Toward a new transcription model in XML for Sign Language Processing based on gloss annotation system

Abstract

Representation of Sign Language (SL) in written form is required for the generation via avatar or any other tools of synthesis. Although, this problem can be solved by developing a new transcription system based on one of existing annotation like gloss. In this context, we present a new transcription system for the American Sign Language (ASL) based on gloss annotation system. Initially, a descriptive study of glosses will be detailed to clarify the transcription system. In a second step, we describe our system following an XML format, to facilitate the interpretation of coded data that we assign. Finally, we propose our API in Java programming language to build an annotation gloss as XML to create corpus or to manipulate a virtual signer as an intermediate language. Also, the new transcription system can be useful for any Sign Language Processing tool like machine translation or building n-gram models.