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

A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet

people.xiph.org

Post reply on HN
Print view View original

71–76 of 76 posts

Re: A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet

#71

Post by rasz »

jmvalin wrote: post #12
rasz wrote: post #5

3 Gflops, we are deep beyond diminishing returns here. Opus seems good enough.

Keep in mind that the very first CELP speech codec (in 1984) used to take 90 seconds to encode just 1 second of speech... on a Cray supercomputer. Ten years later, people had that running in their cell phones. It's not just that hardware keeps getting faster, but algorithms are also getting more efficient. LPCNet is already 1/100 the complexity of the original WaveNet (which is just 2 years old) and I'm pretty sure i…

This is roughly >100x computation for 2x improvement, which might sound great, except we are already talking single digit Kbits here, hence diminishing returns.

Re: A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet

#72

Post by db48x »

teraflop wrote: post #49
CamperBob2 wrote: post #27

Earlier quoted context omitted.

That was a fairly ignorant comment because the whole idea behind a speech codec is to compress and reproduce speech in a manner that allows one to at least recognize who's speaking. But I wonder if there isn't a gem in there somewhere. The essential expressive characteristics of a person's voice change much more slowly than the frame rate of any codec, and predictive coding alone doesn't cover all of the possibilitie…

This idea is the basis of an interesting plot point in Vernor Vinge's sci-fi novel A Fire Upon the Deep . The book is set in a universe where long-distance, faster-than-light communication is possible, but extremely bandwidth-constrained. However, localized computational power is many orders of magnitude beyond what we have today. As a result, much of the communication on the "Known Net" is text (heavily inspired by…

I love that book. I loved that the ships could send text messages across 10,000 light-years, provided the receiving end had an antenna swarm with the mass of a planet.

He played with the idea in at least one other story that I'm aware of, a short story where a human scientist on a planet just inside the Slow Zone (where no FTL is supposed to be possible) acquires a device from the Transcend (where FTL and AI are apparently trivial). The device is a terminal connected to a transcendent intelligence, and it can send and receive a few bits per second via FTL, even in the Slow Zone. Using those few bits it's able to transmit natural-language questions, and reproduce the answers to those questions, but the scientist can't decide whether he can trust it. Can the AI really model him well enough to understand his questions using that tiny amount of information? Can the answers coming back be anything but random? And then the solar weather starts acting a bit unusual...

Re: A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet

#73

Post by bonzini »

StavrosK wrote: post #37
petercooper wrote: post #31

Earlier quoted context omitted.

Here you go: http://no.gd/vega2.wav It holds up ridiculously well considering the entire song compresses down to 25392 bytes.

The lyrics of the song are 1200 characters long, so this version of the song only takes up twenty times more space than the written lyrics.

At some point she sings "loose" instead of "nice" in the compressed version, and a bit later it also sounds like "lulk" instead of "milk". So it's a bit lossy even with respect to the lyrics!

Re: A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet

#74

Post by jmvalin »

krisoft wrote: post #63
jmvalin wrote: post #53

Earlier quoted context omitted.

In theory, it wouldn't be too hard to implement with an neural network. In theory. In practice, the problem is figuring out how to do the training because I don't have 2 hours of your voice saying the same thing as the target voice and with perfect alignment. I suspect it's still possible, but it's not a simple thing either.

Perfect alignment, or any alignment for that matter, is not necessary. Check out adversarial networks. CycleGAN can be trained to do similar feats in image domain without aligned inputs. Shouldn't be hard to adopt it to audio.

I didn't say "impossible", merely "not simple". The minute you bring in a GAN, things are already not simple. Also, I'm not aware of any work on a GAN that works with a network that does conditional sampling (like LPCNet/WaveNet), so it would mean starting from scratch.

Re: A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet

#75

Post by petercooper »

bravura wrote: post #64
petercooper wrote: post #31

Earlier quoted context omitted.

Here you go: http://no.gd/vega2.wav It holds up ridiculously well considering the entire song compresses down to 25392 bytes.

Could you also try "I Feel Love" by Donna Summer? I am curious how it sounds when there is a really active bassline and lead synth.

http://no.gd/donna2.mp3

The vocal sections just sound like someone clearing their throat out.

Re: A Real-Time Wideband Neural Vocoder at 1.6 Kb/S Using LPCNet

#76

Post by davidf560 »

metildaa wrote: post #66
jdc wrote: post #38

Earlier quoted context omitted.

So maybe this line of work will mean more spectrum available in the future.

Only if Motorola gets out of the way and supports modern codecs and standards. Current public safety radio networks are using ancient TDMA tech that Motorola has cobbled together, along with audio codecs that shred voice quality. The only good part is the durability of the pricey radio, some are even intrinsically safe.

Public safety digital radio networks are primarily APCO Project 25 (P25) which use IMBE/AMBE developed by DVSI. Motorola's original digital radios used a proprietary vocoder called VSELP (also used by iDEN/Nextel). When APCO standardized public safety digital radios, they rejected VSELP and chose IMBE from DVSI instead. Personally I think VSELP sounds better than IMBE, and I'm not sure IMBE was chosen due to technical superiority or if it was political reasons (i.e. picking a non-Motorola solution due to Motorola's dominance). Also, APCO Project 25 Phase 1 was not TDMA, however Phase 2 is.

https://en.wikipedia.org/wiki/Project_25

Public safety radio is a true mission critical service that moves slowly - equipment lasts years or decades and is expensive and not frequently replaced or upgraded, hence new technology adoption is slow. Vocoder choice is driven by a standards committee for interoperability (which has seen more emphasis since 9/11), and of course committees aren't typically known for working fast. Public safety radio is definitely not a place for a "move fast and break things" mentality.

Post reply on HN