Speech enhancement for binaural hearing aids based on blind source separation

The availability of wireless technologies leads from monaural or bilateral hearing aids to binaural processing strategies. In this paper, we investigate a class of blind source separation (BSS)-based speech enhancement algorithms for binaural hearing aids. The blind binaural processing strategies are analyzed and evaluated for different scenarios, i.e., determined scenarios, where the number of sources does not exceed the number of available sensors and underdetermined scenarios, where there are more active source signals than microphones which is typical for hearing aid applications. These blind algorithms are an attractive alternative to beamforming as no a-priori knowledge on the sensor positions is required. Moreover, BSS algorithms have the advantage that their optimization criteria are solely based on the fundamental assumption of mutual statistical independence of the different source signals.