• Sanchit Garg
• Priyam Parikh

This research focuses on the creation of a novel gadget that facilitates simultaneous two-way communication between American Sign Language (ASL) and speech. The primary objective of this technology is to enhance the smoothness and efficiency of communication for individuals who are deaf and/or mute, hence encouraging inclusiveness and facilitating contact. This gadget comprises a camera designed for the recognition of American Sign Language (ASL) gestures, a screen for displaying the results, and a microphone and speaker for communication with a typical human. The hardware components are interconnected by a unique 3D printed structure, while a machine learning algorithm incorporating sign recognition facilitates real-time communication. The entire system is controlled by a Raspberry Pi, which utilises a camera and microphone to receive input from two users: one who is deaf and/or silent, and one who can speak and listen. Subsequently, the AI model analyses the captured images of ASL signs to determine their corresponding speech content. It further employs Natural Language Processing (NLP) on both inputs to generate coherent and intelligible sentences. Subsequently, it employs speakers to audibly convey the communication of the impaired individual and visually displays American Sign Language (ASL) signals on a screen to represent the words of the able-bodied person. This type of bidirectional communication enables smooth integration into everyday activities with a high level of precision. This device has undergone rigorous testing in several scenarios, encompassing varying settings, lighting conditions, and noise levels. It consistently demonstrates exceptional accuracy across all situations. It serves to enhance the influence that can be achieved when combining hardware, software and machine learning.

sign language converter, speech converter, machine learning, Raspberry Pi, new product development, American Sign Language

"An intelligent tangible full duplex speech and sign language converter using Raspberry Pi and machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.K404-K414, June-2024, Available :http://www.jetir.org/papers/JETIR2406A49.pdf

"An intelligent tangible full duplex speech and sign language converter using Raspberry Pi and machine learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. ppK404-K414, June-2024, Available at : http://www.jetir.org/papers/JETIR2406A49.pdf