3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in music-compression-5
No benchmarks available.
Use these libraries to find music-compression-5 models and implementations
No subtasks available.
It is shown that by prompting VampNet in various ways, it can apply it to tasks like music compression, inpainting, out Painting, continuation, and looping with variation (vamping), and is capable of maintaining style, genre, instrumentation, and other high-level aspects of the music.
A novel model is introduced, called Lead-AE, that models the lead sheets as a discrete subselection of the original sequence, using a differentiable top-k operator to allow for controllable local sparsity constraints and improves upon the established deterministic baseline.
Adding a benchmark result helps the community track progress.