Someone should add an ML decoder to JPEG
Opus 1.5 released: Opus gets a machine learning upgrade
81–90 of 151 posts
Re: Opus 1.5 released: Opus gets a machine learning upgrade
#82>That's why most codecs have packet loss concealment (PLC) that can fill in for missing packets with plausible audio that just extrapolates what was being said and avoids leaving a hole in the audio
...How far can ML PLC "hallucinate" audio? A sound , a syllable, a whole word, half a sentence?
Can I trust anymore what I hear?
Re: Opus 1.5 released: Opus gets a machine learning upgrade
#83I 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.
This is an important question. However, I'd like to point out that similar biases can easily exist for non-ML, hand-tuned algorithms. Even in the latter case test sets and often even "training" and "validation" sets are used for finding good parameters. Any of these can be a source of bias, as can the ears of evaluators making these decisions. It's true that bias questions often come up in ML context because fundamen…
As a notable example, the MP3 format was hand-tuned to vocals based on "Tom's Diner" (i.e. a female voice). It has been accused of being biased towards female vocals as a result.
Re: Opus 1.5 released: Opus gets a machine learning upgrade
#84>That's why most codecs have packet loss concealment (PLC) that can fill in for missing packets with plausible audio that just extrapolates what was being said and avoids leaving a hole in the audio ...How far can ML PLC "hallucinate" audio? A sound , a syllable, a whole word, half a sentence? Can I trust anymore what I hear?
It can already fill in all gaps and create all sorts of audio, but it may sound muddy and metallic. Give it a year, and then you can't trust what you hear anymore. Checking sources is a good idea in either case.
Re: Opus 1.5 released: Opus gets a machine learning upgrade
#85I just want to mention that getting such good speech quality at 9kbps by using NoLACE is absolutely insane.
I wanted to see what it would sound like in comparison to a really early streaming audio codec, realaudio 1.0
$ ffmpeg -i female_ref.wav - acodec real_144 female_ref.ra
This was seen as "14.4" audio, for 14.4kb/s dialup in the mid-90s. The quality increase over those nearly 30 years for what you can get out of what's actually a fewer number of bytes is really impressive.
Re: Opus 1.5 released: Opus gets a machine learning upgrade
#86Earlier quoted context omitted.
This is a great question! Here's a related failure case that I think illustrates the issue. In my country, public restroom facilities replaced all the buttons and levers on faucets, towel dispensers, etc. with sensors that detect your hand under the faucet. Black people tell me they aren't able to easily use these restrooms. I was surprised when I heard this, but if you google this, it's apparently a thing. Why does…
What if it is a pareto improvement: better improvement for some dialects but no worse than the earlier version for anyone. Should it be shelved or tuned down so all improvement for each dialect see gains by an exactly equal percentage?
Here's a question that should have the same/similar answer: Increasingly some part of the job interviews is being handled over the internet. All other things being equal, people are likely to have a more positive response to candidates with more pleasant voice. So if new ML-enhanced codecs become more common, we may find that some group X has a just slightly worse quality score than others. Over enough samples that would translate to lower interview success rate for them.
Do you think we should keep using that codec, because overall we get a better sound quality across all groups? Do you feel the same as a member of group X?
Re: Opus 1.5 released: Opus gets a machine learning upgrade
#87Someone should add an ML decoder to JPEG
You can't do that much on the decoding side (apart from the equivalent of passing the normally decoded result through a low percent img2img ML)
But the encoders are already there: https://medium.com/@migel_95925/supercharging-jpeg-with-mach... https://compression.ai/
Re: Opus 1.5 released: Opus gets a machine learning upgrade
#88Earlier quoted context omitted.
Making a patent troll is just a matter of putting up a press release and a web page. I could claim to have a long list of patents against AptX. Anyone could. Of course I'm not willing to disclose the list of patents at this time, but customers looking to be extorted may contact me privately.
At least in the U.S., anyone can look up all the patents a person/entity owns. So, your fraud wouldn’t get very far. https://assignment.uspto.gov/patent/index.html#/patent/searc...
"I represent the holders of the patents in question" is simple enough. I wonder if it's fraud, if all you're putting out is an unverifiable claim on the net. The pool operators do that all the time.
Re: Opus 1.5 released: Opus gets a machine learning upgrade
#89Someone should add an ML decoder to JPEG
You can't do that much on the decoding side (apart from the equivalent of passing the normally decoded result through a low percent img2img ML) But the encoders are already there: https://medium.com/@migel_95925/supercharging-jpeg-with-mach... https://compression.ai/
You can more accurately invert the quantisation step
Re: Opus 1.5 released: Opus gets a machine learning upgrade
#90Earlier quoted context omitted.
You can't do that much on the decoding side (apart from the equivalent of passing the normally decoded result through a low percent img2img ML) But the encoders are already there: https://medium.com/@migel_95925/supercharging-jpeg-with-mach... https://compression.ai/
You can more accurately invert the quantisation step
You can't do it more accurately. You can make up expected details which aren't encoded in the file. But that's explicitly less accurate.