To augment the task of navigation and orientation of blind individuals, a new travel aid uses 3D scene sonification to present information about the environment using nonverbal audio. The model is composed of two classes of objects: obstacles and planes. The algorithm uses scene image segmentation, personalized spatial audio, musical tones, and sonar-like sound patterns. Individually measured head-related transfer functions were used to provide users with the illusion of sounds originating from the locations of sonified scene elements. Using a segmented and parametric description overcomes the sensory mismatch between visual and auditory perception. In a pilot study using both blind and sighted volunteers, subjects were able to utilize the prototype for spatial orientation and obstacle avoidance after a few minutes of training, attaining 90% accuracy in estimating the direction and depth of obstacles.
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.