Robust Fusion of Differential Beamformers for Speech Enhancement in Dynamic Interference Conditions

Abstract

Differential microphone arrays are widely used for far-field sound acquisition due to their high directivity and compact geometry. However, they lack the flexibility to adapt in dynamic acoustic environments with multiple or moving interferers. This paper proposes a novel method for fusing multiple differential beamformers to improve robustness under such conditions. A set of beamformers is designed with distortionless constraints in the target direction and nulls in various potential interference directions. An online fusion strategy is then applied, where a subset of beamformer outputs is selected and adaptively combined at each time frame based on the criterion of minimizing the instantaneous output variance. Simulation results demonstrate that the proposed method achieves superior interference suppression and speech quality, while maintaining low computational complexity suitable for real-time processing.