Sign Language Mediator

The current era is the boom of technology. Each area of field has its tremendous effects in it which are upgrading on a daily basis. Technology keeps increasing the quality of life everywhere and for everyone, except for those with a hearing-impairment. A Hearing-Impaired individual is a person who

Project Title

Sign Language Mediator

Project Area of Specialization

Artificial Intelligence

Project Summary

The current era is the boom of technology. Each area of field has its tremendous effects in it which are upgrading on a daily basis. Technology keeps increasing the quality of life everywhere and for everyone, except for those with a hearing-impairment. A Hearing-Impaired individual is a person who cannot hear (and in some cases speak or both). The difference between the two is, a hearing-impaired individual cannot hear (and speak in some cases), which increases the communication gap. Due to this they(individuals with a hearing-impairment) cannot have their voice heard in society. Because of this gap of communication, it is hard for people with no hearing-impairment to communicate with those who have no hearing-impairment. The only way for them to communicate is sign language. Sign language is the earliest way to communicate in the universe when there were no appropriate language so this sign language is considered as the best supportive and innovative way for education to present and catch the words what they were trying to say and what others were saying to them .Each country and nation has its own standards. It generally based on the movements of hands, fingers, arms and body as well as facial expression which expresses their feelings and words. Each sign generates its own word which was set up by the standards of the country. A combination of words make a sentence which completely defines as the meaning of their talk.For the hearing-impaired person community, we try to improve their quality of life and provides an application to reduce the communication gap with normal persons. It takes a fair amount of time and effort to learn methods to communicate effectively with hearing impaired individuals. Learning sign language or learning lip reading is not an easy task, especially for people who have no prior experience in corresponding with Deaf persons. Therefore, to overcome this problem, an easier form of communication is required, and this is where our mobile application comes in. It is a digital solution to an age-old problem. This mobile application skips the learning phase and mediates a two-way communication with the deaf. All of this is done through Image and Audio processing. Image processing is used as it the most cost effective way of tackling this issue, and natural language processing is used to capture the other users Audio input

Project Objectives

1. To deliver a cost effective solution to an age-old problem.

2. To achieve high accuracy in translating sign language to speech and vice versa.

3. To increase the quality of life for those with hearing impairment.

Project Implementation Method

The problem can be broken down to 2 things, Translating Sign Language into Speech, and Translating Speech into Sign Language. The Former is done by recording multiple images sending them to a cloud computer, where using a neural network categorizes the Signs and sends back a Sentence as a translation. The Latter is done by converting Speech to a string of text, removing irrelevant words, finding the corresponding Signs to the string of text, and sending back the compilation of the signs

Benefits of the Project

1. Conversing with the deaf would be so much easier for people without the need of a translater.

2. A deaf person would be able easily tell their problem regarding any issue easily.

Technical Details of Final Deliverable

1. The user will select either Sign-to-Speech mode OR Speech-to-Sign mode to be opened as the default mode (when the application starts for the first time).

2. The user can switch between the two modes In Sign-to-Speech mode

3. In Sign-to-Speech mode the user will point the camera towards the person communication in Sign-language, the images will be sent to the cloud for finding the meaning of the corresponding gestures.

4. In Speech-to-Sign mode the user will record the voice of the other person speaking and send the words to the cloud server for finding the Gestures to the corresponding words.

5. The translated data, then is sent back to the user in one of two ways:  Audio & String for translating Sign Language

Final Deliverable of the Project

Software System

Core Industry

IT

Other Industries

IT

Core Technology

Artificial Intelligence(AI)

Other Technologies

Artificial Intelligence(AI)

Sustainable Development Goals

Reduced Inequality, Peace and Justice Strong Institutions, Partnerships to achieve the Goal

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com