Project Hope is an Image, Speech Recognition and Speech Synthesis system. It aims to aid people suffering from hearing and orating /vocal impairments.

Often people suffering from such disability have normal vision and therefore they are able to communicate through sign or gestures. This system through a webcam converts signs into text. The other person who may not know sign language can read this text. It can also be heard through text to speech. Further, when the other person speaks, the system will convert into a text which the deaf and dumb person can read,
Presently the system supports English. The device consists of a wearable camera along with speaker. The vocally disabled person can keep his hand in front of the camera and make gestures using sign language. The camera may capture the gestures and the onboard electronic system will identify and convert the gestures into text. The Onboard voice synthesizer will convert the text into voice. For the hearing disabled the onboard system may record the external voice and convert the same into text that will be displayed for the user.

The device may be lightweight and therefore the user may wear the system on his body. The innovators are also in process of developing a Gestural API, so those using this platform can directly proceed to make use of the platform’s functionality. The team needs support to make the functionalities more smooth, develop viable prototypes and take it to market.

Saurabh Saket and Rahul Ranjan , Bhutta College of Engineering & Technology, Ludhiana
Punjab Technological University

Project Guide: Er Inderdeep Singh Grewal