Project
Overview
Our
goal is to translate English to American Sign Language,
the language of the Deaf in North America. American Sign
Language is different from English, with its own unique
grammar. It is at least as different from English as any
other natural language.
An
automatic English to ASL translator would give Deaf people
greater access to the hearing world. Currently we are
developing tools to generate ASL as animation in response
to spoken English.
Notes
on American Sign Language
American
Sign Language (ASL) is the preferred language of the Deaf
in North America. It is a visual/gestural language, using
handshape, position, palm orientation, movement and nonmanual
signals. There is no one-to-one correspondence to English, as
certain signs become complete phrases or sentences in English.
A manual alphabet is used to
fingerspell a proper noun
before introducing a sign for the noun. It is also used
for technical terms and loan words.
Currently,
human ASL translators are essential for effective
communication between Deaf and hearing presenters and
their audiences. Good ASL translators are in high demand
and are not always available for extremely short
interactions. That means that communication
among hearing and Deaf may be impaired or nonexistent,
to the detriment of both groups.
Development
of an automated synthesizer for ASL will make more
information accessible to Deaf people on a more economical
basis. It has the potential to allow the deaf to participate in and more
fully understand the exchanges among a hearing audience
in classrooms, meetings, and other venues. The synthsizer
will also provide Deaf people with a better tool than
English documents or notes for understanding content.
Given
that ASL is the preferred language of over a 500,000 people
in the United
States, the project team feels that a very large group
of people will benefit.
