News for hackers. Stuff that matters.
Re:Seamless: Meta's New Speech Models by _kb on Monday December 04, 2023 @04:45AM (#38515405)
Apart from the dynamic range challenges for sensing, source separation is hard. There's been a pretty long line of research into the area - see "cocktail-party problem". AFAIK it's still a mostly unsolved problem.

There are no comments on this comment yet.