International Journal of Scientific and Research Publications, Volume 7, Issue 12, December 2017 90 ISSN 2250-3153 www.ijsrp.org Communication between Deaf-Dumb People and Normal People: Chat Assist L. Jayatilake, C. Darshana, G. Indrajith, A. Madhuwantha and N. Ellepola Abstract- Chat applications have become a powerful media that assist people to communicate in different languages with each other. There are lots of chat applications that are used different people in different languages but there are not such a chat application that has facilitate to communicate with sign languages. Sign languages are used by deaf and dump people to communicate among them but those Sign languages vary from nation to nation as American Sign Language, British Sign language, Japanese Sign language etc. The developed system has based on Sinhala Sign language. The system has included four main components as text messages are converted to sign messages, voice messages are converted to sign messages, sign messages are converted to text messages and sign messages are converted to voice messages. Google voice recognition API has used to develop speech character recognition for voice messages. The system has trained for the speech and text patterns by using some text parameters and Signs of Sinhala Sign language is displayed by emoji. Those emoji and signs that are included in this system will pave a new way for the normal people to be more close to hearing disable people and also hearing disable people to be more close to normal people. Index Terms- Sinhala Sign Language, Google voice recognition API, Gifs, Text parameters, Deaf dump people I. INTRODUCTION or years scientists have worked to find a way to make it easier for deaf and dumb people to communicate. Researchers have used image recognition to translate sign language into ‘readable language’ and the tool could one day be used on smartphones. There were some researches about translation of sign language to human readable language. This research was also about finding a proper method to translate sign language to human readable language but in this research, the research team expected to develop a chat application that translates human voice and texts to sign language. This is an android based chatting application that can use anytime anywhere with assist of internet. A sign language is a language which chiefly uses manual communication to convey meaning, as opposed to acoustically conveyed sound patterns. This can involve simultaneously combining hand shapes, orientation and movement of the hands, arms or body, and facial expressions to express a speaker's thoughts. Sign languages share many similarities with spoken languages (sometimes called "oral languages"), which depend primarily on sound, and linguists consider both to be types of natural language. Although there are some significant differences between signed and spoken languages, such as how they use space grammatically, sign languages show the same linguistic properties and use the same language faculty as do spoken languages. Sign languages are different according to the country and nations. The system has developed for Sinhala sign language. The Sinhala Sign Language contains different set of signs and those signs were studied by group member. Voice has translated to the text and then translate to the sign language is another component of this project. That component has added for make more efficient real time face to face chatting feature to this system. This research not only translates voice and text to the sign language. Totally this research scope was expanded up to four main areas. Those main areas were translating voice to the sign language, translating sign to the voice, translating text to the sign language and translating sign language to the text. Another important aspect of this research was performance and accuracy. The system has focused on voice and text and it was needed to clarify whether voice to sign translation consumes more time. If it does not consume more time, then we needed to research about accuracy of translated sentences and utterances. The main research problem was lacking of any communication media between hard of hearing people and normal people. Accordingly, the identified research questions were how to identify the signs in Sinhala Sign Language, how to design a localized sign language keyboard? How to convert voice or text to the sign language and vice versa. The main objective of this application was, reduce the communication gap between normal people and deaf-dumb people by giving some help to deaf-dumb people to do their works at their convenient and also allowing them to chat with ease by using this tool. The project team searched and found some applications that support some of the functionalities as listed. Examples are Signspeak, V2S, Sign Mobile and Hand Talk. They all were designed for some kind of communication and learning process. There was no chat application to communicate with deaf-dumb people and normal people. Thus, our group has developed an application that can cover the application of all the area of deaf- dumb people. II. LITERATURE REVIEW There are many research have begun carried out in this research area. Oi Mean Foong et al has discussed about sign language translation system using Speech and Image processing technique in “V2S: Voice to Sign Language Translation System for Malaysian Deaf People”[1]. The Advantage is Voice (English Language) to sign language of Malaysia. Main disadvantage is System first needs to be trained with speech pattern based on some generic spectral parameter set. F