A Corpus for Verifying American Sign Language During Game Play by Deaf Children

The CopyCat project was designed to develop an interactive educational adventure game to help deaf children acquire language skills. The main goals of the project are to improve the language and memory abilities of deaf signing children, advance basic research in computer-based sign language recognition, and design an efficient language interaction model in order to assist in the language learning of deaf children. The CopyCat project was begun as a collaboration between Georgia Tech and the Atlanta Area School for the Deaf in 2004 and has been collecting ASL (American Sign Language) data since Spring of 2005. Since then we have collected 5829 signed phrases from over 30 children. In this paper we describe the evolution of the CopyCat system design, data collection methodology, and resulting corpus, as well as challenges and successes throughout the process.