A Framework for the Automatic Generation of Indian Sign Language

Abstract

Sign languages are visual-spatial natural languages having their own set of vocabularies, syntax and grammatical structures. Yet, designing machine translation system between spoken and sign languages generates a number of interesting challenges, mainly due to the difference in structure as well as modality of the source and target language pairs. This paper presents a rule-based framework for the English-To-Indian Sign Language machine translation system. The system can be used to disseminate information to the deaf people in India. The present system takes an English sentence as input, performs syntactic analysis, and represents the source language into an intermediate case frame representation. Finally, transfer grammar rules are used to generate the corresponding ISL sentence structure. As ISL does not have any written form, the final sentence is synthesized in terms of pre-recorded video streams. The prototype system has been primarily evaluated by the native signers of India. Our initial evaluation result shows a significant improvement over the existing baseline system.