Search

Independent component analysis (ICA) is a multivariate data analysis method that, given a linear mixture of statistical independent sources, recovers these components by producing an unmixing matrix. Stemming from a more general problem called blind source separation (BSS), ICA has become increasingly popular in recent years with several excellent books (e. g. Cichocki and Amari 2002; Haykin 2000; Hyvarinen et al. 2001) and a large number of papers being published. Its attractiveness is explained by its relative simplicity as well as from a large number of application areas (Haykin 2000). For example, ICA has been successfully employed in sound separation (Lee 1998), financial forecasting (Back and Weingend 1997), biomedical data processing (Lee 1998), image filtering (Cichocki and Amari 2002), and remote sensing (Tu et al. 2001). While in many of these applications, the problems do not exactly fit the required setting, ICA based algorithms have been shown to be robust enough to produce accurate solutions. In fact, it is this robustness that has fueled the theoretical advances in this area (Haykin 2000).

This paper describes a technique to support user interaction in a hierarchical menu, based on spatial sound separation. A complex menu structure is represented in space using a limited number of sound positions obtained by stereo panning or 3-D audio processing techniques. Spatial organisation of menu items can be designed in a logical way to provide navigation cues to the user, independent of the menu item nature. Two different strategies for menu presentation and interaction are described and compared in this paper. Finally, an application of this technique to the navigation in a large music collection is considered. This case study is an interesting example of usage situation for which eyes-free interaction would be useful, for instance on a portable audio player using headphones and a small remote control.