An Image-To-Speech iPad App

Abstract

We describe an iPad app which assists in language acquisition and development. Such an application can be used by clinicians for human developmental disabilities. A user drags images around on the screen. The app generates and speaks random (but sensible) phrases that matches the image interact. For example, if a user drags an image of a squirrel onto an image of a tree, the app may say "the squirrel ran up the tree." A key challenge is the automated creation of "sensible" English phrases, which we solve by using a large corpus and machine learning.