Combining Monaural Beamforming and Blind Source Separation for Binaural Speech Enhancement in Multi-Microphone Hearing Aids

摘要

A binaural speech enhancement concept based on blind source separation (BSS) formulti-microphone hearing aids is introduced. The proposed concept combines monaural differential beamformers and a blind binaural speech enhancement strategy for improved noise suppression. In contrast to a BSS-based speech enhancement strategy with only two microphones, this scheme solves the front-back ambiguity of two-microphone binaural systems. This novel binaural speech enhancement concept is analyzed and evaluated for different scenarios. The proposed combination turns out to be an efficient concept for binaural suppression of interfering point sources as well as background noise.