Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures

TL;DR

This paper introduces a novel directional sparse filtering algorithm that uses weighted Lehmer mean to effectively separate unbalanced speech sources in various acoustic environments.

Contribution

It presents a new DSF-based method with learnable weights for the Lehmer mean, addressing source imbalance in blind speech separation.

Findings

Improved separation performance over baseline methods

Effective in multiple real acoustic environments

Adaptive handling of source imbalance

Abstract

In blind source separation of speech signals, the inherent imbalance in the source spectrum poses a challenge for methods that rely on single-source dominance for the estimation of the mixing matrix. We propose an algorithm based on the directional sparse filtering (DSF) framework that utilizes the Lehmer mean with learnable weights to adaptively account for source imbalance. Performance evaluation in multiple real acoustic environments show improvements in source separation compared to the baseline methods.