Multi-channel target speech enhancement based on ERB-scaled spatial coherence features

TL;DR

This paper introduces a novel ERB-scaled spatial coherence feature for multichannel speech enhancement, improving robustness and computational efficiency in reverberant environments with microphone arrays.

Contribution

The study proposes a new ERB-scaled spatial coherence feature that enhances multichannel speech enhancement and robustness across different microphone array configurations.

Findings

Effective in reverberant environments with speech interference

Robust against variations in microphone array geometry and number

Reduces computational complexity compared to traditional methods

Abstract

Recently, speech enhancement technologies that are based on deep learning have received considerable research attention. If the spatial information in microphone signals is exploited, microphone arrays can be advantageous under some adverse acoustic conditions compared with single-microphone systems. However, multichannel speech enhancement is often performed in the short-time Fourier transform (STFT) domain, which renders the enhancement approach computationally expensive. To remedy this problem, we propose a novel equivalent rectangular bandwidth (ERB)-scaled spatial coherence feature that is dependent on the target speaker activity between two ERB bands. Experiments conducted using a four-microphone array in a reverberant environment, which involved speech interference, demonstrated the efficacy of the proposed system. This study also demonstrated that a network that was trained with the ERB-scaled spatial feature was robust against variations in the geometry and number of the microphones in the array.