this vowel collapse I've never noticed. At any rate, we should not coach people to adapt to technology in this way. It is Procrustean and anti-human and unnecessarily places a burden on people that belongs to the software and the developer.

For what it's worth, amateur radio operators already have specialized rules and techniques for speech, to improve clarity over a muffled noisy analog radio channel.

Re: Google open-sources the Lyra audio codec

#55

Post by tymekpavel »

BlueTemplar wrote: post #44
ksec wrote: post #29

Earlier quoted context omitted.

We wont be replacing Glass Fibre with Vacuum Fibre anytime soon. And I have been following this tech for long, but I do wish I am very wrong.

Starlink ?

Satellite links are orders of magnitude slower than fiber.

Re: Google open-sources the Lyra audio codec

#56

Post by plzbo »

pessimizer wrote: post #25

I've been waiting for an audio codec that could actually silently change the words I've said. https://www.zdnet.com/article/xerox-scanners-alter-numbers-i...

Link to the website of the person who found the error in the first place: http://www.dkriesel.com/en/blog/2013/0802_xerox-workcentres_...

Re: Google open-sources the Lyra audio codec

#57

Post by whoisburbansky »

PaulHoule wrote: post #30
whoisburbansky wrote: post #23

Since this is explicitly targeted at "the next billion users," do we have any sense of how well-optimized this is on non-English audio corpuses? I can't imagine that a model trained primarily on English/Western phonemes would perform as well on the rest of the world.

They say they tested it on 70+ languages.

Ah you're right. I couldn't find it on the original link in this post, but the post links to https://ai.googleblog.com/2021/02/lyra-new-very-low-bitrate-..., which mentions the 70+ languages statistic under the "Fairness" section. Thanks!

Re: Google open-sources the Lyra audio codec

#58

Post by rodjons »

Is there any difference with another audio codec? It's great to see that another player in the market—this time, it's machine learning that produces high-quality calls. I'll keep an eye on the impact in the future. This architecture will surely disrupt our communication industry.

Re: Google open-sources the Lyra audio codec

#59

Post by blendergeek »

tymekpavel wrote: post #55
BlueTemplar wrote: post #44

Earlier quoted context omitted.

Starlink ?

Satellite links are orders of magnitude slower than fiber.

> Satellite links are orders of magnitude slower than fiber.

Minimum end-to-end latency for communications from opposite points of the earth is much lower for Starlink style LEO satellites than for fiber.

Post reply on HN