Apparatuses, methods, systems, and program products are disclosed for gesture detection. A method includes detecting an auditory cue associated with a predefined gesture based on input received from one or more sensors. The method includes detecting a gesture in response to the auditory cue based on gesture input received from the one or more sensors. The method includes performing an action associated with the detected gesture in response to determining the detected gesture is the predefined gesture associated with the auditory cue.