Cepstral Smoothing of Binary Masks for Convolutive Blind Separation of Speech Mixtures

TL;DR

This paper introduces a new speech separation system that combines blind source separation with cepstral smoothing of binary masks to improve audio quality and reduce musical noise in mixed speech recordings.

Contribution

The paper presents a novel approach integrating cepstral smoothing with binary masks in a speech separation system, enhancing separation quality and reducing musical noise.

Findings

Effective reduction of musical noise in separated speech signals

Successful application on both simulated and real recordings

Promising evaluation results demonstrating system effectiveness

Abstract

In this paper, we propose a novel separation system for extracting two speech signals from two microphone recordings. Our system combines the blind source separation technique with cepstral smoothing of binary time-frequency masks. The last is composed of two steps. First, the two binary masks are estimated from the separated output signals of BSS algorithm. In the second step, a cepstral smoothing is applied of these spectral masks in order to reduce musical noise typically produced by time-frequency masking. Experiments were carried out with both artificially mixed speech signals using simulated room model and two real recordings. The evaluation results are promising and have shown the effectiveness of our system.