Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion

Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by Jeff_Brown on Wednesday September 13, 2023 @12:55PM (#37498868)

MIDI is not inherently lossy. You could encode anything in it, just as you can encode any novel as an integer.

In practice, though, transformations from audio to MIDI discard an enormous amount of important information, with the possible exception of transcriptions of performances on piano (where volume, frequency, duration and a good physical model of a piano are enough to reconstruct everything important about the signal) and similar instruments.

[ Parent | on HN ]

Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by PaulDavisThe1st on Thursday September 14, 2023 @01:29AM (#37505316)

MPE/MIDI 2.0 pretty much theoretically fixes the "discard an enormous amount of important information", in that you can have an extremely large number of parameters describing every single note and/or physical performance nuance.

Contemporary MIDI is ready to describe almost any human performance in an almost absurd level of detail. Whether anything can do something useful with the description is a different story.

[ Parent | on HN ]