Learning Disentangled Audio Representations through Controlled Synthesis

Yusuf Brima, Ulf Krumnack, Simone Pika, Gunther Heidemann
2/16/2024
cs.SDcs.LGeess.AS

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Learning Disentangled Speech Representations

87% match1 repo132023

Evaluating Disentangled Representations for Controllable Music Generation

86% match2026

Learning Source Disentanglement in Neural Audio Codec

83% match1 repo482024

Transferring disentangled representations: bridging the gap between synthetic and real images

80% match1 repo32024

USAD: Universal Speech and Audio Representation via Distillation

80% match2025

Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation

80% match2025

Cite this paper

@article{brima2024learning,
  title  = {Learning Disentangled Audio Representations through Controlled Synthesis},
  author = {Yusuf Brima and Ulf Krumnack and Simone Pika and Gunther Heidemann},
  year   = {2024},
  eprint = {2402.10547},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.10547v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.10547.svg)](https://codeofpaper.com/paper/2402.10547)

Discussion