Generative Adversarial Source Separation

Abstract

Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversarial Networks (GANs) can learn data distributions without needing a parametric assumption on the output density. We show on a speech source separation experiment that, a multi-layer perceptron trained with a Wasserstein-GAN formulation outperforms NMF, auto-encoders trained with maximum likelihood, and variational auto-encoders in terms of source to distortion ratio.

References in corpus (1)

• A Neural Network Alternative to Non-Negative Audio Models

Cited by in corpus (3)

• Weakly Supervised Audio Source Separation via Spectrum Energy Preserved Wasserstein Learning
• Blind stain separation using model-aware generative learning and its applications on fluorescence microscopy images
• Semi-Supervised Monaural Singing Voice Separation With a Masking Network Trained on Synthetic Mixtures