Year: 2015
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Stowell, Dan, Turner, Richard E.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G7116948299
OpenAlex ID: W2253434170