A Style Transfer Approach To Source Separation

Abstract

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.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyvenkataramani2019a

Related papers

• End-to-end Networks For Supervised Single-channel Speech Separation (2018)0.00
• End-to-end Source Separation With Adaptive Front-ends (2017)12.17
• End-to-end Non-negative Autoencoders For Sound Source Separation (2019)2.26
• A Comparison And Combination Of Unsupervised Blind Source Separation Techniques (2021)0.00
• Independence-based Joint Dereverberation And Separation With Neural Source Model (2021)4.52
• Deep Variational Generative Models For Audio-visual Speech Separation (2020)0.00
• Unsupervised Music Source Separation Using Differentiable Parametric Source Models (2022)10.97
• Source Separation And Depthwise Separable Convolutions For Computer Audition (2020)0.00