Sign Language Representation using Virtual Characters with 3D Animation

Sign language is a communication system that encompasses bodily gestures, primarilyutilized within the deaf community. Due to its limited prevalence, information from books, newspapers, and videos is often not translated or represented in sign language. This situation createschallenges for deaf individuals in acquiring information, as well as in their learning and interactionswith hearing individuals. Historically, the conversion between spoken language and sign languagerelied entirely on interpreters, a limited resource that is not always readily available. Currently, employing technology to convert spoken language into sign language presents a modern and convenientalternative. This linguistic conversion typically involves two steps: first, converting spoken languageinto text that adheres to the grammatical structure of sign language; second, representing this textthrough the corresponding gestures. This paper proposes a method for representing sign languageusing 3D characters to address the latter step. The method constructs a 3D skeleton motion for eachword or phrase from input text in sign language grammar. Subsequently, the motion data of words isprocessed and interconnected to animate a 3D virtual character for the complete sentence representation. We have applied the proposed method to represent Vietnamese Sign Language (VSL) using 3Dvirtual characters. The results were assessed by experts in sign language, yielding promising findingsthat suggest the practical applicability of the proposed methodology.