News for hackers. Stuff that matters.
Re:Neural audio codecs: how to get audio into LLMs by quinndupont on Tuesday October 21, 2025 @10:32AM (#45656334)
There’s a long history of attempts at artificial speech that take this approach, recreating mouth parts and vibrating air. They are all pretty silly, like this work, which fails to understand how writing isn’t just a derivative of speech.
Re:Neural audio codecs: how to get audio into LLMs by crazygringo on Tuesday October 21, 2025 @11:06AM (#45656743)
> They are all pretty silly,

Huh? How?

> like this work which fails to understand how writing isn’t just a derivative of speech.

The whole point of the article is that writing isn't just a derivative of speech. It's in the introduction.