InstantSL: A Sign Language Model to Support two-Way Communication between Aurally Impaired Communities with Others
Deshinta Arrova Dewi1, Harprith Kaur Rajinder Singh2, Mohammad Abbas Husaini3
1Deshinta Arrova Dewi, Faculty of Information Technology (FIT) INTI International University, Nilai, Malaysia.
2Harprith Kaur Rajinder Singh, Faculty of Information Technology (FIT) INTI International University, Nilai, Malaysia.
3Muhammad Abbas Husaini, Faculty of Information Technology (FIT) INTI International University, Nilai, Malaysia.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 401-406 | Volume-8 Issue-8, June 2019 | Retrieval Number: H6365068819/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Research works in Sign Language (SL) mostly give prominence to the SL detection and solve the complexity of the hand gesture alphabets. The other works focus on real-time SL recognition and solve various technical problems such as hand self-occlusion, limited resolution due to the sensor quality or others. However, lack of attention is given to the essence of two-way communication i.e. communication channel or platform that accommodate the need of aurally impaired people to speak with others in daily life. This paper introduces InstantSL, an alternative model of Sign Language (SL) application to overcome issues of two-way interaction among users who are familiar and unfamiliar with SL. In addition, the demand of more flexible SL becomes significant along with the usage of a mobile application that has been growing rapidly and makes current SL no longer reliable to run only on local devices like desktop and laptop. Hence, InstantSL proposes a cohesive approach that not only covers on technologies of SL recognition like machine learning for detection accuracy but also voice translation for user-friendliness and mobile operating system Android for flexibility. Promoting interactive communication in delivering messages from SL users and be understood by others are always challenging. Therefore, InstantSL is designed to run as an instant messaging (video call) for remote and face-to-face communication. The aim is to intensify the interaction and conversation between SL users and non-SL users in anytime-anywhere when necessary.
Keyword: Sign Language, Machine Learning, Android, Instant Messaging.
Scope of the Article: Multimedia Communications.