Denoising without access to clean data using a partitioned autoencoder
Neural and Evolutionary Computing
2015-09-24 v2 Machine Learning
Abstract
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.
Cite
@article{arxiv.1509.05982,
title = {Denoising without access to clean data using a partitioned autoencoder},
author = {Dan Stowell and Richard E. Turner},
journal= {arXiv preprint arXiv:1509.05982},
year = {2015}
}