A Multi-Channel Quality Assessment Setup Applied to a Distributed Microphone Speech Enhancement SystemWith Spectral Boosting

Abstract:
systems it is common to process the signal components such as speech and noise independently using the filter coefficients obtained from the combined noisy signal. Thus, specific quality measures can be computed. A specified signal-to-noise ratio (SNR) can be set for the noisy signal by rescaling and adding the signal components. In this contribution a setup for a multi-channel instrumental quality assessment of distributed microphone systems is presented, where each of multiple active speakers has a dedicated microphone. For speech active periods of the related speaker the desired SNR is explicitly set in his dedicated microphone by rescaling the signal level, whereas the other channels are adjusted accordingly. The proposed setup allows to create realistic noisy input signals for a speech enhancement system and to preserve the acoustic characteristics of the multi-channel microphone arrangement. Based on this structure a noise reduction approach is evaluated. It performs a selective combination of the multi-channel signals and a frequency selective boosting of speech active bins of the related active speaker as an extension to a recursiveWiener filtering.