Publication

Adaptive Beamforming with a Minimum Mutual Information Criterion

2007
Report or working paper
Abstract

In this work, we consider an acoustic beamforming application where two speakers are simultaneously active. We construct one subband-domain beamformer in \emph{generalized sidelobe canceller} (GSC) configuration for each source. In contrast to normal practice, we then jointly optimize the \emph{active weight vectors} of both GSCs to obtain two output signals with \emph{minimum mutual information} (MMI). Assuming that the subband snapshots are Gaussian-distributed, this MMI criterion reduces to the requirement that the \emph{cross-correlation coefficient} of the subband outputs of the two GSCs vanishes. We also compare separation performance under the Gaussian assumption with that obtained from several super-Gaussian probability density functions (pdfs), namely, the Laplace, K0K_0, and Γ\Gamma pdfs. Our proposed technique provides effective nulling of the undesired source, but without the signal cancellation problems seen in conventional beamforming. Moreover, our technique does not suffer from the source permutation and scaling ambiguities encountered in conventional blind source separation algorithms. We demonstrate the effectiveness of our proposed technique through a series of far-field automatic speech recognition experiments on data from the \emph{PASCAL Speech Separation Challenge} (SSC). On the SSC development data, the simple delay-and-sum beamformer achieves a word error rate (WER) of 70.4%. The MMI beamformer under a Gaussian assumption achieves a 55.2% WER, which is further reduced to 52.0% with a K0K_0 pdf, whereas the WER for data recorded with a close-talking microphone is 21.6%.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.