Avatars help deaf people to understand online text and interact with websites

29 August 2014

Computer scientists from Saarbrücken, Germany are developing animated online characters to display text from web pages in sign language. In the long term, the aim is that deaf people could use the technique to communicate on online platforms via sign language. To do this, users would only need readily available devices.

Sign language was first acknowledged as a separate language in the sixties, which is quite recent. Similar to spoken language, it evolved from different cultural backgrounds. Every country has its own sign language with various dialects, which are based on different rules than the spoken language. For the deaf, sign language is their native language. Therefore, it is not easy for them to learn spoken language, which is why they may struggle with text reading and comprehension even after their graduation.

Although several websites provide video clips in which sign language interpreters translate the text, much Internet content remains cryptic for the deaf community. To inform deaf people quickly in cases where there is no interpreter on hand, researchers are working on a novel approach to provide content: avatars. These animated characters could be used in the context of announcements at train stations, or on websites.

“We have already gained initial experiences with avatars”, explains Alexis Heloir, who is the leader of the Sign Language Synthesis and Interaction research group at the Multimodal Computing and Interaction Cluster of Excellence and also a researcher at the German Center for Artificial Intelligence. “If we try to animate them like human beings, deaf people have issues with understanding the avatars.”

The researcher assumes that this is caused by the greater variety of emotional expressions of humans compared to avatars. To deal with that problem, Alexis Heloir and Fabrizio Nunnari create avatars that make more accentuated movements. The researchers are closely cooperating with Peter Schaar, who is deaf and is a lecturer for German sign language at the Saarland University Language Center and the College of Engineering and Commerce in Saarbrücken.

“Our method should be inexpensive and easy to use so that every member of the deaf community will be able to use it”, says Fabrizio Nunnari. To capture the motions of deaf people, the scientists make use of affordable cameras and sensors that are typically used by teenagers for computer games. A computing method transfers the movements of the entire body onto the avatar. In the long term, the researchers want to create a collection of short sign language sequences that can be used by the deaf to interact on the web.

Computer scientists from Saarbrücken in Germany have developed an approach where animated online characters (upper row) display content in sign language.
The scientists collaborate with Peter Schaar (lower row) who is deaf and a lecturer for sign language. Credits: AG Heloir

More information

See the Sign Synthesis project website: http://slsi.dfki.de/