Neurodyne, a GAN-based singing voice pitch manipulator, uses adversarial representation learning and inversion plus composition cycle-consistency to improve pitch accuracy while preserving singer identity.
It obtains optimized pitch- independent features that avoid the artifacts brought by source- filter-model-based disentanglement
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Neurodyne: Neural Pitch Manipulation with Representation Learning and Cycle-Consistency GAN
Neurodyne, a GAN-based singing voice pitch manipulator, uses adversarial representation learning and inversion plus composition cycle-consistency to improve pitch accuracy while preserving singer identity.