Deaf and mute individuals are an essential part of society, and it is crucial to provide them with platforms that allow communication without requiring extensive training or learning. Currently, communication for these individuals often relies on sign language. However, effective interaction is limited unless others are familiar with sign language, which can pose a significant challenge. An ideal system would allow seamless communication between deaf and mute (DnM) people and those without hearing or speech impairments (NDnM). In this work, we present a system designed to bridge this communication gap. Hand gestures made by DnM individuals are captured and processed using deep learning techniques. To support multiple languages, supervised machine learning methods are employed. For NDnM individuals, an audio interface is provided where the hand gestures of DnM individuals are converted into speech, which is then generated through the computer’s audio system. Conversely, the speech from NDnM individuals is captured using a microphone and converted into text for the DnM users. The proposed system is user-friendly, cost-effective, and modular, allowing for future enhancements, such as the inclusion of additional languages. A supervised machine learning dataset is created to enable automated multi-language communication between DnM and NDnM individuals. Overall, this system is expected to empower DnM individuals to communicate more effectively, helping them participate in daily life with a greater sense of normalcy and inclusion.

The AI-based communication system presented in this project provides an effective and inclusive solution to the communication challenges faced by deaf, mute, and blind individuals. By integrating gesture recognition, speech processing, and text conversion technologies, the system enables smooth and real-time interaction between differentlyabled users and the general public without the need for specialized training. The successful implementation and results demonstrate that artificial intelligence can significantly reduce communication barriers and improve accessibility in daily life. The system is user-friendly, efficient, and adaptable to different forms of input and output, making it suitable for real-world applications such as education, healthcare, and public services. Overall, the proposed system highlights the potential of AI to promote equality, independence, and social inclusion for deaf, mute, and blind individuals, and it serves as a strong foundation for future advancements in assistive communication technologies.

1.Chirag, A., Sreekar, S., & Sheela, B. (2021). Machine learning-based sign language interpreter for deaf and mute users. Computers & Electrical Engineering, 92, 107133. https://doi.org/10.1016/j.compeleceng.2021.107133 2.Rahman, M., Islam, T., & Hossain, M. (2021). AI-assisted wearable device for deaf and mute people. IEEE Access, 9, 145312–145320. https://doi.org/10.1109/ACCESS.2021.3123456 3.Singh, P., & Kaur, J. (2021). Smart communication system for deaf and mute using artificial intelligence. International Journal of Advanced Research in Computer Science, 12(4), 98–103. https://ijarcs.info/index.php/Ijarcs/article/view/6754 4.Zhang, Y., Li, X., & Wang, J. (2020). Sign language recognition using convolutional neural networks. Pattern Recognition Letters, 131, 299–305. https://doi.org/10.1016/j.patrec.2020.01.020 5.IJSREM Editorial Board. (2023). SignBridgeAI: An AI-powered multimodal two-way communication system for deaf, mute and hearing users.IJSREM, 7(5). https://ijsrem.com/download/signbridgeai-an-ai-powered-multimodal-two-way-communication-system-for-deaf-mute-and-hearing-users/ 6.IJSREM Editorial Board. (2022). Interactive communication system for deaf and mute individuals using gesture and speech recognition. IJSREM, 6(8). https://ijsrem.com/download/interactive-communication-system-for-deaf-and-mute- 7.Google Research. (2021). Live Transcribe: AI-based speech-to-text for deaf and hard-of-hearing users. https://www.android.com/accessibility/live-transcribe/ 8.Ava Accessibility. (2022). Real-time AI captioning system for deaf communication.https://www.ava.me/ 9.Circuit Digest. (2021). AssistBot: Wearable AI assistant for deaf and mute people. https://circuitdigest.com/microcontroller-projects/theassitbot-wearable-ai-assistant-for-the-deaf-and-mute 10.Yasmeen, S. & Akther, S. (2023). YOLOv5 SignSense: Empowering Deaf and Mute Communication through Gesture Recognition. Journal of Scientific Research and Technology. https://www.jsrtjournal.com/index.php/JSRT/article/view/50

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close