A gesture detection system having a gesture detection apparatus to detect a gesture of a user, and a mobile communication terminal that can communicate with the gesture detection apparatus, includes a storage unit to store first gesture data defining the gesture of the user, and audio or visual data associated with the first gesture data; an obtainment unit to obtain second gesture data representing the gesture of the user; a transmission unit to transmit the second gesture data to the mobile communication terminal; a determination unit to determine whether the gesture defined by the first gesture data is the same as the gesture represented by the second gesture data; a selection unit to select the audio or visual data associated with the first gesture data depending on the determination result; and an output unit to output the audio or visual data.