Extension of Hidden Markov Model for Recognizing Large Vocabulary of Sign Language

Computers still have a long way to go before they can interact with users in a truly natural fashion. From auser’s perspective, the mostnatural way to interact with a computer would be through a speech and gestureinterface. Although speech recognition has made significant advances in the past ten years, gesturerecognition has been lagging behind.Sign Languages (SL) are the most accomplished forms of gesturalcommunication. Therefore, their automatic analysis is a real challenge, which is interestingly implied to theirlexical and syntactic organization levels. Statements dealing with sign language occupy a significant interestin the Automatic Natural Language Processing (ANLP) domain. In this work, we are dealing with signlanguage recognition, in particular of French Sign Language (FSL). FSL has its own specificities, such as thesimultaneity of several parameters, the important role of the facial expression or movement and the use ofspace for the proper utterance organization. Unlike speech recognition, Frensh sign language (FSL) eventsoccur both sequentially and simultaneously. Thus, the computational processing of FSL is too complex thanthe spoken languages. We present a novel approach based on HMM to reduce the recognition complexity