The impact of speech detection errors on the noise reduction performance of multi-channel Wiener filtering

Abstract

The noise reduction performance of the generalized sidelobe canceller (GSC) depends on the validity of a priori assumptions about the signal model, whereas the recently developed multi-channel Wiener filter (MWF) techniques do not, hence, their potential benefit. However, both techniques rely on a speech detection algorithm. In this paper, we analyze the average effect of speech detection errors on the performance of the GSC and MWF both theoretically and experimentally. It is shown that the MWF preserves its benefit over the GSC for a reasonable speech detection error rate of 20% or less, even when the GSC is supplied with a robustness constraint.