Towards Automated Single Channel Source Separation using Neural Networks

TL;DR

This paper introduces a flexible framework for single channel source separation that enhances existing algorithms by focusing on one source at a time, automates hyper-parameter tuning, and demonstrates improved SDR and SAR results.

Contribution

It proposes a generic, scalable framework for single source separation that improves performance and automates hyper-parameter tuning, applicable to any existing SCSS algorithm.

Findings

Improved SDR and SAR performance on neural network based separation.

Framework scales well with more than two sources.

Automates hyper-parameter tuning for practical use.

Abstract

Many applications of single channel source separation (SCSS) including automatic speech recognition (ASR), hearing aids etc. require an estimation of only one source from a mixture of many sources. Treating this special case as a regular SCSS problem where in all constituent sources are given equal priority in terms of reconstruction may result in a suboptimal separation performance. In this paper, we tackle the one source separation problem by suitably modifying the orthodox SCSS framework and focus only on one source at a time. The proposed approach is a generic framework that can be applied to any existing SCSS algorithm, improves performance, and scales well when there are more than two sources in the mixture unlike most existing SCSS methods. Additionally, existing SCSS algorithms rely on fine hyper-parameter tuning hence making them difficult to use in practice. Our framework takes a step towards automatic tuning of the hyper-parameters thereby making our method better suited for the mixture to be separated and thus practically more useful. We test our framework on a neural network based algorithm and the results show an improved performance in terms of SDR and SAR.