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

Opus 1.5 released: Opus gets a machine learning upgrade

opus-codec.org

Post reply on HN
Print view View original

41–50 of 151 posts

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#41

Post by jmvalin »

CharlesW wrote: post #5
travisporter wrote: post #2

Very cool. seems like they addressed the problem of hallucination. would be interesting to see an example of it hallucinating without redundancy and corrected with redundancy

Isn't packet loss concealment (PLC) a form of hallucination? Not saying it's bad, just that it's still Making Shit Up™ in a statistically-credible way.

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 features (using a regression loss), which means that model is able to continue a vowel. If unsure it'll just pick the "middle point", which won't be something recognizable as a new word. That's in line with how traditional PLCs work. It just sounds better. The only generative part is the vocoder that reconstructs the waveform, but it's constrained to match the predicted spectrum so it can't hallucinate either.

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#42

Post by CharlesW »

jmvalin wrote: post #41
CharlesW wrote: post #5

Earlier quoted context omitted.

Isn't packet loss concealment (PLC) a form of hallucination? Not saying it's bad, just that it's still Making Shit Up™ in a statistically-credible way.

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 features (using a regression loss), which means that model is able to continue a vowel. If unsure it'll just pick the "middle point", which won't be something recognizable as a new word. That's in line with how traditional PLCs work. It just so…

That's really cool. Congratulations on the release!

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#43

Post by yalok »

The main limitation for such codecs is CPU/battery life - and I like how they sparsely applied ML in it here and there, combining it with classic approach (non-ML algos) to achieve better tradeoff of CPU vs quality. E.g. for better low bitrate support/LACE - "we went for a different approach: start with the tried-and-true postfilter idea and sprinkle just enough DNN magic on top of it." The key was not to feed raw audio samples to the NN - "The audio itself never goes through the DNN. The result is a small and very-low-complexity model (by DNN standards) that can run even on older phones."

Looks like the right direction for embedded algos and it seems to be a pretty unexplored one, as compared to the current fashion to do ML E2E.

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#44

Post by pgeorgi »

xoa wrote: post #34
pgeorgi wrote: post #28

Earlier quoted context omitted.

No codec (or any other technical development, really - edit: except for 20+ years old stuff, and only if you don't add any, even "obvious" improvements) is known patent free, or clear on "who owns what." Folks set up pools all the time, but somehow they never offer indemnification for completeness of the pool - because they can't. See https://en.kangxin.com/html/2/218/219/220/11565.html for a few examples how the pat…

FWIW, submarine patents are long dead, so it is possible to feel assured that old enough stuff is patent free. Of course that denies a lot of important improvements, but due to diminishing returns and the ramp of tech development it's still ever more significant. A lot of key stuff is going to lose monopoly lock this decade.

You're right. I could still amend the post, so I added the 20+ years caveat. Thanks!

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#45

Post by sergiotapia »

wilg wrote: post #32
sergiotapia wrote: post #30

Earlier quoted context omitted.

I'd just like to interject for a moment. What you're referring to as AI, is in fact, Machine Learning, or as I've recently taken to calling it, Machine Learning plus Traditional AI methods.

My point is very clearly that you should not spend any time or energy thinking about about the terminology.

I know lol this a famous quote by ganoo loonix enthusiast Richard Stallman.

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#46

Post by pgeorgi »

dogma1138 wrote: post #33
pgeorgi wrote: post #28

Earlier quoted context omitted.

No codec (or any other technical development, really - edit: except for 20+ years old stuff, and only if you don't add any, even "obvious" improvements) is known patent free, or clear on "who owns what." Folks set up pools all the time, but somehow they never offer indemnification for completeness of the pool - because they can't. See https://en.kangxin.com/html/2/218/219/220/11565.html for a few examples how the pat…

No one said that Opus is the only one suffering from licensing ambiguity, but comparing it to say AptX and its variants which do have a clear one stop shop for licensing (Qualcomm) it’s a much riskier venture especially when it comes to hardware.

A drive-by patent owner can show up on anything, and if they don't want to license to you, your entire product is bust.

Even if it's AptX and Qualcomm issues you a license in exchange for money. I wouldn't even bet on being able to claw back these license costs after being ordered to destroy your AptX-equipped product after it ran into somebody else's patent.

The risk that this happens is _exactly_ the same for Opus or AptX.

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#47

Post by unixhero »

luplex wrote: post #27

I wonder: did they address common ML ethics questions? Specifically: Are the ML algorithms better/worse on male than on female speech? How about different languages or dialects? Are they specifically tuned for speech at all, or do they also work well for music or birdsong? That said, the examples are impressive and I can't wait for this level of understandability to become standard in my calls.

Why is the ethics question important? It is a new feature for an audio codec, not a new material to teach in your kids curriculum.

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#48

Post by The_Colonel »

unixhero wrote: post #47
luplex wrote: post #27

I wonder: did they address common ML ethics questions? Specifically: Are the ML algorithms better/worse on male than on female speech? How about different languages or dialects? Are they specifically tuned for speech at all, or do they also work well for music or birdsong? That said, the examples are impressive and I can't wait for this level of understandability to become standard in my calls.

Why is the ethics question important? It is a new feature for an audio codec, not a new material to teach in your kids curriculum.

Imagine you release a codec which optimizes for cis white male voice, every other kind of voice has perceptibly lower fidelity (at low bitrates). That would not go well...

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#49

Post by shrubble »

The_Colonel wrote: post #48
unixhero wrote: post #47

Earlier quoted context omitted.

Why is the ethics question important? It is a new feature for an audio codec, not a new material to teach in your kids curriculum.

Imagine you release a codec which optimizes for cis white male voice, every other kind of voice has perceptibly lower fidelity (at low bitrates). That would not go well...

[flagged]

Re: Opus 1.5 released: Opus gets a machine learning upgrade

#50

Post by Aachen »

a_wild_dandan wrote: post #25
CharlesW wrote: post #5

Earlier quoted context omitted.

Isn't packet loss concealment (PLC) a form of hallucination? Not saying it's bad, just that it's still Making Shit Up™ in a statistically-credible way.

To borrow from Joscha Bach: if you like the output, it's called creativity. If you don't, it's called a hallucination.

That sounds funny, but is it true? Certainly there's a bias that goes towards what you're quoting, but would you otherwise genuinely call the computer creative? Is that a positive aspect of a speech codec or of an information source?

Creative is when you ask a neural net to create a poem, or something else from "scratch" (meant to be unique). Hallucination is when you didn't ask it to make its answer up but to recite or rephrase things it has directly observed

That's my layman's understanding anyway, let me know if you agree

Post reply on HN