AN EYES-FREE USER INTERFACE CONTROLLED BY FINGER SNAPS
Sampo Vesa, Tapio Lokki · 2005
A novel way of controlling a simple user interface based on de-tecting and localizing finger snaps of the user is presented. The analysis method uses binaural signals recorded from the ears of the user. Transient sounds are first detected from a continuous au-dio stream, followed by cross-correlation based localization and simple band-energy ratio based classification. The azimuth plane around the user is divided into three sectors, each of which cor-responds to one of the three “buttons ” in the interface. As an ex-ample, the interface is applied for controlling the playlist of an MP3 player. The algorithm performance was evaluated using a real-world recording. While the algorithm looks promising, more research is needed before it is ready for commercial applications. 1.