A flow-matching model equipped with a learned permutation-equivariant token mapping outperforms regression and generative baselines at inferring synthesizer parameters from audio.
A synthesizer is a map between these spaces, f:P → S
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching
A flow-matching model equipped with a learned permutation-equivariant token mapping outperforms regression and generative baselines at inferring synthesizer parameters from audio.