A multi-view SSL framework with combined reconstruction and separation-based contrastive losses obtains disentangled pitch and instrument subspaces without the accuracy loss seen with contrastive-only training on NSynth.
Learning Disentangled Audio Representations through Controlled Synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper tackles the scarcity of benchmarking data in disentangled auditory representation learning. We introduce SynTone, a synthetic dataset with explicit ground truth explanatory factors for evaluating disentanglement techniques. Benchmarking state-of-the-art methods on SynTone highlights its utility for method evaluation. Our results underscore strengths and limitations in audio disentanglement, motivating future research.
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning
A multi-view SSL framework with combined reconstruction and separation-based contrastive losses obtains disentangled pitch and instrument subspaces without the accuracy loss seen with contrastive-only training on NSynth.