# Denoising without access to clean data using a partitioned autoencoder

arXiv: https://arxiv.org/abs/1509.05982 · HTML: https://mlsanity.com/paper/1509.05982/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2015.

## Built on by (most cited first, 1 of 1)

- [Improving weakly supervised sound event detection with self-supervised auxiliary tasks](https://mlsanity.com/paper/2106.06858/) (2021)

## Abstract (arXiv)

Training a denoising autoencoder neural network requires access to truly clean data, a requirement which is often impractical. To remedy this, we introduce a method to train an autoencoder using only noisy data, having examples with and without the signal class of interest. The autoencoder learns a partitioned representation of signal and noise, learning to reconstruct each separately. We illustrate the method by denoising birdsong audio (available abundantly in uncontrolled noisy datasets) using a convolutional autoencoder.