An adaptive microphone array topology for target signal extraction with humanoid robots

In this paper, an unsupervised adaptation algorithm for the microphone array topology of a humanoid robot is proposed, so that the spatial filtering performance is improved. In the given exemplary case, the target suppression (`blocking´) performance of a geometrically-constrained BSS (GC-BSS) algorithm is shown to improve by the adaptation of the array topology. As a decisive feature, an online performance measure for blind source separation is introduced which provides a robust and reliable estimate of the instantaneous signal separation performance based on currently observable data. Experimental results based on simulated environments confirm the efficacy of the concept.