News for hackers. Stuff that matters.
Re:SoundStream: An End-to-End Neural Audio Codec by cblconfederate on Sunday August 15, 2021 @08:44AM (#28188330)
> that induce the reconstructed audio to sound like the uncompressed original input.

What if we want the codec to produce easier-perceptible sound, not just a reconstruction. Could bake in noise and echo reduction, voice improvements etc

Re:SoundStream: An End-to-End Neural Audio Codec by vlovich123 on Sunday August 15, 2021 @10:09AM (#28188839)
Did you read the “ Joint Audio Compression and Enhancement” section part of the announcement?
Re:SoundStream: An End-to-End Neural Audio Codec by cblconfederate on Sunday August 15, 2021 @10:57AM (#28189269)
I wonder how the training works in that system
Re:SoundStream: An End-to-End Neural Audio Codec by rcthompson on Sunday August 15, 2021 @01:38PM (#28190617)
I assume think they start with the "signal" and "noise" as separate audio files, and then they play them together in order to create a synthetic noisy input. Then they can train the output against only the signal so that it will learn to filter out the noise.