Enhanced Robot Audition Based on Microphone Array Source Separation with Post-Filter

TL;DR

This paper presents a real-time microphone array system for mobile robots that separates multiple speech sources using geometric source separation and post-filtering, achieving significant noise reduction and source adaptation.

Contribution

The system combines geometric source separation with a post-filter for rapid adaptation and interference reduction in mobile robot auditory scenes.

Findings

Approximately 10 dB reduction in log spectral distortion

Around 14 dB increase in signal-to-noise ratio

Effective separation of three simultaneous speakers in noisy environments

Abstract

We propose a system that gives a mobile robot the ability to separate simultaneous sound sources. A microphone array is used along with a real-time dedicated implementation of Geometric Source Separation and a post-filter that gives us a further reduction of interferences from other sources. We present results and comparisons for separation of multiple non-stationary speech sources combined with noise sources. The main advantage of our approach for mobile robots resides in the fact that both the frequency-domain Geometric Source Separation algorithm and the post-filter are able to adapt rapidly to new sources and non-stationarity. Separation results are presented for three simultaneous interfering speakers in the presence of noise. A reduction of log spectral distortion (LSD) and increase of signal-to-noise ratio (SNR) of approximately 10 dB and 14 dB are observed.