Learning Disentangled Audio Representations through Controlled Synthesis
arXiv:2402.10547
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.
12 pages, 12 figures, accepted as a Tiny paper at ICLR 2024