An action-conditioned JEPA trained on paired piano audio and MIDI learns latent sound dynamics that support MIR tasks and transcription-style planning.
PESTO: pitch estimation with self-supervised transposition-equivariant objective,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Music-JEPA: Learning a World Model of Sound from Action
An action-conditioned JEPA trained on paired piano audio and MIDI learns latent sound dynamics that support MIR tasks and transcription-style planning.