News for hackers. Stuff that matters.
Re:Opus 1.5 released: Opus gets a machine learning upgrade by yalok on Monday March 04, 2024 @03:53PM (#39595918)
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 by indolering on Monday March 04, 2024 @11:01PM (#39599273)
It's a really smart application of ML: helping around the edges and not letting the ML algo invent pheonems or even whole words by accident. ML transcription has a similar trade-off of performing better on some benchmarks but also hallucinating results.
Re:Opus 1.5 released: Opus gets a machine learning upgrade by kolinko on Tuesday March 05, 2024 @01:51AM (#39600183)
A nice story about Xerox discovering this issue in 2003, when their copiers began slightly changing random numbers in copied documents

https://www.theverge.com/2013/8/6/4594482/xerox-copiers-rand...

Re:Opus 1.5 released: Opus gets a machine learning upgrade by cedilla on Tuesday March 05, 2024 @03:05AM (#39600587)
I don't think machine learning was involved there at all. As I understand it, it was an issue of a specifically implemented feature (reusing a single picture of a glyph for all other instances to save space) being turned on in archive-grade settings, despite the manual stating otherwise.
Re:Opus 1.5 released: Opus gets a machine learning upgrade by h4x0rr on Tuesday March 05, 2024 @02:51AM (#39600504)
https://youtu.be/zXXmhxbQ-hk Interesting yet funny CCC video about this
Re:Opus 1.5 released: Opus gets a machine learning upgrade by yalok on Tuesday March 05, 2024 @03:26AM (#39600721)
fwiw, in ASR/speech transcription world, it looks reverse to me - in the past, there was lots of custom non-ML code & separate ML models for audio modeling and language modeling - but current SOTA ASRs are all e2e, and that's what's used even in mobile applications, iiuc.

I still think the pendulum will swing back there again, to have even better battery/larger models on mobile.