Viewing profile — jmvalin

Actually, what we're doing from DRED isn't that far from what you're suggesting. The difference is that we keep more information about the voice/intonation and we don't need the la…

What the PLC does is (vaguely) equivalent to momentarily freezing the image rather than showing a blank screen when packets are lost. If you're in the middle of a vowel, it'll cont…

Well, there's different ways to make things up. We decided against using a pure generative model to avoid making up phoneme or words. Instead, we predict the expected acoustic feat…

Quoting from our paper, training was done using "205 hours of 16-kHz speech from a combination of TTS datasets including more than 900 speakers in 34 languages and dialects". Mostl…

As part of the packet loss challenge, there was an ASR word accuracy evaluation to see how PLC impacted intelligibility. See https://www.microsoft.com/en-us/research/academic-progr…

(Opus author here) I'm curious what kind of "glitch" this is referring to.

> This is entirely my fault, and I take all the blame for that. You shouldn't be blaming yourself, it was the best thing to do. Some people may have been confused over who the "goo…

No, exactly none of that data was used for training. The training was done before the demo that was asking for noise contributions. The contributions are CC0, but were never used (…

All major browsers now implement WebRTC, including Opus support. Also, most browsers now support Opus playback in HTML5, though AFAIK Safari only supports it in the CAF container. …

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 tha…

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 y…

The ceptrum that takes up most of the bits (or the LSPs in other codecs) is actually a model of the larynx -- another reason why it doesn't do well on music. Because of the accurac…

Actually, what's in the demo already includes pruning (through sparse matrices) and indeed, it does keep just 1/10 of the weights as non-zero. In practice it's not quite a 10x spee…

Iridium appears to be using a vocoder called AMBE. Its quality is similar to the one of the MELP codec from the demo and it also runs at 2.4 kb/s. LPCNet at 1.6 is a significant im…

Well, in the case of music, what happens is that due to the low bit-rate there are many different signals that can produce the same features. The LPCNet model is trained to reprodu…

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 …

Actually, this won't work at all for music because it makes fundamental assumptions that the signal is speech. For normal conversations, it should work, though for now the models a…

Like many other audio codecs, Opus lets the encoder decide how to spend the bits is has -- on what frame and on what frequency bands. On top of that is has a few special features t…

The reason we are not calling it Opus 2 is that it could confuse some people into thinking we broke compatibility. Opus 1.3 is perfectly compatible with Opus 1.0, and all future re…

Thanks for reporting that. It's fixed now.

Getting something like AOM would have been easy back in 1993 because the costs would have been much lower. Back then complexity had to be really low, which means most of the compli…

The C part is mostly for low-level functions and was brought in to help bootstrap development (it's easier to work on improving a working encoder than one that doesn't work yet). T…

There's already a Rust AV1 encoder project you might want to look at: https://github.com/xiph/rav1e

There's a good reason all the listening tests have stopped at 96 kb/s. Above that, the quality of Opus, Vorbis and AAC is so close to transparency that it's pretty much impossible …