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.

Stats

• citations36
• S2 citations—
• github stars0
• HF likes0
• heat score11.76
• arxiv keysubakan2017generative

Related papers

• SVSGAN: Singing Voice Separation Via Generative Adversarial Network (2017)0.00
• End-to-end Non-negative Autoencoders For Sound Source Separation (2019)2.26
• Single-channel Signal Separation And Deconvolution With Generative Adversarial Networks (2019)6.77
• Deep Variational Generative Models For Audio-visual Speech Separation (2020)0.00
• A Style Transfer Approach To Source Separation (2019)3.58
• Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks (2017)16.21
• Robust Speech Recognition Using Generative Adversarial Networks (2017)11.29
• Neural Network Alternatives To Convolutive Audio Models For Source Separation (2017)0.00