Blind source separation (BSS) is the approach taken to estimate original source signals using only the information of the mixed signals observed in each input channel. This technique is based on unsupervised filtering in that the source-separation procedure requires no training sequences and no a priori information on the directions-of-arrival (DOAs) of the sound sources. Owing to the attractive features of BSS, much attention has been paid to the BSS technique in many fields of signal processing. One promising example in acoustic signal processing is a humanoid robot auditory system [1], i.e., separation of binaural mixed signals observed at the ears of the robot, which constructs an indispensable basis for intelligent robot technology [2], [3]. In recent works of BSS based on independent component analysis (ICA) [4], various methods have been proposed for acoustic-sound separation [5], [6], [7], [8]. In this paper, we mainly address the BSS problem under highly reverberant conditions which often arise in many practical audio applications. The separation performance of the conventional ICA is far from being sufficient in such a case because too long separation filters is required but the unsupervised learning ofWe newly propose a real-time two-stage blind source separation (BSS) for binaural mixed signals observed at the ears of humanoid robot, in which a Single-Input Multiple-Output (SIMO)-model-based independent component analysis (ICA) and binary mask processing are combined. SIMO-model-based ICA can separate the mixed signals, not into monaural source signals but into SINIO-model-based signals from independent sources as they are at the microphones. Thus, the separated signals of SIMO-model-based ICA can maintain the spatial qualities of each sound source, and this yields that binary mask processing can be applied to efficiently remove the residual interference components after SIMO-model-based ICA. The experimental results obtained with a human-like head reveal that the separation performance can be considerably improved by using the proposed method in comparison to the conventional ICA-based and binary-mask-based BSS methods.
