Sound Source Separation Using Latent Variational Block-Wise Disentanglement

Karim Helwani, Masahito Togami, Paris Smaragdis, Michael M. Goodwin
Electrical Engineering and Systems Science, Audio and Speech Processing, Audio and Speech Processing (eess.AS), Machine Learning (cs.LG), Sound (cs.SD)
2024-02-08 00:00:00
While neural network approaches have made significant strides in resolving classical signal processing problems, it is often the case that hybrid approaches that draw insight from both signal processing and neural networks produce more complete solutions. In this paper, we present a hybrid classical digital signal processing/deep neural network (DSP/DNN) approach to source separation (SS) highlighting the theoretical link between variational autoencoder and classical approaches to SS. We propose a system that transforms the single channel under-determined SS task to an equivalent multichannel over-determined SS problem in a properly designed latent space. The separation task in the latent space is treated as finding a variational block-wise disentangled representation of the mixture. We show empirically, that the design choices and the variational formulation of the task at hand motivated by the classical signal processing theoretical results lead to robustness to unseen out-of-distribution data and reduction of the overfitting risk. To address the resulting permutation issue we explicitly incorporate a novel differentiable permutation loss function and augment the model with a memory mechanism to keep track of the statistics of the individual sources.
PDF: Sound Source Separation Using Latent Variational Block-Wise Disentanglement.pdf
Empowered by ChatGPT