Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM61146
Volume:
10 |
4 |
April 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Engineering
Rizvi College of Engineering
Department of Computer Engineering
Rizvi College of Engineering
Department of Computer Engineering
Rizvi College of Engineering
Department of Computer Engineering
Rizvi College of Engineering
Department of Computer Engineering
Rizvi College of Engineering
Communication barriers faced by speech-impaired individuals continue to limit their ability to interact effectively in daily life, especially in multilingual environments like India. Most existing communication aids are either expensive, bulky, or restricted to a single language, making them unsuitable for widespread use. The NEUROSYNAPSE smart glove is designed as a wearable assistive device that converts hand gestures into meaningful speech. The glove is equipped with flex sensors and an inertial measurement unit (IMU) to capture finger movements and hand orientation accurately. These sensor inputs are processed by an ESP32 microcontroller, where a trained machine learning model classifies gestures into predefined words. A word-buffering mechanism collects individual words as gestures are performed; when a short pause is detected, these words are combined to form a complete sentence. The sentence is then sent to a cloud-based translation service, allowing conversion into the desired language. Finally, the translated sentence is converted into speech using a text-to-speech module and played through a speaker. Overall, NEUROSYNAPSE integrates hardware, machine learning, and cloud technologies into a compact, cost-effective solution that enhances accessibility, independence, and social inclusion for speech-impaired individuals.
KEYWORDS
The NEUROSYNAPSE smart glove successfully demonstrates a practical and innovative solution to bridge the communication gap faced by speech-impaired individuals. By converting hand gestures into meaningful words and subsequently into audible speech, the system enables real-time and effective interaction. The integration of gesture recognition, machine learning, sentence formation, and multilingual translation creates a complete communication pipeline. The use of a word-buffering mechanism for sentence construction improves the natural flow of communication, while multilingual support makes the system adaptable to diverse real-world environments. Although the current implementation is limited to a predefined gesture set and requires internet connectivity for translation, it provides a strong foundation for future development. Future enhancements include: (1) expanding gesture vocabulary toward full sign language support; (2) training on a larger, more diverse user dataset and exploring lightweight deep learning models; (3) implementing offline translation and TTS to eliminate cloud dependency; (4) developing a mobile application interface for enhanced user experience; and (5) bidirectional communication (speech-to-gesture feedback). These improvements would evolve NEUROSYNAPSE into a scalable, high-impact assistive ecosystem.
[1] A. Kadambi et al., “SignAloud: Translating American Sign Language to Speech,” Univ. of Washington Research Project, 2016. [2] EnableTalk Team, “EnableTalk Gloves for DeafMute Communication,” Microsoft Imagine Cup Project, 2012. [3] P. Kumar, R. Sharma, and S. Verma, “A Wearable Smart Glove for Hand Gesture Recognition and Sign Language Classification,” Int. J. Eng. Res. & Technol. (IJERT), vol. 11, no. 6, pp. 845–850, 2022. [4] R. Singh, D. Patel, and K. Mehta, “Smart Glove for Sign Language Recognition Using Machine Learning Techniques,” Int. J. Adv. Comput. Sci. Appl. (IJACSA), vol. 14, no. 2, pp. 210–216, 2023. [5] X. Chen, Y. Liu, and H. Zhao, “GloSign: GloveBased Wearable Devices for Sign Language Interpretation,” IEEE Access, vol. 11, pp. 45678– 45689, 2023. [6] T. Ahmed, M. Khan, and S. Ali, “Sign Language Recognition System Using Wearable Sensors,” Int. J. Comput. Appl., vol. 175, no. 12, pp. 15–20, 2020. [7] S. Patel, R. Shah, and P. Desai, “Real-Time Hand Gesture Recognition Using Deep Learning Approaches,” Procedia Comput. Sci., vol. 167, pp. 254–263, 2022. [8] H. Wang, J. Li, and Z. Chen, “A Survey of IoTBased Smart Systems for Gesture and Activity Recognition,” IEEE Internet Things J., vol. 7, no. 5, pp. 4215–4232, 2020. [9] C. M. Bishop, Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2006. [10]A. Géron, Hands-On Machine Learning with ScikitLearn, Keras, and TensorFlow, 2nd ed. Sebastopol, CA, USA: O'Reilly Media, 2019
Publication Date
4/23/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...