Binaural Speech Enhancement Using STOI-Optimal Masks

TL;DR

This paper extends STOI-optimal masking techniques to binaural speech enhancement, effectively improving SNR while preserving spatial cues and speech intelligibility in noisy environments.

Contribution

It introduces a novel binaural masking approach that estimates masks for each channel and combines them to enhance speech without losing spatial information.

Findings

Improved SNR in binaural speech signals.

Preservation of binaural cues and speech intelligibility.

Effective in directional noise conditions.

Abstract

STOI-optimal masking has been previously proposed and developed for single-channel speech enhancement. In this paper, we consider the extension to the task of binaural speech enhancement in which spatial information is known to be important to speech understanding and therefore should be preserved by the enhancement processing. Masks are estimated for each of the binaural channels individually and a `better-ear listening' mask is computed by choosing the maximum of the two masks. The estimated mask is used to supply probability information about the speech presence in each time-frequency bin to an Optimally-modified Log Spectral Amplitude (OM-LSA) enhancer. We show that using the proposed method for binaural signals with a directional noise not only improves the SNR of the noisy signal but also preserves the binaural cues and intelligibility.