• Nandhini V
• Indhumathi GK
• Ruth Christy J
• B. Rajalakshmi

Patients with severe speech and motor impairments, who are not able to speak, require specific human-computer interfaces to communicate with the world. Existing system uses flex sensors that fit to hand. The hand movements are monitored continuously and are converted to speech signals. These hand wearing sensors may cause uncomfortable to the patients. In our system we enhance the augmented reality techniques to allow differently abled people to interact with digital world. The proposed system uses a camera that captures sign movements of the patient and are processed using C# and Python programs to identify signs shown by the patient. Then the output is displayed using augmented assisted screen as text or speech. The proposed system has proved to be efficient in terms of speed and processing time compared to formal flex sensor systems. The proposed system thus reduces complex hardware components and is compatible to handle.

Augmented Reality, Machine learning, Python, Vuforia, dumb people

"Design of Sign to Speech Conversion System with Augmented Reality Assistant", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.149-154, May 2019, Available :http://www.jetir.org/papers/JETIRCU06031.pdf

"Design of Sign to Speech Conversion System with Augmented Reality Assistant", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp149-154, May 2019, Available at : http://www.jetir.org/papers/JETIRCU06031.pdf