Learning Disentangled Audio Representations through Controlled Synthesis
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 5 of its 14 references that are in the map. First posted on arXiv 16 Feb 2024.
Builds on
5 of 14 references.
References · 5
- 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
- 2018Disentangling by Factorisingcited by 614
- 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
- 2018Learning Deep Disentangled Embeddings with the F-Statistic Losscited by 101
- 2019Theory and Evaluation Metrics for Learning Disentangled Representationscited by 57
Built on by
Not cited yet.