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. |
Year | Venue | Field |
---|---|---|
2015 | arXiv: Neural and Evolutionary Computing | Noise reduction,Noisy data,Autoencoder,Computer science,Speech recognition,Artificial intelligence,Denoising autoencoder,Artificial neural network,Machine learning |
DocType | Volume | Citations |
Journal | abs/1509.05982 | 1 |
PageRank | References | Authors |
0.36 | 11 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dan Stowell | 1 | 209 | 21.84 |
Richard E. Turner | 2 | 322 | 37.95 |