End-to-end Non-negative Autoencoders For Sound Source Separation

Abstract

Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical methods like Non-negative Matrix Factorization (NMF) provide modular approaches to source separation that can be easily updated to adapt to new mixture scenarios. In this paper, we generalize NMF to develop end-to-end non-negative auto-encoders and demonstrate how they can be used for source separation. Our experiments indicate that these models deliver comparable separation performance to discriminative approaches, while retaining the modularity of NMF and the modeling flexibility of neural networks.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyvenkataramani2019end

Related papers

• End-to-end Source Separation With Adaptive Front-ends (2017)12.17
• Neural Network Alternatives To Convolutive Audio Models For Source Separation (2017)0.00
• End-to-end Networks For Supervised Single-channel Speech Separation (2018)0.00
• Generalized Multichannel Variational Autoencoder For Underdetermined Source Separation (2018)7.81
• Complex NMF Under Phase Constraints Based On Signal Modeling: Application To Audio Source Separation (2016)7.50
• Generative Adversarial Source Separation (2017)11.76
• A Style Transfer Approach To Source Separation (2019)3.58
• Unsupervised Music Source Separation Using Differentiable Parametric Source Models (2022)10.97