News for hackers. Stuff that matters.
Re:Opus 1.5 released: Opus gets a machine learning upgrade by aredox on Monday March 04, 2024 @06:32PM (#39597559)
>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 by jmvalin on Monday March 04, 2024 @07:50PM (#39598117)
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 continue the vowel (trying to follow the right energy) for about 100 ms before fading out. It's explicitly designed not to make up anything you didn't say -- for obvious reasons.
Re:Opus 1.5 released: Opus gets a machine learning upgrade by aredox on Tuesday March 05, 2024 @09:51AM (#39604149)
Reassuring - thanks for clarifying that up.
Re:Opus 1.5 released: Opus gets a machine learning upgrade by xyproto on Monday March 04, 2024 @06:36PM (#39597583)
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 by samus on Tuesday March 05, 2024 @03:20AM (#39600674)
You never can when lossy compression is involved. It is commonly considered good practice to verify that the communication partner understood what was said, e.g., by restating, summarizing, asking for clarification, follow-up questions etc.