The ventriloquist effect results from near-optimal bimodal integration

Ventriloquism is the ancient art of making one's voice appear to come from elsewhere, an art exploited by the Greek and Roman oracles, and possibly earlier [1]. We regularly experience the effect when watching television and movies, where the voices seem to emanate from the actors' lips rather than from the actual sound source. Originally, ventriloquism was explained by performers projecting sound to their puppets by special techniques [1], but more recently it is assumed that ventriloquism results from vision "capturing" sound [2-5]. In this study we investigate spatial localization of audio-visual stimuli. When visual localization is good, vision does indeed dominate and capture sound. However, for severely blurred visual stimuli (that are poorly localized), the reverse holds: sound captures vision. For less blurred stimuli, neither sense dominates and perception follows the mean position. Precision of bimodal localization is usually better than either the visual or the auditory unimodal presentation. All the results are well explained not by one sense capturing the other, but by a simple model of optimal combination of visual and auditory information.