Understanding Prosodic Pauses in Sign Language from Motion-Capture and Video-data

Abstract

In this paper, we deal to understand how the conversational agent (avatar) can achieve human-friendly Sign Language interpretations to improve web accessibility to people with hearing disability and hearing impairment with a low level of literacy. One of the key element in Sign Language is the prosodic pauses during a conversation in Sign Language applied in a machine translation or in real-time interpretation using assistive technologies. We introduce the importance of the prosodic pauses in Sign Language through several examples. After that, we present an approach to recognize prosodic pauses from Motion-Capture and Video-data based on the sentence syntax and other grammatical features.