Denoising without access to clean data using a partitioned autoencoder
This addresses a practical limitation for researchers and practitioners in audio processing by enabling denoising without clean data, though it appears incremental as it builds on existing autoencoder frameworks.
The authors tackled the problem of training denoising autoencoders without clean data by introducing a method that uses only noisy data with and without the signal of interest, achieving denoising of birdsong audio with a convolutional autoencoder.
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.