DeepAI AI Chat
Log In Sign Up

A Style Transfer Approach to Source Separation

by   Shrikant Venkataramani, et al.

Training neural networks for source separation involves presenting a mixture recording at the input of the network and updating network parameters in order to produce an output that resembles the clean source. Consequently, supervised source separation depends on the availability of paired mixture-clean training examples. In this paper, we interpret source separation as a style transfer problem. We present a variational auto-encoder network that exploits the commonality across the domain of mixtures and the domain of clean sounds and learns a shared latent representation across the two domains. Using these cycle-consistent variational auto-encoders, we learn a mapping from the mixture domain to the domain of clean sounds and perform source separation without explicitly supervising with paired training examples.


page 1

page 2

page 3

page 4


Semi-blind source separation with multichannel variational autoencoder

This paper proposes a multichannel source separation method called the m...

Music Source Separation with Generative Flow

Full supervision models for source separation are trained on mixture-sou...

Generative Adversarial Source Separation

Generative source separation methods such as non-negative matrix factori...

Underdetermined source separation using a sparse STFT framework and weighted laplacian directional modelling

The instantaneous underdetermined audio source separation problem of K-s...

Latent Iterative Refinement for Modular Source Separation

Traditional source separation approaches train deep neural network model...

CASS: Cross Adversarial Source Separation via Autoencoder

This paper introduces a cross adversarial source separation (CASS) frame...

Separating a Real-Life Nonlinear Image Mixture

When acquiring an image of a paper document, the image printed on the ba...